datasets/ADES/ADES_data_fetching.py

import requests
import pandas as pd
import geopandas as gpd
from shapely.geometry import Point
from tqdm import tqdm

# Departments intersecting the study area
departments = ["27", "61", "76"]

url = "https://hubeau.eaufrance.fr/api/v1/niveaux_nappes/stations"

stations = []

for dep in departments:

    params = {
        "code_departement": dep,
        "size": 20000,
        "format": "json"
    }

    r = requests.get(url, params=params)

    if r.status_code == 200:
        stations.extend(r.json()["data"])

stations = pd.DataFrame(stations)

print(f"{len(stations)} stations downloaded.")

print(stations.columns)

stations = gpd.GeoDataFrame(
    stations.drop(columns="geometry", errors="ignore"),
    geometry=gpd.points_from_xy(
        stations["x"],
        stations["y"]
    ),
    crs="EPSG:4326"
)


# Watershed Merging

# Read shapefiles
risle = gpd.read_file("data/Watershed_Risle.shp")
eure = gpd.read_file("data/Watershed_Eure.shp")

# Same CRS
eure = eure.to_crs(risle.crs)

# Combine
watersheds = pd.concat([risle, eure], ignore_index=True)
watersheds = gpd.GeoDataFrame(watersheds, crs=risle.crs)

# Create one merged geometry
watershed = gpd.GeoDataFrame(
    geometry=[watersheds.unary_union],
    crs=watersheds.crs
)

# Convert to station CRS
watershed = watershed.to_crs("EPSG:2154")
stations = stations.to_crs("EPSG:2154")

print(stations.total_bounds)
print(watershed.total_bounds)



stations_clip = gpd.clip(stations, watershed)

print(f"Total stations downloaded: {len(stations)}")
print(f"Stations inside Risle + Eure watersheds: {len(stations_clip)}")

watershed.to_file(
    "output/shapefile/Risle_Eure_Watershed.gpkg",
    driver="GPKG"
)

watershed.to_file(
    "output/shapefile/Risle_Eure_Watershed.shp"
)


# Save station list 

stations_clip.to_file(
    "output/shapefile/groundwater_stations.gpkg",
    driver="GPKG"
)

stations_clip.to_file(
    "output/shapefile/groundwater_stations.shp"
)

stations_clip.drop(columns="geometry").to_csv(
    "output/csv/groundwater_stations.csv",
    index=False
)

# Download ground water levels
#levels_all = []

#for code in tqdm(stations_clip["code_bss"]):
#
#    url = "https://hubeau.eaufrance.fr/api/v1/niveaux_nappes/chroniques"
#
#    params = {
#        "code_bss": code,
#        "format": "json",
#        "size": 20000
#    }
#
#    r = requests.get(url, params=params)
#
#    if r.status_code == 200:
#        data = r.json().get("data", [])
#        if data:
#            df = pd.DataFrame(data)
#            df["code_bss"] = code
#            levels_all.append(df)

## Combine
#levels_df = pd.concat(levels_all, ignore_index=True)

## Save
#levels_df.to_csv("output/csv/groundwater_levels_watershed.csv", index=False)

#print("Groundwater levels downloaded:", len(levels_df))

# Download groundwater quality
quality_all = []

for code in tqdm(stations_clip["code_bss"]):

    url = "https://hubeau.eaufrance.fr/api/v1/qualite_nappes/analyses"

    params = {
        "bss_id": code,
        "format": "json",
        "size": 20000
    }

    r = requests.get(url, params=params)

    if r.status_code == 200:
        data = r.json().get("data", [])
        if data:
            df = pd.DataFrame(data)
            df["code_bss"] = code
            quality_all.append(df)

quality_df = pd.concat(quality_all, ignore_index=True)

quality_df.to_csv("output/csv/groundwater_quality_watershed.csv", index=False)

print("Groundwater quality records:", len(quality_df))