界面优化

src/core/prediction/inference_batch.py

@@ -555,7 +555,13 @@ class WaterQualityInference:
         print(f"输入数据形状: {spectra_processed.shape}")
 
         try:
-            predictions = model.predict(spectra_processed)
+            # 清洗 NaN / Inf，防止 SVR 等模型报错
+            spectra_clean = np.nan_to_num(spectra_processed, nan=0.0, posinf=0.0, neginf=0.0)
+            if np.any(np.isnan(spectra_clean)) or np.any(np.isinf(spectra_clean)):
+                print("警告: 清洗后数据中仍存在 NaN/Inf，已重置为 0")
+                spectra_clean = np.nan_to_num(spectra_clean, nan=0.0, posinf=0.0, neginf=0.0)
+
+            predictions = model.predict(spectra_clean)
             print(f"预测完成，结果形状: {predictions.shape}")
             print(f"预测值范围: [{np.min(predictions):.4f}, {np.max(predictions):.4f}]")
             print(f"预测值统计: 均值={np.mean(predictions):.4f}, 标准差={np.std(predictions):.4f}")

src/core/water_quality_inversion_pipeline_GUI.py

@@ -1724,7 +1724,11 @@ class WaterQualityInversionPipeline:
                     final_water_mask, temp_shape, geotransform, projection, img_path
                 )
                 
-                # 应用Goodman算法：直接传递文件路径，让算法类使用GDAL逐波段处理
+                # 加载影像数据（Goodman算法需要numpy数组用于后插值）
+                image_array, geotransform, projection = self._load_image_as_array(img_path)
+                print(f"影像尺寸: {image_array.shape}")
+
+                # 应用Goodman算法：传递文件路径
                 goodman = Goodman(img_path, NIR_lower=nir_lower, NIR_upper=nir_upper,
                                 A=goodman_A, B=goodman_B, water_mask=mask_for_algorithm,
                                 output_path=output_path)  # 传递output_path，算法类会保存