fix: DualStream_MNF 推理先重采样308→训练网格再进Pipeline

- 推理数据 308 波段 vs 训练时 113 列(50光谱+63WQI)维度不同
- SimpleImputer fit在113列上不接受308列输入
- 修复: 先 np.interp 重采样到训练波长网格, 再 WQI 补齐,
  然后喂入 Pipeline 的 imputer+preproc+cleaner 最终进 SVR

src/core/prediction/inference_batch.py

@@ -478,13 +478,54 @@ class WaterQualityInference:
 
         # ═══════════════════════════════════════════════════════════
         # ★ DualStream_MNF 快速通道：Pipeline 已内置 MNF + 物理指数
-        #   无需手动重采样或 WQI 补齐，直接走 Pipeline 的 preproc 步骤
+        #   但需先将推理光谱重采样到训练特征空间（308→113列），
+        #   再走 Pipeline 的 imputer+preproc 步骤
         # ═══════════════════════════════════════════════════════════
         if actual_preprocess_method == "DualStream_MNF" and isinstance(model, Pipeline):
-            print("[DualStream_MNF] 推理直通 Pipeline（MNF+物理指数已内置）")
+            print("[DualStream_MNF] 推理：先重建训练特征集再直通 Pipeline")
-            # Pipeline 的 imputer + preproc 步骤会处理一切
+            # 1) 重采样 308 波段 → 训练波长网格
-            spectra_processed = model.named_steps['imputer'].transform(spectra.values)
+            train_wl = metadata.get('train_wavelengths', None)
-            spectra_processed = model.named_steps['preproc'].transform(spectra_processed)
+            train_cols = metadata.get('train_columns', None)
+            if train_wl is not None and len(train_wl) > 0 and train_cols is not None:
+                # 从 spectra 中提取光谱列（列名可转 float 的即为波长列）
+                spec_cols = []
+                for c in spectra.columns:
+                    try:
+                        float(str(c)); spec_cols.append(c)
+                    except (ValueError, TypeError):
+                        pass
+                spec_data = spectra[spec_cols].values.astype(np.float64)
+                src_wl = np.array([float(c) for c in spec_cols], dtype=np.float64)
+                dst_wl = np.array(train_wl, dtype=np.float64)
+                resampled = np.zeros((spec_data.shape[0], len(dst_wl)), dtype=np.float64)
+                for i in range(spec_data.shape[0]):
+                    resampled[i] = np.interp(dst_wl, src_wl, spec_data[i],
+                                             left=np.nan, right=np.nan)
+                resampled = np.nan_to_num(resampled, nan=0.0)
+                # 2) 计算 WQI 补齐到训练列数
+                wl_col_names = [f'{wl:.6f}' for wl in train_wl]
+                spectra_df = pd.DataFrame(resampled, columns=wl_col_names)
+                n_need = len(train_cols)
+                if spectra_df.shape[1] < n_need:
+                    print(f"[DualStream_MNF] 计算 WQI 补齐: {spectra_df.shape[1]} → {n_need}")
+                    try:
+                        from src.utils.water_index import WaterQualityIndexCalculator
+                        calc = WaterQualityIndexCalculator()
+                        formulas = calc.list_available()
+                        wqi = calc.calculate_many(formulas, spectra_df, fast=True)
+                        spectra_df = pd.concat([spectra_df, wqi], axis=1)
+                    except Exception as e:
+                        print(f"[DualStream_MNF] WQI 失败: {e}")
+                    # 如果还不够，补零
+                    while spectra_df.shape[1] < n_need:
+                        spectra_df[f'_pad_{spectra_df.shape[1]}'] = 0.0
+                    spectra_df = spectra_df.iloc[:, :n_need]
+                # 3) 喂入 Pipeline
+                spectra_processed = model.named_steps['imputer'].transform(spectra_df.values)
+                spectra_processed = model.named_steps['preproc'].transform(spectra_processed)
+            else:
+                spectra_processed = model.named_steps['imputer'].transform(spectra.values)
+                spectra_processed = model.named_steps['preproc'].transform(spectra_processed)
             spectra_processed = np.nan_to_num(spectra_processed, nan=0.0, posinf=0.0, neginf=0.0)
             print(f"[DualStream_MNF] 预处理完成: {spectra_processed.shape}")
             print(f"[特征对齐] 最终输入维度: {spectra_processed.shape}")