# -*- coding: utf-8 -*- """Desertification_Forecasting.ipynb Automatically generated by Colab. Original file is located at https://colab.research.google.com/drive/1t1WFmaiHgQ-9ukBo3NhJ3RZ1Qp-IvGxD """ import numpy as np import pandas as pd import joblib from sklearn.base import BaseEstimator, TransformerMixin DYNAMIC_FEATURES = [ "ndvi", "t2m_c", "td2m_c", "rh_pct", "tp_m", "ssrd_jm2" ] STATIC_FEATURES = [ "sand", "silt", "clay", "soc", "ph", "bdod", "cec", "nitrogen", "phosphorus", "potassium", "lc_type1" ] LAGS = [1, 2, 3] REQUIRED_DYNAMIC = [ "year", "month", "ndvi", "t2m_c", "td2m_c", "rh_pct", "tp_m", "ssrd_jm2" ] # UTILS class FeatureFilter(BaseEstimator, TransformerMixin): def __init__(self, expected_features): self.expected_features = expected_features def fit(self, X, y=None): return self def transform(self, X): X = X.copy() X = X[[c for c in self.expected_features if c in X.columns]] for c in self.expected_features: if c not in X.columns: X[c] = np.nan return X[self.expected_features] def validate_api_payload(payload): if len(payload) < 3: raise ValueError("At least 3 months of data are required") for item in payload: for f in REQUIRED_DYNAMIC: if f not in item["features"]: raise ValueError(f"Missing required feature: {f}") def sanitize_features(df): df["ndvi"] = df["ndvi"].clip(-1, 1) df["rh_pct"] = df["rh_pct"].clip(0, 100) df["tp_m"] = df["tp_m"].clip(lower=0) df["ssrd_jm2"] = df["ssrd_jm2"].clip(lower=0) return df forecast_models = { f: joblib.load(f"xgb_forecast_{f}.pkl") for f in DYNAMIC_FEATURES } cls_model = joblib.load("xgb_desertification_pipeline.pkl") label_encoder = joblib.load("label_encoder.pkl") feature_order = joblib.load("feature_names.pkl") # API → DataFrame def api_payload_to_df(payload): rows = [] for item in payload: row = item["features"].copy() row["location_name"] = item["metadata"]["location_name"] rows.append(row) df = pd.DataFrame(rows) df = df.rename(columns={"LC_Type1": "lc_type1"}) df = df.drop(columns=["latitude", "longitude"], errors="ignore") return df # PREPARE TIME SERIES def prepare_time_series(df): df = df.sort_values( ["location_name", "year", "month"] ).reset_index(drop=True) df["month_sin"] = np.sin(2 * np.pi * df["month"] / 12) df["month_cos"] = np.cos(2 * np.pi * df["month"] / 12) for col in DYNAMIC_FEATURES: for lag in LAGS: df[f"{col}_lag{lag}"] = ( df.groupby("location_name")[col].shift(lag) ) df = df.dropna().reset_index(drop=True) return df # FORECAST def forecast_future(df, years=5): months = years * 12 forecast_feature_cols = ( DYNAMIC_FEATURES + ["month_sin", "month_cos"] + [f"{c}_lag{l}" for c in DYNAMIC_FEATURES for l in LAGS] ) last_row = df.iloc[-1].copy() forecasts = [] year = int(last_row["year"]) month = int(last_row["month"]) for _ in range(months): month += 1 if month > 12: month = 1 year += 1 last_row["month_sin"] = np.sin(2 * np.pi * month / 12) last_row["month_cos"] = np.cos(2 * np.pi * month / 12) row_pred = {"year": year, "month": month} for feature in DYNAMIC_FEATURES: X = last_row[forecast_feature_cols].values.reshape(1, -1) pred = forecast_models[feature].predict(X)[0] if feature == "ssrd_jm2": pred = np.expm1(pred) row_pred[feature] = pred last_row[f"{feature}_lag3"] = last_row[f"{feature}_lag2"] last_row[f"{feature}_lag2"] = last_row[f"{feature}_lag1"] last_row[f"{feature}_lag1"] = pred forecasts.append(row_pred) return pd.DataFrame(forecasts) # CLASSIFICATION def classify_risk(future_df, static_row): for col in STATIC_FEATURES: future_df[col] = static_row[col] feature_filter = FeatureFilter(feature_order) X = feature_filter.transform(future_df) encoded = cls_model.predict(X) labels = label_encoder.inverse_transform(encoded) proba = cls_model.predict_proba(X).max(axis=1) future_df["risk_level"] = labels future_df["risk_confidence"] = proba return future_df # MAIN PIPELINE def run_pipeline(api_payload, years=5): validate_api_payload(api_payload) df = api_payload_to_df(api_payload) df = sanitize_features(df) ts_df = prepare_time_series(df) future = forecast_future(ts_df, years) static_row = ts_df.iloc[-1] final = classify_risk(future, static_row) return { "success": True, "forecast": final[ ["year", "month"] + DYNAMIC_FEATURES + ["risk_level", "risk_confidence"] ].to_dict(orient="records") }