"""Evaluate actual RainNet rollout outputs and create diagnostic figures.""" import json from pathlib import Path import matplotlib matplotlib.use("Agg") import matplotlib.pyplot as plt import numpy as np import torch import torch.nn.functional as F import yaml ROOT = Path(__file__).resolve().parents[1] def load_config(): with (ROOT / "conf/config.yaml").open(encoding="utf-8") as handle: return yaml.safe_load(handle) def csi(prediction, target, threshold): pred_event, target_event = prediction >= threshold, target >= threshold hits = np.logical_and(pred_event, target_event).sum(dtype=np.float64) false_alarms = np.logical_and(pred_event, ~target_event).sum(dtype=np.float64) misses = np.logical_and(~pred_event, target_event).sum(dtype=np.float64) denominator = hits + false_alarms + misses return float(hits / denominator) if denominator else 0.0 def fss(prediction, target, threshold, window): pred = torch.from_numpy((prediction >= threshold).astype(np.float32))[None, None] obs = torch.from_numpy((target >= threshold).astype(np.float32))[None, None] if window > 1: padding = window // 2 pred = F.avg_pool2d(pred, window, stride=1, padding=padding) obs = F.avg_pool2d(obs, window, stride=1, padding=padding) pred = pred[..., : prediction.shape[0], : prediction.shape[1]] obs = obs[..., : target.shape[0], : target.shape[1]] numerator = torch.sum((pred - obs) ** 2) denominator = torch.sum(pred**2) + torch.sum(obs**2) return float(1.0 - numerator / denominator) if denominator > 0 else 0.0 def metric_series(predictions, targets, thresholds, windows): output = [] for index, (prediction, target) in enumerate(zip(predictions, targets)): pred_rate, target_rate = prediction * 12.0, target * 12.0 output.append( { "lead_minutes": (index + 1) * 5, "mae_mm_h": float(np.mean(np.abs(pred_rate - target_rate), dtype=np.float64)), "csi": {str(t): csi(pred_rate, target_rate, t) for t in thresholds}, "fss": { str(t): {str(w): fss(pred_rate, target_rate, t, w) for w in windows} for t in thresholds }, } ) return output def main(): config = load_config() output_dir = ROOT / config["inference"]["output_dir"] required = ["inputs.npy", "predictions.npy", "targets.npy", "persistence.npy"] missing = [name for name in required if not (output_dir / name).exists()] if missing: raise FileNotFoundError(f"Missing inference outputs: {missing}") inputs = np.load(output_dir / "inputs.npy") predictions = np.load(output_dir / "predictions.npy") targets = np.load(output_dir / "targets.npy") persistence = np.load(output_dir / "persistence.npy") for name, array in (("prediction", predictions), ("target", targets), ("persistence", persistence)): if array.shape != predictions.shape or not np.isfinite(array).all(): raise ValueError(f"Invalid {name}: shape={array.shape}, finite={np.isfinite(array).all()}") thresholds = config["evaluation"]["thresholds_mm_h"] windows = config["evaluation"]["fss_windows_km"] rainnet_metrics = metric_series(predictions, targets, thresholds, windows) persistence_metrics = metric_series(persistence, targets, thresholds, windows) metrics = { "units": "mm/h", "rainnet": rainnet_metrics, "persistence": persistence_metrics, } result_dir = ROOT / config["evaluation"]["result_dir"] result_dir.mkdir(parents=True, exist_ok=True) with (result_dir / "metrics.json").open("w", encoding="utf-8") as handle: json.dump(metrics, handle, indent=2) history_path = result_dir / "train_history.json" with history_path.open(encoding="utf-8") as handle: history = json.load(handle) fig, ax = plt.subplots(figsize=(6, 4)) ax.plot(history["train_loss"], marker="o", label="Train") ax.plot(history["validation_loss"], marker="o", label="Validation") ax.set(xlabel="Epoch", ylabel="Log-Cosh loss", title="RainNet smoke training") ax.legend() fig.tight_layout() fig.savefig(result_dir / "loss.png", dpi=150) plt.close(fig) selected = [0, 5, 11] fig, axes = plt.subplots(3, 5, figsize=(16, 10)) for row, index in enumerate(selected): panels = [inputs[-1], targets[index], predictions[index], persistence[index], predictions[index] - targets[index]] titles = ["Last Input", "Truth", "RainNet Prediction", "Persistence", "Prediction Error"] for axis, panel, title in zip(axes[row], panels, titles): image = axis.imshow(panel, cmap="RdBu_r" if title == "Prediction Error" else "Blues") axis.set_title(f"{title}\n{(index + 1) * 5} min") axis.axis("off") fig.colorbar(image, ax=axis, fraction=0.046) fig.tight_layout() fig.savefig(result_dir / "forecast_comparison.png", dpi=120) plt.close(fig) leads = [item["lead_minutes"] for item in rainnet_metrics] fig, axes = plt.subplots(1, 3, figsize=(15, 4)) axes[0].plot(leads, [item["mae_mm_h"] for item in rainnet_metrics], label="RainNet") axes[0].plot(leads, [item["mae_mm_h"] for item in persistence_metrics], label="Persistence") axes[0].set(title="MAE", xlabel="Lead time (min)", ylabel="mm/h") for threshold in thresholds: axes[1].plot(leads, [item["csi"][str(threshold)] for item in rainnet_metrics], label=str(threshold)) axes[2].plot(leads, [item["fss"][str(threshold)]["20"] for item in rainnet_metrics], label=str(threshold)) axes[1].set(title="RainNet CSI", xlabel="Lead time (min)", ylabel="CSI") axes[2].set(title="RainNet FSS (20 km)", xlabel="Lead time (min)", ylabel="FSS") axes[0].legend() axes[1].legend(title="mm/h", fontsize=7) axes[2].legend(title="mm/h", fontsize=7) fig.tight_layout() fig.savefig(result_dir / "metrics.png", dpi=150) plt.close(fig) print(f"Prediction shape: {predictions.shape}") print(f"Target shape: {targets.shape}") print(f"Persistence shape: {persistence.shape}") for index in selected: item = rainnet_metrics[index] print(f"Lead {item['lead_minutes']} min MAE: {item['mae_mm_h']:.8f} mm/h") print(f"Lead {item['lead_minutes']} min CSI: {item['csi']}") print(f"Lead {item['lead_minutes']} min FSS: {item['fss']}") if __name__ == "__main__": main()