import geopandas as gpd import matplotlib.pyplot as plt from geopy.geocoders import…
- User
import geopandas as gpd import matplotlib.pyplot as plt from geopy.geocoders import Nominatim import requests from bs4 import BeautifulSoup import re from tqdm import tqdm from shapely.geometry import Point import json import pandas as pd import numpy as np import rasterio import warnings from scipy.spatial import cKDTree from rasterio.transform import from_origin from rasterio.features import rasterize from rasterio.warp import reproject, Resampling import os import rasterio.mask import matplotlib.colors as mcolors import matplotlib.patheffects as patheffects from pykrige.uk import UniversalKriging from sklearn.ensemble import RandomForestRegressor from sklearn.preprocessing import StandardScaler from datetime import datetime import pytz import math import glob
os.environ['PROJ_LIB'] = r'C:\Users\Lenovo\Documents\conda\Library\share\proj'
warnings.filterwarnings("ignore")
Keywords to remove
keywords_to_remove = [ r"(centrum)", "rondo", "most", "Obwodnica", "obwodnica I", "obwodnica II", "obwodnica", "- Zawiszyn", "OUD Węzeł", "PPO", "Węzeł", "N (wąwóz)", "S (most)", "stacja", "z pomiarów", "min", "max", "średnia" ]
def clean_station_name(station_name): pattern = re.compile("|".join(keywords_to_remove), re.IGNORECASE) cleaned_name = pattern.sub("", station_name).strip() return cleaned_name
def get_masovian_boundary(): url = "https://raw.githubusercontent.com/ppatrzyk/polska-geojson/master/wojewodztwa/wojewodztwa-medium.geojson" # Fetch the content using requests response = requests.get(url) if response.status_code == 200: data = response.json() # Set the CRS to EPSG:4326 when creating the GeoDataFrame gdf = gpd.GeoDataFrame.from_features(data["features"], crs="EPSG:4326") masovian = gdf[gdf['nazwa'] == 'mazowieckie'] return masovian else: print(f"Error fetching GeoJSON data: {response.status_code}") return None
Global variable for Masovian boundary
masovian_boundary = get_masovian_boundary()
def is_in_masovian(lat, lon): point = gpd.GeoSeries([Point(lon, lat)], crs="EPSG:4326") masovian_geom = masovian_boundary.to_crs(epsg=2180).reset_index(drop=True) point_projected = point.to_crs(epsg=2180) return masovian_geom.contains(point_projected.buffer(100)).values[0]
def fetch_traxelektronik_data(): url = 'https://www.traxelektronik.pl/pogoda/zbiorcza.php?RejID=10' response = requests.get(url) soup = BeautifulSoup(response.text, 'html.parser')
stations = [] temperatures = [] table_rows = soup.find_all('tr')[2:] for row in table_rows: columns = row.find_all('td') if len(columns) > 1: station = columns[0].get_text(strip=True) temperature = columns[1].get_text(strip=True) if temperature != "-": stations.append(station) # Keep original station names temperatures.append(temperature) return stations, temperaturesdef fetch_netatmo_data(): url = "https://api.netatmo.com/api/getpublicdata" params = { "lat_ne": 53, "lon_ne": 22, "lat_sw": 51, "lon_sw": 19, "required_data": "temperature", "filter": "true", "access_token": "66e1e80975134797710422cd|e9d1a7fa73c25e43e907720abc987649" }
response = requests.get(url, params=params) if response.status_code != 200: print(f"Error fetching Netatmo data: {response.status_code}") return [], [], [] data = json.loads(response.text) stations = [] temperatures = [] coordinates = [] # List of cities to exclude excluded_cities = ["Płońsk", "Łochów"] for station in data.get('body', []): place = station.get('place', {}) location = place.get('location') if location: lon, lat = location if is_in_masovian(lat, lon): city = place.get('city', 'Unknown') if city in excluded_cities: # Skip this station continue for module, module_data in station.get('measures', {}).items(): if 'temperature' in module_data.get('type', []): res = module_data.get('res', {}) if res: latest_timestamp = max(res.keys()) temperature = res[latest_timestamp][0] stations.append(city) temperatures.append(temperature) coordinates.append((lat, lon)) break return stations, temperatures, coordinatesdef fetch_imgw_data(): url = "https://rafalraczynski.com.pl/imgw/dane-imgw/getJSON.php?type=table&province=14&sort=temp&order=asc" response = requests.get(url) if response.status_code == 200: data = response.json() else: return [], [], []
target_stations = [ "ANDRZEJEWO", "BORKOWO", "CZARNOWO", "KAZANÓW", "RUSZKOWICE", "RYBIENKO", "RZĄŚNIK WŁOŚCIAŃSKI", "WIELGOLAS" ] stations = [] temperatures = [] station_ids = [] for item in data: statName = item.get('statName') temp = item.get('temp') if statName and temp and statName.upper() in target_stations: stations.append(statName) temperatures.append(temp) station_ids.append(item.get('statId', 'Unknown')) return stations, temperatures, station_idsdef get_coordinates(station_name, geolocator): try: location = geolocator.geocode(f"{station_name}, Masovian Voivodeship, Poland") if location: if is_in_masovian(location.latitude, location.longitude): return (location.latitude, location.longitude), False else: return None, False return None, False except Exception as e: return None, False
def clean_temperature(temp): cleaned_temp = re.sub(r'[↓↑\s]', '', temp) try: return float(cleaned_temp) except ValueError: return None
def remove_nearby_duplicates(trax_coords, trax_temperatures, netatmo_coords, netatmo_temperatures, distance_threshold=0.01): trax_points = np.array([(lon, lat) for station, (lat, lon) in trax_coords.items()]) netatmo_points = np.array([(lon, lat) for lat, lon in netatmo_coords]) trax_tree = cKDTree(trax_points)
netatmo_filtered_coords = [] netatmo_filtered_temperatures = [] for netatmo_point, netatmo_temp in zip(netatmo_points, netatmo_temperatures): distance, index = trax_tree.query(netatmo_point) if distance > distance_threshold: netatmo_filtered_coords.append(tuple(netatmo_point)) netatmo_filtered_temperatures.append(netatmo_temp) return netatmo_filtered_coords, netatmo_filtered_temperaturesdef hillshade(array, azimuth=315, angle_altitude=45): # Convert angles to radians azimuth_rad = np.radians(azimuth) altitude_rad = np.radians(angle_altitude)
# Calculate gradients in x and y directions x, y = np.gradient(array) # Calculate the slope and aspect slope = np.pi/2.0 - np.arctan(np.sqrt(x*x + y*y)) aspect = np.arctan2(-x, y) # Calculate shaded relief shaded = np.sin(altitude_rad) * np.sin(slope) + np.cos(altitude_rad) * np.cos(slope) * np.cos(azimuth_rad - aspect) # Normalize the shaded relief shaded = (shaded + 1) / 2 shaded = (shaded * 255).astype(np.uint8) return shadeddef read_and_process_modis_data(modis_day_folder, modis_night_folder): # Read and stack MODIS day data modis_day_files = sorted(glob.glob(os.path.join(modis_day_folder, '*.tif'))) modis_day_arrays = [] modis_day_transform = None for modis_file in modis_day_files: with rasterio.open(modis_file) as src: data = src.read(1) # Replace fill values with np.nan fill_value = src.nodata if fill_value is None: # If nodata is not set, check for common fill values data = np.where((data == -9999) | (data <= -1e20), np.nan, data) else: data = np.where(data == fill_value, np.nan, data) modis_day_arrays.append(data) if modis_day_transform is None: modis_day_transform = src.transform if modis_day_arrays: modis_day_stack = np.stack(modis_day_arrays) modis_day_data = np.nanmean(modis_day_stack, axis=0) else: modis_day_data = None
# Read and stack MODIS night data modis_night_files = sorted(glob.glob(os.path.join(modis_night_folder, '*.tif'))) modis_night_arrays = [] modis_night_transform = None for modis_file in modis_night_files: with rasterio.open(modis_file) as src: data = src.read(1) # Replace fill values with np.nan fill_value = src.nodata if fill_value is None: data = np.where((data == -9999) | (data <= -1e20), np.nan, data) else: data = np.where(data == fill_value, np.nan, data) modis_night_arrays.append(data) if modis_night_transform is None: modis_night_transform = src.transform if modis_night_arrays: modis_night_stack = np.stack(modis_night_arrays) modis_night_data = np.nanmean(modis_night_stack, axis=0) else: modis_night_data = None return (modis_day_data, modis_day_transform), (modis_night_data, modis_night_transform)def resample_modis_data(modis_data, modis_transform, dest_shape, dest_transform): if modis_data is None: return None else: # Resample to match the destination grid dest_modis_data = np.zeros(dest_shape, dtype=modis_data.dtype) reproject( source=modis_data, destination=dest_modis_data, src_transform=modis_transform, src_crs='EPSG:4326', dst_transform=dest_transform, dst_crs='EPSG:4326', resampling=Resampling.nearest # Use nearest to maintain original resolution ) # Replace zeros (from areas without data) with NaN dest_modis_data = np.where(dest_modis_data == 0, np.nan, dest_modis_data) return dest_modis_data
def plot_stations_with_boundary_and_interpolation( trax_stations, trax_temperatures, trax_coords, netatmo_stations, netatmo_temperatures, netatmo_coords, imgw_stations, imgw_temperatures, imgw_coords, modis_day_folder, modis_night_folder): import math # Define a function to compute the cooling effect of water bodies based on the hour of the day def compute_water_body_cooling_effect(hour): """ Computes the cooling effect of water bodies based on the hour of the day. Cooling effect varies between -1°C during the day to -4°C at night. """ # Normalize hour to range 0 to 24 hour = hour % 24 # Use a cosine function to model the cooling effect # Peak cooling at midnight (hour=0), minimal cooling at noon (hour=12) cooling_effect = -3.0 - 2.0 * math.cos((hour / 24) * 2 * math.pi) return cooling_effect
# Determine the current time in CET cet = pytz.timezone('CET') now_cet = datetime.now(cet) hour = now_cet.hour + now_cet.minute / 60.0 # Define daytime and nighttime hours day_start = 6 day_end = 18 is_daytime = day_start <= hour <= day_end # List of Traxelektronik stations to exclude during daytime exclude_trax_stations_daytime = [ 'Ceranów', 'Baranów', 'Drobin', 'Kamion', 'Mińsk Mazowiecki', 'Mostówka', 'Paplin', 'Pilawa', 'Stromiec', 'Węzeł Łabiszyńska', 'Węzeł Marki', 'Węzeł Marynarska', 'Wilchta', 'Wiśniew' ] # Clean the exclude list for matching exclude_trax_stations_daytime_cleaned = [clean_station_name(name) for name in exclude_trax_stations_daytime] # Map station names to cleaned station names cleaned_station_dict = {station: clean_station_name(station) for station in trax_stations} # Process Traxelektronik data trax_filtered_stations = [] trax_filtered_temperatures = [] trax_geometries = [] # Filter and clean Traxelektronik data for station, temperature in zip(trax_stations, trax_temperatures): cleaned_station = cleaned_station_dict[station] # Exclude certain stations during daytime if is_daytime and cleaned_station in exclude_trax_stations_daytime_cleaned: continue # Skip this station cleaned_temperature = clean_temperature(temperature) if cleaned_station in trax_coords and cleaned_temperature is not None: lat, lon = trax_coords[cleaned_station] trax_filtered_stations.append(cleaned_station) trax_filtered_temperatures.append(cleaned_temperature) trax_geometries.append(Point(lon, lat)) # Create GeoDataFrame for Traxelektronik data trax_gdf = gpd.GeoDataFrame({ 'Station': trax_filtered_stations, 'Temperature': trax_filtered_temperatures, 'Source': 'Traxelektronik' }, geometry=trax_geometries, crs="EPSG:4326") # Handle Netatmo data netatmo_filtered_coords = [] netatmo_filtered_temperatures = [] netatmo_filtered_stations = [] for station, temperature, coord in zip(netatmo_stations, netatmo_temperatures, netatmo_coords): if isinstance(temperature, (int, float)) and coord is not None: netatmo_filtered_coords.append(coord) netatmo_filtered_temperatures.append(temperature) netatmo_filtered_stations.append(station) if len(netatmo_filtered_coords) > 0: netatmo_geometries = [Point(lon, lat) for lat, lon in netatmo_filtered_coords] netatmo_gdf = gpd.GeoDataFrame({ 'Station': netatmo_filtered_stations, 'Temperature': netatmo_filtered_temperatures, 'Source': 'Netatmo' }, geometry=netatmo_geometries, crs="EPSG:4326") else: netatmo_gdf = gpd.GeoDataFrame(columns=['Station', 'Temperature', 'Source', 'geometry'], crs="EPSG:4326") # Handle IMGW data imgw_filtered_stations = [] imgw_filtered_temperatures = [] imgw_geometries = [] # Clean and process IMGW data for station, temperature in zip(imgw_stations, imgw_temperatures): cleaned_temperature = clean_temperature(temperature) if station in imgw_coords and cleaned_temperature is not None: lat, lon = imgw_coords[station] imgw_filtered_stations.append(station) imgw_filtered_temperatures.append(cleaned_temperature) imgw_geometries.append(Point(lon, lat)) # Create GeoDataFrame for IMGW data imgw_gdf = gpd.GeoDataFrame({ 'Station': imgw_filtered_stations, 'Temperature': imgw_filtered_temperatures, 'Source': 'IMGW' }, geometry=imgw_geometries, crs="EPSG:4326") # Add X and Y coordinates to imgw_gdf imgw_gdf['X'] = imgw_gdf.geometry.x imgw_gdf['Y'] = imgw_gdf.geometry.y # Read and clip DEM dem_data, dem_transform = read_and_clip_dem(masovian_boundary) # Read and clip Forest Cover forest_data, forest_transform = read_and_clip_forest(masovian_boundary) # Read and clip Water Bodies water_data, water_transform, water_crs = read_and_clip_water_bodies(masovian_boundary) # Ensure geometries are in EPSG:4326 trax_gdf_dem_crs = trax_gdf.to_crs("EPSG:4326") netatmo_gdf_dem_crs = netatmo_gdf.to_crs("EPSG:4326") imgw_gdf_dem_crs = imgw_gdf.to_crs("EPSG:4326") # Get elevation at station points using dem_data and dem_transform trax_elevations = get_elevation_at_points( trax_gdf_dem_crs.geometry, dem_data=dem_data, dem_transform=dem_transform ) netatmo_elevations = get_elevation_at_points( netatmo_gdf_dem_crs.geometry, dem_data=dem_data, dem_transform=dem_transform ) imgw_elevations = get_elevation_at_points( imgw_gdf_dem_crs.geometry, dem_data=dem_data, dem_transform=dem_transform ) # Add elevation to the GeoDataFrames trax_gdf['Elevation'] = trax_elevations netatmo_gdf['Elevation'] = netatmo_elevations imgw_gdf['Elevation'] = imgw_elevations # Get tree cover density at station points using forest_data and forest_transform trax_forest = get_raster_value_at_points( trax_gdf_dem_crs.geometry, raster_data=forest_data, raster_transform=forest_transform ) netatmo_forest = get_raster_value_at_points( netatmo_gdf_dem_crs.geometry, raster_data=forest_data, raster_transform=forest_transform ) imgw_forest = get_raster_value_at_points( imgw_gdf_dem_crs.geometry, raster_data=forest_data, raster_transform=forest_transform ) # Add tree cover density to the GeoDataFrames trax_gdf['Tree_Cover'] = trax_forest netatmo_gdf['Tree_Cover'] = netatmo_forest imgw_gdf['Tree_Cover'] = imgw_forest # Get water body data at station points trax_water = get_water_body_at_points( trax_gdf_dem_crs.geometry, water_data=water_data, water_transform=water_transform ) netatmo_water = get_water_body_at_points( netatmo_gdf_dem_crs.geometry, water_data=water_data, water_transform=water_transform ) imgw_water = get_water_body_at_points( imgw_gdf_dem_crs.geometry, water_data=water_data, water_transform=water_transform ) # Add water body data to the GeoDataFrames trax_gdf['Water_Body'] = trax_water netatmo_gdf['Water_Body'] = netatmo_water imgw_gdf['Water_Body'] = imgw_water # Compute distance to water bodies for station points water_mask_array = water_data.astype(bool) grid_spacing = water_transform.a # Assuming square pixels from scipy.ndimage import distance_transform_edt distance_to_water_array = distance_transform_edt(~water_mask_array) * grid_spacing # Distance in same units as grid_spacing # Get distance to water bodies at station points trax_distance_to_water = get_raster_value_at_points( trax_gdf_dem_crs.geometry, raster_data=distance_to_water_array, raster_transform=water_transform ) netatmo_distance_to_water = get_raster_value_at_points( netatmo_gdf_dem_crs.geometry, raster_data=distance_to_water_array, raster_transform=water_transform ) imgw_distance_to_water = get_raster_value_at_points( imgw_gdf_dem_crs.geometry, raster_data=distance_to_water_array, raster_transform=water_transform ) # Add distance to water to the GeoDataFrames trax_gdf['Distance_to_Water'] = trax_distance_to_water netatmo_gdf['Distance_to_Water'] = netatmo_distance_to_water imgw_gdf['Distance_to_Water'] = imgw_distance_to_water # Add 'Priority' column to each GeoDataFrame trax_gdf['Priority'] = 2 netatmo_gdf['Priority'] = 1 imgw_gdf['Priority'] = 3 # Higher priority # Combine GeoDataFrames stations_gdf = gpd.GeoDataFrame(pd.concat([trax_gdf, netatmo_gdf, imgw_gdf], ignore_index=True)) stations_gdf.crs = "EPSG:4326" stations_gdf = stations_gdf.dropna(subset=['Temperature', 'Elevation', 'Tree_Cover', 'Distance_to_Water']) # Extract coordinates stations_gdf['X'] = stations_gdf.geometry.x stations_gdf['Y'] = stations_gdf.geometry.y # Read ECOSTRESS data ecostress_data, ecostress_transform = read_and_clip_ecostress(masovian_boundary) # Read MODIS data (modis_day_data, modis_day_transform), (modis_night_data, modis_night_transform) = read_and_process_modis_data( modis_day_folder, modis_night_folder) # Adjust grid_spacing as per your requirements grid_spacing = 0.0025 # Approximately ~250 meters x_min, y_min, x_max, y_max = masovian_boundary.total_bounds # Compute the number of cols and rows with the new grid_spacing ncols = int(np.ceil((x_max - x_min) / grid_spacing)) nrows = int(np.ceil((y_max - y_min) / grid_spacing)) # Create the affine transform for the grid transform = from_origin(x_min, y_max, grid_spacing, grid_spacing) # Create arrays of row and column indices cols = np.arange(ncols) rows = np.arange(nrows) # Create a meshgrid of indices cols_indices, rows_indices = np.meshgrid(cols, rows) # Flatten the indices cols_flat = cols_indices.ravel() rows_flat = rows_indices.ravel() # Get the x and y coordinates for each grid cell center xs_flat, ys_flat = rasterio.transform.xy(transform, rows_flat, cols_flat) # Resample MODIS data to match grid modis_day_resampled = resample_modis_data( modis_day_data, modis_day_transform, dest_shape=(nrows, ncols), dest_transform=transform ) modis_night_resampled = resample_modis_data( modis_night_data, modis_night_transform, dest_shape=(nrows, ncols), dest_transform=transform ) # Decide which MODIS data to use based on time of day if is_daytime: modis_resampled = modis_day_resampled else: modis_resampled = modis_night_resampled # After resampling, replace any extreme negative values with np.nan modis_resampled = np.where(modis_resampled <= -1e20, np.nan, modis_resampled) # Include MODIS LST data at station points stations_gdf['MODIS_LST'] = get_raster_value_at_points( stations_gdf.geometry, raster_data=modis_resampled, raster_transform=transform ) # Handle missing MODIS_LST values # Compute mean over finite values modis_lst_mean = np.nanmean(stations_gdf['MODIS_LST']) stations_gdf['MODIS_LST'].fillna(modis_lst_mean, inplace=True) # Add MODIS_LST as a covariate X = stations_gdf[['X', 'Y', 'Elevation', 'Tree_Cover', 'Distance_to_Water', 'MODIS_LST']] # Replace infinite values with NaN X = X.replace([np.inf, -np.inf], np.nan) # Remove rows with NaN values in X X = X.dropna() # Update y accordingly y = stations_gdf.loc[X.index, 'Temperature'] # Proceed with scaling and model fitting # Training Model Progress Bar with tqdm(total=100, desc='Training Model', unit='%', ncols=80) as pbar: scaler = StandardScaler() X_scaled = scaler.fit_transform(X) pbar.update(30) # Prepare sample weights: Assign higher weight to IMGW stations weights_map = {'Netatmo': 1, 'Traxelektronik': 1, 'IMGW': 5} sample_weights = stations_gdf.loc[X.index, 'Source'].map(weights_map).values rf_model = RandomForestRegressor(n_estimators=100, random_state=42) rf_model.fit(X_scaled, y, sample_weight=sample_weights) pbar.update(60) # Get feature importances feature_importances = rf_model.feature_importances_ feature_names = X.columns # Create a DataFrame for better visualization feature_importances_df = pd.DataFrame({'Feature': feature_names, 'Importance': feature_importances}) feature_importances_df = feature_importances_df.sort_values('Importance', ascending=False) pbar.update(10) # Create grid dataframe grid_df = pd.DataFrame({ 'X': xs_flat, 'Y': ys_flat, 'row_idx': rows_flat, 'col_idx': cols_flat }) # Running Model Progress Bar with tqdm(total=100, desc='Running Model', unit='%', ncols=80) as pbar: # Retrieve elevations from DEM grid_elevations = get_elevation_at_points( [Point(x, y) for x, y in zip(grid_df['X'], grid_df['Y'])], dem_data=dem_data, dem_transform=dem_transform ) grid_df['Elevation'] = grid_elevations pbar.update(12) # Retrieve tree cover density from forest cover raster grid_forest = get_raster_value_at_points( [Point(x, y) for x, y in zip(grid_df['X'], grid_df['Y'])], raster_data=forest_data, raster_transform=forest_transform ) grid_df['Tree_Cover'] = grid_forest pbar.update(12) # Calculate distance to water bodies for grid points grid_distance_to_water = get_raster_value_at_points( [Point(x, y) for x, y in zip(grid_df['X'], grid_df['Y'])], raster_data=distance_to_water_array, raster_transform=water_transform ) grid_df['Distance_to_Water'] = grid_distance_to_water pbar.update(12) # Retrieve water body data at grid points grid_water = get_water_body_at_points( [Point(x, y) for x, y in zip(grid_df['X'], grid_df['Y'])], water_data=water_data, water_transform=water_transform ) grid_df['Water_Body'] = grid_water pbar.update(12) # Remove grid points with NaN values (i.e., outside data coverage) grid_df = grid_df.dropna(subset=['Elevation', 'Tree_Cover', 'Distance_to_Water', 'Water_Body']) pbar.update(2) # Include MODIS_LST in grid_df grid_df['MODIS_LST'] = grid_df.apply( lambda row: get_raster_value_at_point(row['X'], row['Y'], modis_resampled, transform), axis=1 ) # Handle missing MODIS_LST values modis_lst_mean_grid = np.nanmean(grid_df['MODIS_LST']) grid_df['MODIS_LST'].fillna(modis_lst_mean_grid, inplace=True) pbar.update(10) # Prepare data for regression prediction X_grid = grid_df[['X', 'Y', 'Elevation', 'Tree_Cover', 'Distance_to_Water', 'MODIS_LST']] # Handle infinite values in X_grid X_grid = X_grid.replace([np.inf, -np.inf], np.nan) # Handle NaNs in X_grid X_grid = X_grid.fillna(method='ffill').fillna(method='bfill') # Ensure that all values are finite # Scale X_grid X_grid_scaled = scaler.transform(X_grid) pbar.update(10) grid_df['Predicted_Temperature'] = rf_model.predict(X_grid_scaled) pbar.update(10) # Calculate residuals at station locations stations_gdf['Predicted_Temperature'] = rf_model.predict(X_scaled) stations_gdf['Residual'] = stations_gdf['Temperature'] - stations_gdf['Predicted_Temperature'] # Force residuals to zero at IMGW stations stations_gdf.loc[stations_gdf['Source'] == 'IMGW', 'Residual'] = 0 # Adjust anomalously large residuals to reduce their impact lower_percentile = np.percentile(stations_gdf['Residual'], 2.5) upper_percentile = np.percentile(stations_gdf['Residual'], 97.5) # Cap the residuals stations_gdf['Adjusted_Residual'] = stations_gdf['Residual'].clip(lower=lower_percentile, upper=upper_percentile) # Remove duplicates by prioritizing IMGW data data = stations_gdf.copy() # Sort by priority (higher priority first) data = data.sort_values('Priority', ascending=False) # Group by coordinates and keep the first record in each group (highest priority) data = data.groupby(['X', 'Y'], as_index=False).first() # Perform Universal Kriging using Adjusted Residual uk = UniversalKriging( x=data['X'].values, y=data['Y'].values, z=data['Adjusted_Residual'].values, variogram_model='spherical', nlags=20, verbose=False ) z, ss = uk.execute( 'points', grid_df['X'].values, grid_df['Y'].values ) grid_df['Residual'] = z grid_df['Kriging_Variance'] = ss # Handle NaNs in residuals by filling them with zero grid_df['Residual'].fillna(0, inplace=True) # Final temperature estimation grid_df['Temperature'] = grid_df['Predicted_Temperature'] + grid_df['Residual'] # Save a copy of the temperature before ECOSTRESS adjustments grid_df['Temperature_No_ECOSTRESS'] = grid_df['Temperature'].copy() # Topographic Cooling Effect max_cooling_effect = 3.0 # Maximum cooling effect in degrees Celsius # Normalize elevation to range from 0 to 1 elevation_min = grid_df['Elevation'].min() elevation_max = grid_df['Elevation'].max() grid_df['Normalized_Elevation'] = (grid_df['Elevation'] - elevation_min) / (elevation_max - elevation_min) # Compute the topographic cooling effect grid_df['Topographic_Cooling'] = grid_df['Normalized_Elevation'] * max_cooling_effect * (1 - is_daytime) # Ensure topographic cooling is not applied over water bodies grid_df.loc[grid_df['Water_Body'] == 1, 'Topographic_Cooling'] = 0 # Apply the topographic cooling effect to the temperature grid_df['Temperature'] -= grid_df['Topographic_Cooling'] # ECOSTRESS Adjustments # Retrieve ECOSTRESS LST values at grid points (same as before) grid_ecostress = get_raster_value_at_points( [Point(x, y) for x, y in zip(grid_df['X'], grid_df['Y'])], raster_data=ecostress_data, raster_transform=ecostress_transform ) grid_df['ECOSTRESS_LST'] = grid_ecostress # Handle NaNs in ECOSTRESS_LST by filling with MODIS_LST values or the mean value grid_df['ECOSTRESS_LST'] = grid_df.apply( lambda row: row['ECOSTRESS_LST'] if not np.isnan(row['ECOSTRESS_LST']) else row['MODIS_LST'], axis=1 ) grid_df['ECOSTRESS_LST'].fillna(grid_df['ECOSTRESS_LST'].mean(), inplace=True) # Compute ECOSTRESS anomalies (deviation from mean) ecostress_mean = grid_df['ECOSTRESS_LST'].mean() grid_df['ECOSTRESS_Anomaly'] = grid_df['ECOSTRESS_LST'] - ecostress_mean # --- Begin Anomaly Adjustment for Nighttime Forested Areas --- if not is_daytime: forest_threshold = 50 # Define the threshold for forest cover (e.g., 50%) warm_anomaly_forest_mask = (grid_df['ECOSTRESS_Anomaly'] > 0) & (grid_df['Tree_Cover'] >= forest_threshold) # Invert the anomalies in forested areas with warm anomalies at night grid_df.loc[warm_anomaly_forest_mask, 'ECOSTRESS_Anomaly'] *= -1 # --- End Anomaly Adjustment --- # Normalize anomalies to range [-1, 1] ecostress_anomaly_min = grid_df['ECOSTRESS_Anomaly'].min() ecostress_anomaly_max = grid_df['ECOSTRESS_Anomaly'].max() grid_df['ECOSTRESS_Anomaly_Normalized'] = ( (grid_df['ECOSTRESS_Anomaly'] - ecostress_anomaly_min) / (ecostress_anomaly_max - ecostress_anomaly_min) * 2 - 1 ) # Increase the impact of ECOSTRESS LST data amplification_factor = 3.0 # Adjust as needed # Compute night_weight: maximum at midnight, zero at noon night_weight = (math.cos(((hour % 24) / 24) * 2 * math.pi) + 1) / 2 # Ranges from 1 at midnight to 0 at noon # Apply anomalies with the night_weight adjustment = grid_df['ECOSTRESS_Anomaly_Normalized'] * amplification_factor * night_weight # Prevent ECOSTRESS adjustments on water bodies adjustment[grid_df['Water_Body'] == 1] = 0 # Limit maximum adjustment to avoid over-adjusting max_adjustment = 5.0 # degrees Celsius adjustment = adjustment.clip(-max_adjustment, max_adjustment) # Apply adjustments to the interpolated temperatures grid_df['Temperature'] += adjustment # Apply the variable cooling effect to water bodies based on time of day cooling_effect = compute_water_body_cooling_effect(hour) # Apply the cooling effect to grid cells identified as water bodies grid_df.loc[grid_df['Water_Body'] == 1, 'Temperature'] += cooling_effect # Apply Gaussian smoothing to the interpolated temperature grid # Reintroduce smoothing to reduce square artifacts from scipy.ndimage import gaussian_filter # Create 2D arrays of temperatures grid_temperature_with_ecostress = np.full((nrows, ncols), np.nan) grid_temperature_with_ecostress[grid_df['row_idx'], grid_df['col_idx']] = grid_df['Temperature'].values # Apply Gaussian smoothing sigma = 0.5 # Adjust sigma to control the amount of smoothing temperature_with_ecostress_smoothed = gaussian_filter(grid_temperature_with_ecostress, sigma=sigma) # Mask the grid_temperature with the Masovian boundary masovian_shape = [masovian_boundary.geometry.unary_union] mask = rasterize( masovian_shape, out_shape=(nrows, ncols), transform=transform, fill=0, all_touched=True, default_value=1, dtype='uint8' ) # Apply the mask temperature_with_ecostress_smoothed = np.ma.array(temperature_with_ecostress_smoothed, mask=mask == 0) # Use the smoothed temperature grid temperature_with_ecostress = temperature_with_ecostress_smoothed # Also create grid_variance array (we'll skip smoothing variance for simplicity) grid_variance = np.full((nrows, ncols), np.nan) grid_variance[grid_df['row_idx'], grid_df['col_idx']] = grid_df['Kriging_Variance'] grid_variance = np.ma.array(grid_variance, mask=mask == 0) # Compute Standard Deviation from Variance grid_std_dev = np.sqrt(grid_variance) grid_std_dev = np.ma.array(grid_std_dev, mask=mask == 0) # Extract temperatures over water bodies water_temperatures = grid_df.loc[grid_df['Water_Body'] == 1, 'Temperature'] land_temperatures = grid_df.loc[grid_df['Water_Body'] == 0, 'Temperature'] # Compare average temperatures avg_water_temp = water_temperatures.mean() avg_land_temp = land_temperatures.mean() print(f"Average Water Temperature: {avg_water_temp:.2f}°C") print(f"Average Land Temperature: {avg_land_temp:.2f}°C") print(f"Temperature Difference (Land - Water): {(avg_land_temp - avg_water_temp):.2f}°C") # Read the custom color scale from the CSV file color_scale_df = pd.read_csv('input/color_scale.csv') color_scale_df = color_scale_df.sort_values('value') values = color_scale_df['value'].values hex_colors = color_scale_df['color'].values # Ensure colors start with '#' hex_colors = [color if color.startswith('#') else f"#{color}" for color in hex_colors] # Create a custom colormap # Normalize the values to 0..1 vmin = values.min() vmax = values.max() normalized_values = (values - vmin) / (vmax - vmin) # Create a list of tuples (position, color) color_tuples = list(zip(normalized_values, hex_colors)) # Create a LinearSegmentedColormap cmap = mcolors.LinearSegmentedColormap.from_list('custom_cmap', color_tuples) # Set the normalization norm = mcolors.Normalize(vmin=vmin, vmax=vmax) with rasterio.open('input/masovian_dem.tif') as dem_src: # Reproject Masovian boundary to DEM CRS if necessary if masovian_boundary.crs != dem_src.crs: masovian_boundary_dem_crs = masovian_boundary.to_crs(dem_src.crs) else: masovian_boundary_dem_crs = masovian_boundary # Clip the DEM to the Masovian boundary dem_plot_data, dem_plot_transform = rasterio.mask.mask( dem_src, masovian_boundary_dem_crs.geometry, crop=True, filled=True, nodata=np.nan ) # Read the first band (assuming single-band DEM) dem_plot_data = dem_plot_data[0] # Since mask returns data as (bands, rows, cols) # Handle NaNs in the DEM data dem_plot_data = np.nan_to_num(dem_plot_data, nan=np.nanmin(dem_plot_data)) # Calculate the extent of the clipped DEM for plotting dem_left, dem_top = dem_plot_transform * (0, 0) dem_right, dem_bottom = dem_plot_transform * (dem_plot_data.shape[1], dem_plot_data.shape[0]) dem_extent = [dem_left, dem_right, dem_bottom, dem_top] # Compute extent for plotting (same as before) def get_extent(transform, array): x_min = transform.c y_max = transform.f x_max = x_min + transform.a * array.shape[1] y_min = y_max + transform.e * array.shape[0] return [x_min, x_max, y_min, y_max] hs = hillshade(dem_plot_data, azimuth=315, angle_altitude=45) extent = get_extent(transform, temperature_with_ecostress) dem_extent = get_extent(dem_plot_transform, dem_plot_data) # Read water data and get CRS water_data, water_transform, water_crs = read_and_clip_water_bodies(masovian_boundary) # Create an empty array to hold the resampled water data water_resampled = np.empty((nrows, ncols), dtype=water_data.dtype) # Perform the reprojection and resampling reproject( source=water_data, destination=water_resampled, src_transform=water_transform, src_crs=water_crs, dst_transform=transform, dst_crs='EPSG:4326', # Assuming temperature grid is in EPSG:4326 resampling=Resampling.nearest ) # Now water_resampled is aligned with the temperature grid # Create the water mask water_mask = np.where(water_resampled > 0, 1, 0) # Define the bounding box coordinates (EPSG:4326) xmin, ymin, xmax, ymax = 20.188477, 51.017203, 22.061646, 51.821759 # Compute the indices for the bounding box from rasterio.transform import rowcol # Convert coordinates to row and column indices in the temperature grid row_ul, col_ul = rowcol(transform, xmin, ymax) row_lr, col_lr = rowcol(transform, xmax, ymin) # Ensure indices are within valid ranges nrows, ncols = temperature_with_ecostress.shape row_ul = max(0, min(nrows - 1, row_ul)) row_lr = max(0, min(nrows - 1, row_lr)) col_ul = max(0, min(ncols - 1, col_ul)) col_lr = max(0, min(ncols - 1, col_lr)) # Ensure row_ul <= row_lr and col_ul <= col_lr if row_ul > row_lr: row_ul, row_lr = row_lr, row_ul if col_ul > col_lr: col_ul, col_lr = col_lr, col_ul # Extract the subset arrays temperature_subset = temperature_with_ecostress[row_ul:row_lr+1, col_ul:col_lr+1] hs_subset = hs[row_ul:row_lr+1, col_ul:col_lr+1] water_mask_subset = water_mask[row_ul:row_lr+1, col_ul:col_lr+1] mask_subset = mask[row_ul:row_lr+1, col_ul:col_lr+1] # Apply the Masovian mask to the subsets temperature_subset = np.ma.array(temperature_subset, mask=mask_subset == 0) hs_subset = np.ma.array(hs_subset, mask=mask_subset == 0) water_mask_subset = np.ma.array(water_mask_subset, mask=mask_subset == 0) grid_spacing_x = transform.a # Positive grid spacing in x direction grid_spacing_y = transform.e # Negative grid spacing in y direction new_x_min = transform.c + col_ul * grid_spacing_x new_y_max = transform.f + row_ul * grid_spacing_y # grid_spacing_y is negative new_transform = from_origin(new_x_min, new_y_max, grid_spacing_x, -grid_spacing_y) # Compute the new extent extent_subset = get_extent(new_transform, temperature_subset) # Filter stations within the bounding box from shapely.geometry import box bbox_polygon = box(xmin, ymin, xmax, ymax) stations_in_bbox = stations_gdf[stations_gdf.geometry.within(bbox_polygon)] # Clip the Masovian boundary to the bounding box masovian_boundary_clipped = masovian_boundary.clip(bbox_polygon) # Plotting Temperature Map with Contours # Calculate the aspect ratio of the bounding box width = xmax - xmin height = ymax - ymin aspect_ratio = width / height # Set the figure size based on the aspect ratio desired_height_inches = 10 # You can adjust this value as desired desired_width_inches = desired_height_inches * aspect_ratio # Plotting Temperature Map with ECOSTRESS Adjustments fig1, ax1 = plt.subplots(figsize=(15, 15)) # Plot the interpolated temperature grid with ECOSTRESS adjustments img1 = ax1.imshow(temperature_with_ecostress, extent=extent, origin='upper', cmap=cmap, norm=norm, alpha=1) # Plot hillshade on top ax1.imshow(hs, extent=dem_extent, cmap='gray', origin='upper', alpha=0.3) ax1.imshow(water_mask, extent=extent, origin='upper', cmap='Blues', alpha=0.5) # Increased alpha to 0.5 # Plot Masovian Voivodeship boundary with a light, dark stroke masovian_boundary.boundary.plot(ax=ax1, edgecolor='#333333', linewidth=1.5) # Plot stations stations_gdf.plot(ax=ax1, color='black', marker='s', markersize=5) # Remove axes for a minimalistic look ax1.axis('off') # Draw a light, dark stroke around the plot extent from matplotlib.patches import Rectangle rect = Rectangle( (extent[0], extent[2]), # Lower-left corner (x0, y0) extent[1] - extent[0], # Width extent[3] - extent[2], # Height linewidth=1.5, edgecolor='#333333', facecolor='none', transform=ax1.transData ) ax1.add_patch(rect) # Introduce a subtle background gradient from matplotlib.colors import LinearSegmentedColormap background_cmap = LinearSegmentedColormap.from_list( 'background_gradient', ['#ffffff', '#f0f0f0'], N=256) ax1.imshow( np.linspace(0, 1, 256).reshape(1, -1), cmap=background_cmap, extent=(extent[0], extent[1], extent[2], extent[3]), aspect='auto', alpha=0.2, zorder=-1 # Place it below other elements ) # Adjust font properties for a modern look plt.rcParams.update({ 'font.size': 14, # Base font size 'font.family': 'sans-serif', 'font.sans-serif': ['Arial', 'Helvetica', 'DejaVu Sans'], 'text.color': '#333333' }) # Enlarge and reposition the product name (Title) fig1.text( 0.5, 0.94, # Adjusted y-position for better placement "High-Resolution Mesoscale Temperature Analysis", fontsize=28, # Increased font size fontweight='bold', ha='center', va='top', fontname='DejaVu Sans', color='#333333' ) # Move the model name/resolution text closer to the product name text fig1.text( 0.5, 0.91, # Adjusted y-position to move it closer "Model: TempMeso v1.0 (Preview) | Resolution: 250 m", fontsize=18, # Increased font size ha='center', va='top', fontname='DejaVu Sans', color='#666666' ) # Adjust colorbar position and style from mpl_toolkits.axes_grid1 import make_axes_locatable divider = make_axes_locatable(ax1) cax = divider.append_axes("right", size="3%", pad=0.1) cbar1 = fig1.colorbar(img1, cax=cax) ticks = np.arange(np.floor(vmin / 5) * 5, np.ceil(vmax / 5) * 5 + 1, 5) cbar1.set_ticks(ticks) cbar1.set_ticklabels(ticks.astype(int)) cbar1.ax.tick_params(labelsize=14) # Enhance colorbar aesthetics cbar1.outline.set_visible(False) cbar1.ax.yaxis.set_tick_params(width=0.5) cbar1.ax.tick_params(labelsize=14, colors='#333333') # Move the logo to the bottom right corner, directly below the colorbar from matplotlib.offsetbox import OffsetImage, AnnotationBbox import matplotlib.image as mpimg # Read the logo image logo_path = 'input/logo.png' logo_img = mpimg.imread(logo_path) # Adjust the size of the logo logo_zoom = 0.25 imagebox = OffsetImage(logo_img, zoom=logo_zoom) # Get the position of the colorbar axes cbar_bbox = cax.get_position() cbar_x0 = cbar_bbox.x0 # Left cbar_x1 = cbar_bbox.x1 # Right # Calculate the x position for the logo (centered below the colorbar) logo_x = (cbar_x0 + cbar_x1) / 2 # Set the y position as low as possible, but ensure the logo is fully visible logo_y = 0.02 # Adjust this value if necessary ab = AnnotationBbox( imagebox, xy=(logo_x, logo_y), xycoords='figure fraction', frameon=False, box_alignment=(0.5, 0), # Centered horizontally, aligned at bottom ) fig1.add_artist(ab) # Adjust the bottom margin to ensure the logo is not cut off plt.subplots_adjust(left=0.05, right=0.95, top=0.88, bottom=0.05) # On the map, add texts at the coldest and warmest temperature locations # Calculate min and max temperatures over the entire Masovian region min_temp = np.nanmin(temperature_with_ecostress) max_temp = np.nanmax(temperature_with_ecostress) # Get the indices of the min and max temperatures min_indices = np.unravel_index(np.nanargmin(temperature_with_ecostress), temperature_with_ecostress.shape) max_indices = np.unravel_index(np.nanargmax(temperature_with_ecostress), temperature_with_ecostress.shape) # Convert grid indices to coordinates min_lon_full, min_lat_full = rasterio.transform.xy(transform, min_indices[0], min_indices[1]) max_lon_full, max_lat_full = rasterio.transform.xy(transform, max_indices[0], max_indices[1]) # Plot the temperature values on the map (without markers) # Use white text with a thick black stroke text_kwargs = dict( fontsize=18, # Increased font size fontname='Arial', ha='center', va='center', color='white', transform=ax1.transData, path_effects=[patheffects.withStroke(linewidth=3, foreground='black')] ) # Format temperature values with one decimal point ax1.text(min_lon_full, min_lat_full, f"{min_temp:.1f}", **text_kwargs) ax1.text(max_lon_full, max_lat_full, f"{max_temp:.1f}", **text_kwargs) # Save and show the plot plt.savefig('output/temperature_analysis_modern.png', dpi=300) plt.show() print("Updated temperature analysis plot created successfully.") # Calculate the aspect ratio of the bounding box width = xmax - xmin height = ymax - ymin aspect_ratio = width / height # Set the maximum desired width max_width_inches = 15 # Adjust this value as desired # Calculate the figure height based on the aspect ratio and maximum width desired_width_inches = min(max_width_inches, aspect_ratio * desired_height_inches) desired_height_inches = desired_width_inches / aspect_ratio # Ensure the height doesn't exceed a certain value desired_height_inches = min(desired_height_inches, 10) # Adjust as needed fig2, ax2 = plt.subplots(figsize=(desired_width_inches, desired_height_inches)) # Proceed with previous plotting code, using adjusted fig2 and ax2 # Use the subset data and extent with applied mask img2 = ax2.imshow(temperature_subset, extent=extent_subset, origin='upper', cmap=cmap, norm=norm, alpha=1) # Plot hillshade on top using subset data with mask # ax2.imshow(hs_subset, extent=extent_subset, cmap='gray', origin='upper', alpha=0.3) # Overlay water bodies using subset data with mask # ax2.imshow(water_mask_subset, extent=extent_subset, origin='upper', cmap='Blues', alpha=0.5) # Plot clipped Masovian boundary with a light, dark stroke masovian_boundary_clipped.boundary.plot(ax=ax2, edgecolor='#333333', linewidth=1.5) # Plot stations within the bounding box stations_in_bbox.plot(ax=ax2, color='black', marker='s', markersize=5) # Remove axes for a minimalistic look ax2.axis('off') # Introduce a subtle background gradient using the subset extent ax2.imshow( np.linspace(0, 1, 256).reshape(1, -1), cmap=background_cmap, extent=extent_subset, aspect='auto', alpha=0.2, zorder=-1 # Place it below other elements ) # Adjust font properties for a modern look plt.rcParams.update({ 'font.size': 14, 'font.family': 'sans-serif', 'font.sans-serif': ['Arial', 'Helvetica', 'DejaVu Sans'], 'text.color': '#333333' }) # Enlarge and reposition the product name (Title) fig2.text( 0.5, 0.995, # Moved up towards the top edge "High-Resolution Mesoscale Temperature Analysis", fontsize=12, fontweight='bold', ha='center', va='top', fontname='DejaVu Sans', color='#333333' ) # Move the model name/resolution text closer to the product name text fig2.text( 0.5, 0.970, # Moved up slightly below the title "Model: HRMTA v1.0 (Preview) | Resolution: 250 m", fontsize=9, ha='center', va='top', fontname='DejaVu Sans', color='#666666' ) # Add data source attribution at the bottom left corner fig2.text( 0.01, 0.02, "Data source: IMGW-PIB (processed)", fontsize=12, ha='left', va='bottom', fontname='DejaVu Sans', color='#333333' ) # Adjust colorbar position and style from mpl_toolkits.axes_grid1 import make_axes_locatable divider = make_axes_locatable(ax2) cax2 = divider.append_axes("right", size="3%", pad=0.1) cbar2 = fig2.colorbar(img2, cax=cax2) cbar2.set_ticks(ticks) cbar2.set_ticklabels(ticks.astype(int)) # Import FontProperties and load the font from matplotlib.font_manager import FontProperties # Replace 'input/RobotoCondensed-Regular.ttf' with the actual path to your font file roboto_font_path = 'input/RobotoCondensed-Regular.ttf' roboto_condensed = FontProperties(fname=roboto_font_path) # Apply font properties to the colorbar tick labels for label in cbar2.ax.yaxis.get_ticklabels(): label.set_fontproperties(roboto_condensed) cbar2.ax.tick_params(labelsize=14) # Enhance colorbar aesthetics cbar2.outline.set_visible(False) cbar2.ax.yaxis.set_tick_params(width=0.5) cbar2.ax.tick_params(labelsize=14, colors='#333333') # Move the logo to the bottom right corner, directly below the colorbar from matplotlib.offsetbox import OffsetImage, AnnotationBbox import matplotlib.image as mpimg # Read the logo image again for the second plot logo_img2 = mpimg.imread(logo_path) # Adjust the size of the logo imagebox2 = OffsetImage(logo_img2, zoom=logo_zoom) # Get the position of the colorbar axes cbar_bbox2 = cax2.get_position() logo_x2 = (cbar_bbox2.x0 + cbar_bbox2.x1) / 2 logo_y2 = 0.02 # Adjust this value if necessary ab2 = AnnotationBbox( imagebox2, xy=(logo_x2, logo_y2), xycoords='figure fraction', frameon=False, box_alignment=(0.5, 0), ) fig2.add_artist(ab2) # Adjust the bottom margin to ensure the logo and data attribution text are not cut off plt.subplots_adjust(left=0.05, right=0.95, top=0.95, bottom=0.06) # Calculate min and max temperatures over the temperature_subset min_temp = np.nanmin(temperature_subset) max_temp = np.nanmax(temperature_subset) # Get the indices of the min and max temperatures within the subset array min_indices = np.unravel_index(np.nanargmin(temperature_subset), temperature_subset.shape) max_indices = np.unravel_index(np.nanargmax(temperature_subset), temperature_subset.shape) # Convert grid indices to coordinates using the new_transform from rasterio.transform import xy min_lon, min_lat = xy(new_transform, min_indices[0], min_indices[1]) max_lon, max_lat = xy(new_transform, max_indices[0], max_indices[1]) # Add contours to the plot using the subset data min_temp_c = np.floor(min_temp) max_temp_c = np.ceil(max_temp) contour_levels = np.arange(min_temp_c, max_temp_c + 1, 1) contours = ax2.contour( temperature_subset, levels=contour_levels, colors='black', linewidths=0.5, extent=extent_subset, origin='upper' ) contour_labels = ax2.clabel( contours, inline=False, fontsize=8, fmt='%d', colors='white', inline_spacing=4, manual=False ) for txt in contour_labels: txt.set_path_effects([ patheffects.Stroke(linewidth=3, foreground='black'), patheffects.Normal() ]) # Now add the min/max temperature labels after the contours and contour labels text_kwargs = dict( fontsize=18, fontname='Arial', ha='center', va='center', color='white', transform=ax2.transData, path_effects=[patheffects.withStroke(linewidth=3, foreground='black')] ) # Format temperature values with one decimal point ax2.text(min_lon, min_lat, f"{min_temp:.1f}", **text_kwargs, zorder=5) ax2.text(max_lon, max_lat, f"{max_temp:.1f}", **text_kwargs, zorder=5) # Reverse geocode min and max temperature locations to find nearest village from geopy.geocoders import Nominatim geolocator = Nominatim(user_agent="geoapiExercises") try: min_location = geolocator.reverse((min_lat_full, min_lon_full), language='en') min_address = min_location.raw.get('address', {}) min_village = min_address.get('village', min_address.get('town', min_address.get('city', 'Unknown Location'))) except Exception as e: print(f"Error reverse geocoding min location: {e}") min_village = 'Unknown Location' try: max_location = geolocator.reverse((max_lat_full, max_lon_full), language='en') max_address = max_location.raw.get('address', {}) max_village = max_address.get('village', max_address.get('town', max_address.get('city', 'Unknown Location'))) except Exception as e: print(f"Error reverse geocoding max location: {e}") max_village = 'Unknown Location' # Create label texts min_label_text = f"MIN\n {min_temp:.1f}°C: {min_village}" max_label_text = f"MAX\n {max_temp:.1f}°C: {max_village}" # Define font properties from matplotlib.font_manager import FontProperties roboto_font_path = 'input/RobotoCondensed-Regular.ttf' roboto_condensed = FontProperties(fname=roboto_font_path) # Add text labels to the figure fig1.text(0.01, 0.95, min_label_text, ha='left', va='top', fontsize=14, fontproperties=roboto_condensed) fig1.text(0.99, 0.95, max_label_text, ha='right', va='top', fontsize=14, fontproperties=roboto_condensed) # Save and show the plot plt.savefig('output/temperature_analysis_with_contours2.png', dpi=300) plt.show() print("Temperature analysis plot with contours created successfully.") # At the end, print feature importances to confirm MODIS influence print("\nFeature importances from the Random Forest model:") print(feature_importances_df)Check if 'Distance_to_Water' has significant importance
distance_water_importance = feature_importances_df.loc[feature_importances_df['Feature'] == 'Distance_to_Water', 'Importance'].values[0] if distance_water_importance > 0.05: # Threshold can be adjusted print(f"\n'Distance_to_Water' feature has significant influence on the model (importance: {distance_water_importance:.4f}).") else: print(f"\n'Distance_to_Water' feature has low influence on the model (importance: {distance_water_importance:.4f}).") return temperature_with_ecostress, transformdef get_elevation_at_points(geometry, dem_data=None, dem_transform=None): from rasterio.transform import rowcol
if dem_data is not None and dem_transform is not None: elevations = [] for point in geometry: x, y = point.x, point.y try: row, col = rowcol(dem_transform, x, y) row = int(row) col = int(col) elevation = dem_data[row, col] elevations.append(elevation) except (IndexError, ValueError): elevations.append(np.nan) return elevations else: raise ValueError("Provide dem_data and dem_transform.")def get_interpolated_temperature_at_point(lat, lon, temperature_grid, transform): """ Given a latitude and longitude, return the interpolated temperature value at that point.
Parameters: - lat, lon: Latitude and longitude of the point. - temperature_grid: The interpolated temperature grid (2D numpy array). - transform: Affine transform for the grid. Returns: - Interpolated temperature value at the point, or None if point is outside the grid. """ from rasterio.transform import rowcol try: row, col = rowcol(transform, lon, lat) # Note that rasterio uses (x, y), so (lon, lat) row = int(row) col = int(col) value = temperature_grid[row, col] if np.ma.is_masked(value) or np.isnan(value): # Value is masked or NaN, meaning outside the interpolated area return None else: return value.item() except (IndexError, ValueError): return None # Point is outside the griddef get_raster_value_at_points(geometry, raster_data=None, raster_transform=None): from rasterio.transform import rowcol
if raster_data is not None and raster_transform is not None: values = [] for point in geometry: x, y = point.x, point.y try: row, col = rowcol(raster_transform, x, y) row = int(row) col = int(col) if (0 <= row < raster_data.shape[0]) and (0 <= col < raster_data.shape[1]): value = raster_data[row, col] # Check for NaN in raster data if np.isnan(value): values.append(np.nan) else: values.append(value) else: values.append(np.nan) except (IndexError, ValueError): values.append(np.nan) return values else: raise ValueError("Provide raster_data and raster_transform.")def get_raster_value_at_point(x, y, raster_data=None, raster_transform=None): from rasterio.transform import rowcol
if raster_data is not None and raster_transform is not None: try: row, col = rowcol(raster_transform, x, y) row = int(row) col = int(col) if (0 <= row < raster_data.shape[0]) and (0 <= col < raster_data.shape[1]): value = raster_data[row, col] if np.isnan(value): return np.nan else: return value else: return np.nan except (IndexError, ValueError): return np.nan else: raise ValueError("Provide raster_data and raster_transform.")def get_water_body_at_points(geometry, water_data=None, water_transform=None): from rasterio.transform import rowcol
if water_data is not None and water_transform is not None: water_bodies = [] for point in geometry: x, y = point.x, point.y try: row, col = rowcol(water_transform, x, y) row = int(row) col = int(col) if (0 <= row < water_data.shape[0]) and (0 <= col < water_data.shape[1]): value = water_data[row, col] # Adjust the condition based on your raster's water encoding # For binary raster where 1 = water, 0 = land water_bodies.append(1 if value else 0) else: water_bodies.append(0) except (IndexError, ValueError): water_bodies.append(0) return water_bodies else: raise ValueError("Provide water_data and water_transform.")def read_and_clip_dem(masovian_boundary): dem_path = 'input/masovian_dem.tif' with rasterio.open(dem_path) as src: dem_data = src.read(1, masked=True) dem_transform = src.transform return dem_data, dem_transform
def read_and_clip_forest(masovian_boundary): forest_path = 'input/forests.tif' with rasterio.open(forest_path) as src: forest_data = src.read(1, masked=True) forest_data = np.where(forest_data == src.nodata, 0, forest_data) forest_transform = src.transform return forest_data, forest_transform
def read_and_clip_water_bodies(masovian_boundary): water_path = 'input/water_bodies.tif' with rasterio.open(water_path) as src: water_crs = src.crs # Get the CRS of the water raster
# Ensure the Masovian boundary is in the same CRS as the water raster if masovian_boundary.crs != src.crs: masovian_boundary = masovian_boundary.to_crs(src.crs) # Perform the clipping clipped_water, water_transform = rasterio.mask.mask( src, masovian_boundary.geometry, crop=True, filled=True, nodata=0 ) # Read the first band (assuming single-band raster) water_data = clipped_water[0] # Handle NoData values by setting them to 0 (assuming 0 represents no water) water_data = np.where(water_data == src.nodata, 0, water_data) return water_data, water_transform, water_crsdef read_and_clip_ecostress(masovian_boundary): ecostress_path = 'input/raw_ecostress.tif' with rasterio.open(ecostress_path) as src: # Read data ecostress_data = src.read(1, masked=True) ecostress_data = np.where(ecostress_data == src.nodata, np.nan, ecostress_data) ecostress_transform = src.transform return ecostress_data, ecostress_transform
if name == "main": # Fetching Data Progress Bar with tqdm(total=100, desc='Fetching Data', unit='%', ncols=80) as pbar: # Fetch Traxelektronik data trax_stations, trax_temperatures = fetch_traxelektronik_data() pbar.update(20)
# Geocode Traxelektronik stations geolocator = Nominatim(user_agent="geoapi") trax_coords = {} for station in tqdm(trax_stations, desc="Geocoding Traxelektronik Stations", unit="station"): cleaned_station = clean_station_name(station) coords, was_cleaned = get_coordinates(cleaned_station, geolocator) if coords: trax_coords[cleaned_station] = coords # Use cleaned station names as keys pbar.update(30) # Fetch Netatmo data netatmo_stations, netatmo_temperatures, netatmo_coords = fetch_netatmo_data() pbar.update(20) # Fetch IMGW data imgw_stations, imgw_temperatures, imgw_station_ids = fetch_imgw_data() pbar.update(10) # Geocode IMGW stations imgw_coords = {} for station in tqdm(imgw_stations, desc="Geocoding IMGW Stations", unit="station"): coords, was_cleaned = get_coordinates(station, geolocator) if coords: imgw_coords[station] = coords pbar.update(20) # Paths to MODIS data folders modis_day_folder = 'input/MODIS_day' modis_night_folder = 'input/MODIS_night' # Call the function with all required arguments smoothed_temperature, transform = plot_stations_with_boundary_and_interpolation( trax_stations, trax_temperatures, trax_coords, netatmo_stations, netatmo_temperatures, netatmo_coords, imgw_stations, imgw_temperatures, imgw_coords, modis_day_folder, modis_night_folder ) # Coordinates to test test_lat = 51.40118 test_lon = 21.14805 interpolated_temp = get_interpolated_temperature_at_point( test_lat, test_lon, smoothed_temperature, transform ) if interpolated_temp is not None: print(f"\nInterpolated temperature value at {test_lat}, {test_lon} is {interpolated_temp:.2f}°C") else: print(f"\nCoordinates {test_lat}, {test_lon} are outside the interpolated grid or have no data.")Detailly analyze this code, it's structure, functions and overall how it works. Don't write any code, just analyze it, it's effectiveness and accuracy.
- Assistant
Analysis of the Provided Code for Temperature Analysis and Mapping in the Masovian Voivodeship
Overview
The code is designed to fetch, process, and visualize temperature data for the Masovian Voivodeship in Poland. It integrates data from multiple sources, including Traxelektronik, Netatmo, and IMGW (the Polish Institute of Meteorology and Water Management). The code performs data cleaning, geocoding, spatial interpolation, and various adjustments to create high-resolution temperature maps. It also incorporates environmental factors like elevation, forest cover, water bodies, and satellite-derived land surface temperatures from MODIS and ECOSTRESS data to enhance the accuracy of the temperature estimations.
Structure and Workflow
-
Imports and Configuration: The code begins by importing necessary libraries for geospatial processing, data manipulation, machine learning, and visualization. It sets up environment variables and warnings to ensure smooth execution.
-
Data Cleaning and Preprocessing Functions:
clean_station_name: Removes specific keywords from station names to standardize them.get_masovian_boundary: Fetches the geographic boundary of the Masovian Voivodeship from an online GeoJSON file.is_in_masovian: Checks whether a given point (latitude and longitude) lies within the Masovian boundary.
-
Data Fetching Functions:
fetch_traxelektronik_data: Scrapes temperature data from the Traxelektronik website using BeautifulSoup.fetch_netatmo_data: Retrieves public temperature data from the Netatmo API within specified geographic boundaries.fetch_imgw_data: Obtains temperature data from a personal website representing IMGW data for select stations.
-
Geocoding and Data Cleaning:
get_coordinates: Geocodes station names to obtain their coordinates using the Nominatim geocoding service.clean_temperature: Cleans the temperature data by removing unwanted characters and converting them to floats.remove_nearby_duplicates: Filters out Netatmo stations that are too close to Traxelektronik stations to avoid data redundancy.
-
Environmental Data Processing:
hillshade: Computes hillshade from a Digital Elevation Model (DEM) to enhance map visualization.read_and_process_modis_data: Reads and processes MODIS land surface temperature data for both day and night.
-
Main Processing Function:
plot_stations_with_boundary_and_interpolation: This is the core function that integrates all data and performs the temperature analysis. It follows these steps:- Time-Based Adjustments: Determines whether it's daytime or nighttime and excludes certain stations accordingly.
- Data Merging: Combines Traxelektronik, Netatmo, and IMGW data into a single GeoDataFrame.
- Environmental Variables: Associates each station with elevation, forest cover density, water body presence, and distance to water bodies.
- Satellite Data Integration: Includes MODIS Land Surface Temperature (LST) data as a covariate in the model.
- Machine Learning Model:
- Prepares feature matrix
Xand target vectory. - Scales features using
StandardScaler. - Trains a
RandomForestRegressor, weighting IMGW stations more heavily due to their presumed higher accuracy. - Analyzes feature importances to understand variable influence.
- Prepares feature matrix
- Spatial Interpolation:
- Creates a spatial grid over the Masovian region.
- Predicts temperatures over the grid using the trained model.
- Calculates residuals at station locations and performs Universal Kriging to interpolate these residuals across the grid.
- Adjusts predicted temperatures with the interpolated residuals.
- Environmental Adjustments:
- Applies topographic cooling effects based on elevation and time of day.
- Incorporates ECOSTRESS LST data for fine-scale adjustments, especially over forested areas at night.
- Adjusts temperatures over water bodies according to a diurnal cooling effect model.
- Smoothing and Visualization:
- Applies Gaussian smoothing to the temperature grid to reduce artifacts.
- Generates high-quality visualizations, including maps with temperature contours, hillshade, water bodies, and annotations of the coldest and warmest areas.
- Saves the resulting maps as image files.
-
Helper Functions:
get_elevation_at_points: Retrieves elevation values from the DEM for given points.get_raster_value_at_points: Extracts raster values (e.g., forest cover, distance to water) at specified locations.get_water_body_at_points: Identifies if a point lies on a water body based on a raster dataset.read_and_clip_dem,read_and_clip_forest,read_and_clip_water_bodies,read_and_clip_ecostress: Reads and clips various environmental raster datasets to the Masovian boundary.
-
Execution Block:
- The
if __name__ == "__main__":block orchestrates the entire process, sequentially calling the data fetching, preprocessing, and analysis functions. - Finally, it tests the interpolated temperature at a specific coordinate.
- The
Detailed Functionality and Methods
-
Data Acquisition and Cleaning:
- Scrapes data from online sources, handling potential connection issues with status code checks.
- Cleans and standardizes station names to ensure consistent geocoding results.
- Filters out stations based on geographic location and time of day to enhance data relevance and accuracy.
-
Geocoding:
- Uses the Nominatim API to convert station names to coordinates.
- Verifies that geocoded points are within the Masovian region to prevent erroneous data inclusion.
-
Handling Missing and Erroneous Data:
- Employs functions like
clean_temperatureto sanitize temperature readings. - Drops stations with missing or invalid data.
- Replaces fill values and nodata values in raster datasets with
np.nanto handle missing data uniformly.
- Employs functions like
-
Environmental Data Integration:
- Incorporates elevation, forest cover, and proximity to water bodies as explanatory variables in the model.
- Uses raster datasets for these variables, extracting values at station locations and across the grid.
-
Machine Learning Model:
- The Random Forest model predicts temperature based on spatial coordinates and environmental factors.
- Assigns sample weights to different data sources, giving higher priority to more reliable stations (IMGW).
- Analyzes feature importances to understand the influence of each variable.
-
Spatial Interpolation and Kriging:
- Performs Universal Kriging on the residuals to account for spatial autocorrelation not captured by the Random Forest.
- Adjusts model predictions with kriged residuals for improved spatial accuracy.
-
Adjustments for Diurnal and Environmental Effects:
- Applies time-of-day adjustments, considering differences in temperature behavior between day and night.
- Introduces a topographic cooling effect based on elevation during nighttime.
- Adjusts temperatures over water bodies using a cosine function to model diurnal cooling.
- Modifies ECOSTRESS LST data anomalies in forested areas during nighttime to account for expected cooling.
-
Visualization:
- Generates high-resolution maps with custom color scales for temperature representation.
- Overlays additional features like hillshade to enhance the visual interpretation of terrain influences.
- Annotates maps with significant temperature values and locations.
- Adjusts map aesthetics, including fonts and colors, for a modern and professional appearance.
Effectiveness and Accuracy
-
Strengths:
- Comprehensive Data Integration: The code effectively combines data from multiple sources, increasing spatial coverage and data richness.
- Use of Environmental Variables: Incorporating elevation, forest cover, and proximity to water bodies enhances the model's ability to capture microclimatic variations.
- Machine Learning Application: The Random Forest model is suitable for handling nonlinear relationships and interactions between variables.
- Spatial Interpolation with Kriging: Universal Kriging of residuals accounts for spatial autocorrelation, improving the accuracy of spatial predictions.
- Temporal Adjustments: The code dynamically adjusts for diurnal variations, recognizing the different temperature behaviors between day and night.
- Visualization Quality: The generated maps are visually appealing and informative, aiding in effective communication of the results.
-
Potential Issues and Areas for Improvement:
- Data Source Reliability:
- Netatmo Data: While Netatmo provides high-density data, the quality and reliability can be variable due to consumer-grade sensors.
- Access Tokens and APIs: The use of a hardcoded access token for the Netatmo API is not secure and may lead to unauthorized access or abuse.
- IMGW Data Source: Fetching IMGW data from a personal website rather than the official API or portal may introduce reliability concerns.
- Geocoding Limitations:
- Reliance on Nominatim for geocoding may result in inaccuracies or failed geocoding due to rate limits or missing data.
- No error handling for geocoding failures other than returning
None, which might silently exclude some stations.
- Time Handling:
- The code uses Central European Time (CET) but does not account for daylight saving time, which could shift the actual local time.
- The time-based adjustments, such as the cooling effect, are modeled simplistically using cosine functions, which may not accurately reflect real-world conditions.
- Environmental Data Resolution and Accuracy:
- The DEM, forest cover, and water bodies data sources and resolutions are not specified. Using outdated or low-resolution data could impact accuracy.
- Assumptions about the environmental variables' effect on temperature may not hold uniformly across the region.
- Model Validation:
- The code does not include any validation of the machine learning model (e.g., cross-validation or test set evaluation) to assess prediction accuracy.
- There's no assessment of prediction errors or uncertainty beyond kriging variance.
- Feature Importance Interpretation:
- While feature importances are printed, the implications of these importances are not deeply analyzed.
- High importance of certain variables (e.g., distance to water) may not be causally interpretable without further investigation.
- Hardcoded Values and Thresholds:
- Several thresholds and parameters are hardcoded (e.g., forest cover threshold of 50%, maximum cooling effect of 3.0°C), which may not be optimal.
- These parameters could be data-driven instead, estimated from the data.
- Data Source Reliability:
-
Accuracy Considerations:
- Data Quality: The accuracy of the final temperature map is highly dependent on the quality of input data. Errors or biases in station measurements directly affect predictions.
- Spatial Coverage: Areas with sparse data may have less accurate predictions due to extrapolation beyond the range of observed data.
- Model Limitations: The Random Forest model, while robust, may not capture all the complexities of atmospheric processes influencing temperature, particularly in the vertical dimension.
- Environmental Variable Effects: The assumed relationships between environmental variables and temperature need empirical validation. For example, the effect of tree cover on nighttime temperature can vary based on other factors like atmospheric conditions.
Recommendations for Improvement
-
Data Source Enhancement:
- Secure API Access: Obtain official API keys and tokens securely stored, avoiding hardcoding sensitive information.
- Use Official Data Sources: Wherever possible, use data directly from official sources (e.g., IMGW's official APIs) to ensure data reliability and legal compliance.
- Data Quality Checks: Implement data validation steps to detect and handle erroneous measurements (e.g., sudden spikes, outlier detection).
-
Geocoding Robustness:
- Rate Limit Handling: Incorporate mechanisms to handle potential rate limits from the geocoding API, such as caching results or using alternative services.
- Error Logging: Log geocoding errors for further analysis rather than silently failing.
-
Model Validation and Testing:
- Cross-Validation: Use techniques like k-fold cross-validation to assess the model's predictive performance.
- Error Metrics: Calculate metrics such as RMSE (Root Mean Square Error) to quantify prediction errors.
- Uncertainty Quantification: Incorporate uncertainty estimates into the final map, informing users about confidence levels in different areas.
-
Parameter Optimization:
- Hyperparameter Tuning: Optimize model parameters (e.g., number of estimators in Random Forest) using grid search or random search.
- Dynamic Thresholds: Replace hardcoded thresholds with values derived from data analysis or literature.
-
Temporal Dynamics:
- Daylight Saving Time: Adjust time calculations to account for daylight saving time where applicable.
- Advanced Temporal Models: Consider using time-series models or incorporating meteorological forecast data for more accurate temporal adjustments.
-
Environmental Data Refinement:
- High-Resolution Data: Use the most recent and highest-resolution environmental datasets available.
- Variable Selection: Explore additional variables that may influence temperature, such as soil moisture or land use types.
- Empirical Validation: Validate the assumed effects of environmental variables using statistical tests or domain knowledge.
-
Visualization Enhancements:
- Interactive Maps: Create interactive visualizations that allow users to explore the data dynamically.
- Accessibility Considerations: Ensure color scales and map features are accessible to users with color vision deficiencies.
-
Documentation and Reproducibility:
- Code Comments: Add comments explaining complex code sections for better maintainability.
- Modularization: Break down large functions into smaller, reusable modules.
- Version Control: Use version control systems to track changes and collaborate effectively.
Conclusion
The provided code is a comprehensive attempt to model and visualize mesoscale temperature variations in the Masovian Voivodeship using a combination of observed data, environmental variables, and machine learning techniques. It demonstrates a solid understanding of geospatial processing and data integration for environmental analysis.
However, the effectiveness and accuracy of the results are influenced by several factors, including data quality, model validation, and the handling of environmental effects. By addressing the potential issues and implementing the recommended improvements, the code's reliability and utility can be enhanced, leading to more accurate and informative temperature analyses.
Note: The analysis provided is based on the code structure and functions as described. Specific numerical results or direct outputs from the code execution are not included, as the focus is on understanding and evaluating the code's functionality and methodology.
-