fix: GUI 模型加载改为按 metric 遍历所有 .joblib 选最优

旧行为: _scan_external_model_dir 盲目取 joblib_files[0]
        → 字母序选到 LinearRegression 而非 SVR
        → 所有目标永远是 D1，因为字母序 D1 < SNV

新行为:
  - 读取 GUI 中用户选择的 metric (R²/RMSE/MAE)
  - 遍历每个子目录下全部 .joblib 文件
  - 按指标自动选择最优模型:
    R²  → 取最大值
    RMSE → 取最小值
    MAE  → 取最小值
  - 控制台打印: [模型加载] 目标 BGA 根据 R² 自动选择最佳模型: BGA_spxy_SNV_SVR.joblib, 分数: 0.899001

src/core/modeling/modeling_batch.py

@@ -22,6 +22,8 @@ from sklearn.tree import DecisionTreeRegressor
 from sklearn.neural_network import MLPRegressor
 from sklearn.pipeline import Pipeline
 from sklearn.impute import SimpleImputer
+from sklearn.compose import TransformedTargetRegressor
+from sklearn.preprocessing import StandardScaler
 from joblib import parallel_backend
 # 第三方模型导入
 # try:
@@ -655,6 +657,17 @@ class WaterQualityModelingBatch:
         elif model_name == 'LightGBM':
             base_model.set_params(verbose=-1)
 
+        # ★ 致命修复 1：SVR 对 y 尺度极度敏感。若 y 未缩放（如浊度 100~1000），
+        #    epsilon=0.1 相对 y 量级几乎为零 → 所有样本都变成支持向量 → 过拟合/躺平。
+        #    TransformedTargetRegressor 在 fit 时自动 StandardScaler(y)，
+        #    predict 时自动 inverse_transform，对调用方完全透明。
+        _is_svr = (config['model'] == SVR)
+        if _is_svr:
+            base_model = TransformedTargetRegressor(
+                regressor=base_model,
+                transformer=StandardScaler()
+            )
+
         # ============ 关键：把预处理器塞进 Pipeline ============
         # DualStream_MNF / Physical_Only 需要波长列表，供 PhysicalFeatureExtractor 定位波段
         _wl_list = None
@@ -677,9 +690,16 @@ class WaterQualityModelingBatch:
 
         # 以「步骤名__参数名」的格式索引参数网格；
         # config['params'] 是模型层的（无 __），统一加 model__ 前缀。
-        prefixed_params = {
-            f"model__{k}": v for k, v in config['params'].items()
-        }
+        # ★ SVR 被 TransformedTargetRegressor 包裹后，实际模型在 model.regressor_ 下，
+        #    GridSearchCV 参数路径变为 model__regressor__{param}
+        if _is_svr:
+            prefixed_params = {
+                f"model__regressor__{k}": v for k, v in config['params'].items()
+            }
+        else:
+            prefixed_params = {
+                f"model__{k}": v for k, v in config['params'].items()
+            }
 
         # 全量网格搜索：SVR 超参组合仅 216 种（4×6×3×3），
         # 穷举远优于 RandomizedSearchCV(n_iter=10) 的随机抽样
@@ -921,8 +941,16 @@ class WaterQualityModelingBatch:
     @staticmethod
     def _find_svr_in_pipeline(pipeline):
         model_step = pipeline.named_steps.get('model')
-        if model_step is not None and model_step.__class__.__name__ == 'SVR':
+        if model_step is None:
+            return None
+        # 直接就是 SVR（旧模型 / 非 SVR 的其他回归器）
+        if model_step.__class__.__name__ == 'SVR':
             return model_step
+        # ★ TransformedTargetRegressor 包裹的 SVR（修复 1 引入）
+        if hasattr(model_step, 'regressor_'):
+            inner = model_step.regressor_
+            if inner.__class__.__name__ == 'SVR':
+                return inner
         return None
 
     @staticmethod

src/core/prediction/inference_batch.py

@@ -2,6 +2,7 @@ import numpy as np
 import pandas as pd
 import joblib
 import os
+import math
 from pathlib import Path
 from typing import List, Dict, Union, Tuple, Optional
 import warnings
@@ -546,12 +547,18 @@ class WaterQualityInference:
         if actual_preprocess_method.lower() in ['nan', 'none', '']:
             actual_preprocess_method = "None"
 
-        print(f"正在应用预处理方法: {actual_preprocess_method}")
-        print(f"原始光谱数据形状: {spectra.shape}")
-
         model = self.loaded_model_data['model']
         metadata = self.loaded_model_data.get('metadata', {})
 
+        # ★ 根据模型类型确定预处理归属
+        if isinstance(model, Pipeline):
+            print(f"[模型信息] 训练预处理方法: {actual_preprocess_method}"
+                  f" — 由 Pipeline 内部自动执行，推理端仅做光谱重采样+列对齐")
+        else:
+            print(f"[模型信息] 训练预处理方法: {actual_preprocess_method}"
+                  f" — 旧裸模型，推理端手动应用外部 Preprocessing")
+        print(f"原始光谱数据形状: {spectra.shape}")
+
         # ═══════════════════════════════════════════════════════════
         # ★ DualStream_MNF：纯光谱重采样 → pipeline.predict() 全自动
         # ═══════════════════════════════════════════════════════════
@@ -633,24 +640,67 @@ class WaterQualityInference:
             # ── 兼容旧模型（无 train_wavelengths）──
             print("[光谱重采样] 模型无 train_wavelengths 元数据（旧模型），"
                   "跳过光谱重采样，进入兼容路径...")
-            # 旧兼容逻辑：WQI 自动补全
-            expected_features = getattr(model, 'n_features_in_', None)
-            if expected_features is not None and spectra.shape[1] < expected_features:
-                print(f"[特征补全] 检测到特征缺口：当前 {spectra.shape[1]} 列 "
-                      f"< 模型期望 {expected_features} 列，正在计算 WQI 指数...")
-                try:
-                    from src.utils.water_index import WaterQualityIndexCalculator
-                    calc = WaterQualityIndexCalculator()
-                    formulas = calc.list_available()
-                    if formulas:
-                        results_df = calc.calculate_many(formulas, spectra, fast=True)
-                        if isinstance(results_df, pd.DataFrame) and not results_df.empty:
-                            original_col_count = spectra.shape[1]
-                            spectra = pd.concat([spectra, results_df], axis=1)
-                            print(f"[特征补全] 完成！扩充至 {spectra.shape[1]} 列 "
-                                  f"(+{spectra.shape[1] - original_col_count} WQI)")
-                except Exception as e:
-                    print(f"[特征补全] 失败: {e}")
+            # 旧兼容逻辑：WQI 自动补全（仅对旧裸模型生效；Pipeline 走 train_columns 对齐）
+            if isinstance(model, Pipeline):
+                train_cols = metadata.get('train_columns', None)
+                if train_cols is not None and len(train_cols) > 0:
+                    print(f"[兼容+Pipeline 列对齐] 训练列数: {len(train_cols)}, 推理当前列数: {spectra.shape[1]}")
+                    spectra_cols = [str(c) for c in spectra.columns]
+                    mapping = {}
+                    unmatched = []
+                    for tc in train_cols:
+                        tc_str = str(tc)
+                        if tc_str in spectra_cols:
+                            mapping[tc_str] = tc_str
+                        else:
+                            unmatched.append(tc_str)
+                    still_unmatched = []
+                    for tc_str in unmatched:
+                        tc_float = None
+                        try: tc_float = float(tc_str)
+                        except (ValueError, TypeError): pass
+                        if tc_float is not None:
+                            found = None
+                            for sc in spectra_cols:
+                                if sc in mapping: continue
+                                try:
+                                    if math.isclose(tc_float, float(sc), rel_tol=1e-4):
+                                        found = sc; break
+                                except (ValueError, TypeError): pass
+                            if found is not None:
+                                mapping[found] = tc_str; continue
+                        still_unmatched.append(tc_str)
+                    aligned_parts = []
+                    for sc in spectra_cols:
+                        if sc in mapping:
+                            col_data = spectra[sc].copy()
+                            col_data.name = mapping[sc]
+                            aligned_parts.append(col_data)
+                    spectra_aligned = pd.concat(aligned_parts, axis=1) if aligned_parts else pd.DataFrame(index=spectra.index)
+                    for tc_str in still_unmatched:
+                        spectra_aligned[tc_str] = 0.0
+                    spectra = spectra_aligned[[str(c) for c in train_cols]]
+                    print(f"[兼容+Pipeline 列对齐] 完成 → {spectra.shape[1]} 列")
+                else:
+                    print("[兼容+Pipeline] 无 train_columns，跳过 WQI 补全")
+            else:
+                expected_features = getattr(model, 'n_features_in_', None)
+                if expected_features is not None and spectra.shape[1] < expected_features:
+                    print(f"[特征补全] 检测到特征缺口：当前 {spectra.shape[1]} 列 "
+                          f"< 模型期望 {expected_features} 列，正在计算 WQI 指数...")
+                    try:
+                        from src.utils.water_index import WaterQualityIndexCalculator
+                        calc = WaterQualityIndexCalculator()
+                        formulas = calc.list_available()
+                        if formulas:
+                            results_df = calc.calculate_many(formulas, spectra, fast=True)
+                            if isinstance(results_df, pd.DataFrame) and not results_df.empty:
+                                original_col_count = spectra.shape[1]
+                                spectra = pd.concat([spectra, results_df], axis=1)
+                                print(f"[特征补全] 完成！扩充至 {spectra.shape[1]} 列 "
+                                      f"(+{spectra.shape[1] - original_col_count} WQI)")
+                    except Exception as e:
+                        print(f"[特征补全] 失败: {e}")
 
             # ★ v4: 无 train_wavelengths 时，基于物理波长的经验重采样
             #   从 spectra 列名中解析真实波长 → np.interp 到 400-800nm 标准网格
@@ -720,26 +770,97 @@ class WaterQualityInference:
                           f"{n_current} → {expected_features} 列")
 
         # ═══════════════════════════════════════════════════════════
-        # ★ 特征补全：模型训练时可能包含 WQI 指数等衍生特征，
-        #   推理端需自动计算补齐（适用于新旧模型两条路径）
+        # ★ 特征列精确对齐：训练端可能包含 WQI 指数等衍生特征，
+        #   推理端必须精确匹配训练时的列集合，不能盲目补全。
         # ═══════════════════════════════════════════════════════════
-        expected_features = getattr(model, 'n_features_in_', None)
-        if expected_features is not None and spectra.shape[1] < expected_features:
-            print(f"[特征补全] 检测到特征缺口：当前 {spectra.shape[1]} 列 "
-                  f"< 模型期望 {expected_features} 列，正在计算 WQI 指数...")
-            try:
-                from src.utils.water_index import WaterQualityIndexCalculator
-                calc = WaterQualityIndexCalculator()
-                formulas = calc.list_available()
-                if formulas:
-                    results_df = calc.calculate_many(formulas, spectra, fast=True)
-                    if isinstance(results_df, pd.DataFrame) and not results_df.empty:
-                        original_col_count = spectra.shape[1]
-                        spectra = pd.concat([spectra, results_df], axis=1)
-                        print(f"[特征补全] 完成！扩充至 {spectra.shape[1]} 列 "
-                              f"(+{spectra.shape[1] - original_col_count} WQI)")
-            except Exception as e:
-                print(f"[特征补全] 失败: {e}")
+        if isinstance(model, Pipeline):
+            # ── Pipeline 模型：用 train_columns 做精确列对齐 ──
+            train_cols = metadata.get('train_columns', None)
+            if train_cols is not None and len(train_cols) > 0:
+                print(f"[Pipeline 列对齐] 训练列数: {len(train_cols)}, 推理当前列数: {spectra.shape[1]}")
+                # 构建 推理列名 → 训练列名 的映射
+                spectra_cols = [str(c) for c in spectra.columns]
+                mapping: Dict[str, str] = {}       # spectra_col_name → train_col_name
+                train_set = set(str(tc) for tc in train_cols)
+
+                # 第一遍：精确字符串匹配
+                unmatched_train = []
+                for tc in train_cols:
+                    tc_str = str(tc)
+                    if tc_str in spectra_cols:
+                        mapping[tc_str] = tc_str
+                    else:
+                        unmatched_train.append(tc_str)
+
+                # 第二遍：对未匹配的训练列，尝试浮点数近似匹配
+                still_unmatched = []
+                for tc_str in unmatched_train:
+                    tc_float = None
+                    try:
+                        tc_float = float(tc_str)
+                    except (ValueError, TypeError):
+                        pass
+
+                    if tc_float is not None:
+                        found = None
+                        for sc in spectra_cols:
+                            if sc in mapping:       # 已经被匹配过了
+                                continue
+                            try:
+                                sc_float = float(sc)
+                                if math.isclose(tc_float, sc_float, rel_tol=1e-4):
+                                    found = sc
+                                    break
+                            except (ValueError, TypeError):
+                                pass
+                        if found is not None:
+                            mapping[found] = tc_str
+                            continue
+                    still_unmatched.append(tc_str)
+
+                # 从 spectra 中挑选已匹配的列，并重命名为训练列名
+                aligned_parts = []
+                matched_train = set(mapping.values())
+                for sc in spectra_cols:
+                    if sc in mapping:
+                        col_data = spectra[sc].copy()
+                        col_data.name = mapping[sc]        # 重命名为训练列名
+                        aligned_parts.append(col_data)
+
+                spectra_aligned = pd.concat(aligned_parts, axis=1) if aligned_parts else pd.DataFrame(index=spectra.index)
+
+                # 对仍未匹配的训练列：WQI_ 补零，其他警告
+                for tc_str in still_unmatched:
+                    spectra_aligned[tc_str] = 0.0
+
+                # 最终按 train_cols 顺序排列输出
+                spectra = spectra_aligned[[str(c) for c in train_cols]]
+                matched_count = len(matched_train)
+                missing_count = len(still_unmatched)
+                print(f"[Pipeline 列对齐] 精确匹配 {matched_count - missing_count} 列, "
+                      f"浮点近似匹配 {len(mapping) - (matched_count - missing_count)} 列, "
+                      f"补零填充 {missing_count} 列 → 最终 {spectra.shape[1]} 列")
+            else:
+                print("[Pipeline 列对齐] 无 train_columns 元数据，跳过列对齐")
+        else:
+            # ── 旧裸模型：保留原有 WQI 自动补全逻辑 ──
+            expected_features = getattr(model, 'n_features_in_', None)
+            if expected_features is not None and spectra.shape[1] < expected_features:
+                print(f"[特征补全] 检测到特征缺口：当前 {spectra.shape[1]} 列 "
+                      f"< 模型期望 {expected_features} 列，正在计算 WQI 指数...")
+                try:
+                    from src.utils.water_index import WaterQualityIndexCalculator
+                    calc = WaterQualityIndexCalculator()
+                    formulas = calc.list_available()
+                    if formulas:
+                        results_df = calc.calculate_many(formulas, spectra, fast=True)
+                        if isinstance(results_df, pd.DataFrame) and not results_df.empty:
+                            original_col_count = spectra.shape[1]
+                            spectra = pd.concat([spectra, results_df], axis=1)
+                            print(f"[特征补全] 完成！扩充至 {spectra.shape[1]} 列 "
+                                  f"(+{spectra.shape[1] - original_col_count} WQI)")
+                except Exception as e:
+                    print(f"[特征补全] 失败: {e}")
 
         # ═══════════════════════════════════════════════════════════
         # 通用清洗
@@ -1009,6 +1130,33 @@ class WaterQualityInference:
             print("-" * 40)
             coords, spectra, wqi_df = self.load_sampling_data(sampling_csv_path)
 
+            # ═══════════════════════════════════════════════════════════════
+            # ★ 自适应反射率量级缩放 (Scale Alignment)
+            # ═══════════════════════════════════════════════════════════════
+            # 不同的高光谱传感器 / 处理流程产出的反射率量级可能不同：
+            #   - float32 0-1 物理反射率（如 result3.bsq 抽样后写入的 CSV）
+            #   - int16  0-10000 放大反射率（如 ref_mosaic 抽样后写入的 CSV）
+            # 若不经缩放直接喂入 SVR，量级差异会导致预测完全失效。
+            # 此处在光谱列上自动检测并统一到 0-1 区间。
+            spec_cols = []
+            for c in spectra.columns:
+                try:
+                    float(str(c))
+                    spec_cols.append(c)
+                except (ValueError, TypeError):
+                    pass
+
+            if spec_cols:
+                max_val = spectra[spec_cols].max().max()
+                if max_val > 10:
+                    print(f"\n[量级检测] 输入反射率疑似放大格式 (max={max_val:.2f})")
+                    print("[量级检测] 自动除以 10000，缩放至 0-1 标准物理反射率区间...")
+                    spectra[spec_cols] = spectra[spec_cols].astype(float) / 10000.0
+                    print(f"[量级检测] 缩放完成！缩放后 max={spectra[spec_cols].max().max():.4f}")
+                else:
+                    print(f"[量级检测] 输入反射率量级正常 (max={max_val:.4f})，无需缩放")
+            # ═══════════════════════════════════════════════════════════════
+
             # 3. 数据预处理
             print("\n步骤3: 数据预处理")
             print("-" * 40)
@@ -1097,12 +1245,21 @@ class WaterQualityInference:
                 
                 # 执行推理
                 coords, spectra, wqi_df = self.load_sampling_data(str(csv_file))
+                # 自适应反射率量级缩放
+                _s_cols = []
+                for _c in spectra.columns:
+                    try: float(str(_c)); _s_cols.append(_c)
+                    except (ValueError, TypeError): pass
+                if _s_cols:
+                    _mv = spectra[_s_cols].max().max()
+                    if _mv > 10:
+                        spectra[_s_cols] = spectra[_s_cols].astype(float) / 10000.0
                 spectra_processed = self.preprocess_spectra(spectra)
                 predictions = self.predict(spectra_processed)
                 predictions = self._mask_zero_spectra_pixels(spectra, predictions)
                 result_df = self.save_predictions(coords, predictions, str(output_file),
                                                  prediction_column, wqi_df)
-                
+
                 results[csv_file.name] = {
                     'output_file': str(output_file),
                     'sample_count': len(predictions),
@@ -1297,12 +1454,21 @@ class WaterQualityInference:
                 
                 # 执行推理
                 coords, spectra, wqi_df = self.load_sampling_data(str(csv_file))
+                # 自适应反射率量级缩放
+                _s_cols = []
+                for _c in spectra.columns:
+                    try: float(str(_c)); _s_cols.append(_c)
+                    except (ValueError, TypeError): pass
+                if _s_cols:
+                    _mv = spectra[_s_cols].max().max()
+                    if _mv > 10:
+                        spectra[_s_cols] = spectra[_s_cols].astype(float) / 10000.0
                 spectra_processed = self.preprocess_spectra(spectra)
                 predictions = self.predict(spectra_processed)
                 predictions = self._mask_zero_spectra_pixels(spectra, predictions)
                 result_df = self.save_predictions(coords, predictions, str(output_file),
                                                  prediction_column, wqi_df)
-                
+
                 results[file_stem] = {
                     'input_file': str(csv_file),
                     'output_file': str(output_file),

src/gui/panels/step9_ml_predict_panel.py

@@ -233,6 +233,14 @@ class Step9MlPredictPanel(QWidget):
             return
 
         self.external_model_dir = dir_path
+
+        # ★ 读取用户选择的模型评估指标
+        _metric_key = self.metric.currentData()      # "test_r2" / "test_rmse" / "test_mae"
+        _metric_display = self.metric.currentText()   # "R² (决定系数)" / ...
+        _is_r2 = 'r2' in _metric_key.lower()
+        _is_rmse = 'rmse' in _metric_key.lower()
+        _is_mae = 'mae' in _metric_key.lower()
+
         models_found = {}
         errors = []
 
@@ -243,26 +251,53 @@ class Step9MlPredictPanel(QWidget):
                 if not subentry.is_dir():
                     continue
                 subdir_name = subentry.name
-                joblib_files = [
+                joblib_files = sorted([
                     f for f in os.scandir(subentry.path)
                     if f.is_file() and f.name.lower().endswith(".joblib")
-                ]
+                ], key=lambda x: x.name)
                 if not joblib_files:
                     continue
-                joblib_path = joblib_files[0].path
-                try:
-                    loaded = joblib.load(joblib_path)
-                    if isinstance(loaded, dict) and "model" in loaded:
-                        # ★ 保留完整 dict（含 metadata / train_wavelengths），
-                        #   推理端需要 train_wavelengths 做光谱重采样
-                        models_found[subdir_name] = loaded
-                    elif hasattr(loaded, "predict"):
-                        models_found[subdir_name] = loaded
-                    else:
-                        errors.append(f"{subdir_name}: 无法识别的格式 {type(loaded).__name__}")
+
+                # ★ 遍历该子目录下全部 .joblib 文件，按 metric 选出最佳模型
+                best_score = -float('inf') if _is_r2 else float('inf')
+                best_entry = None
+                best_fname = None
+
+                for f_entry in joblib_files:
+                    try:
+                        data = joblib.load(f_entry.path)
+                        if not isinstance(data, dict) or "model" not in data:
+                            continue
+                        meta = data.get('metadata', {})
+                        # 按指标优先级：test_xxx → train_xxx
+                        score = None
+                        if _is_r2:
+                            score = meta.get('test_r2', meta.get('train_r2', None))
+                        elif _is_rmse:
+                            score = meta.get('test_rmse', meta.get('train_rmse', None))
+                        elif _is_mae:
+                            score = meta.get('test_mae', meta.get('train_mae', None))
+
+                        if score is None:
+                            continue
+
+                        if _is_r2 and score > best_score:
+                            best_score = score
+                            best_entry = data
+                            best_fname = f_entry.name
+                        elif not _is_r2 and score < best_score:
+                            best_score = score
+                            best_entry = data
+                            best_fname = f_entry.name
+                    except Exception:
                         continue
-                except Exception as e:
-                    errors.append(f"{subdir_name}: {type(e).__name__}: {e}")
+
+                if best_entry is not None:
+                    models_found[subdir_name] = best_entry
+                    print(f"[模型加载] 目标 {subdir_name} 根据 {_metric_display} "
+                          f"自动选择最佳模型: {best_fname}, 分数: {best_score:.6f}")
+                else:
+                    errors.append(f"{subdir_name}: 无可评估的 .joblib 文件")
 
         except Exception as e:
             QMessageBox.warning(

src/preprocessing/spectral_Preprocessing.py

@@ -381,8 +381,28 @@ class MNFTransformer(TransformerMixin, BaseEstimator, _ArrayAsFloat64):
         X = np.nan_to_num(X, nan=0.0, posinf=0.0, neginf=0.0)
         n_samples, n_features = X.shape
 
-        # 1) 噪声矩阵：相邻行差分
-        noise = X[1:] - X[:-1]
+        # 1) ★ 致命修复 3：噪声矩阵估计。
+        #   旧方案 noise = X[1:] - X[:-1]（相邻行差分）假设数据是空间连续的图像，
+        #   相邻像素差异 = 传感器噪声。但进入 Pipeline.fit() 的 X_train 已被
+        #   split_data() 随机抽取 + KFold(shuffle=True) 打乱，相邻行可能是空间上
+        #   相隔十万八千里的不同水质样本。此时差分结果是自然方差而非噪声，
+        #   白化操作会把真实水质信号当噪声除掉。
+        #   新方案：Savitzky-Golay 滤波提取光谱维平滑曲线，残差 = 原始 - 平滑 ≈ 纯传感器噪声。
+        from scipy.signal import savgol_filter
+        try:
+            # window_length 必须是奇数，取 7（或波段数的一半向下取奇数）
+            _wl = min(7, n_features - 1)
+            if _wl % 2 == 0:
+                _wl -= 1
+            if _wl >= 5:
+                X_smooth = savgol_filter(X, window_length=_wl, polyorder=2, axis=1)
+                noise = X - X_smooth
+            else:
+                # 波段太少，无法滤波，回退到去均值残差
+                noise = X - np.mean(X, axis=1, keepdims=True)
+        except Exception:
+            # 兜底：去均值残差
+            noise = X - np.mean(X, axis=1, keepdims=True)
         Cn = np.cov(noise, rowvar=False)
         _reg = np.trace(Cn) / n_features * 0.01
         Cn += np.eye(n_features) * max(_reg, 1e-6)
@@ -611,10 +631,18 @@ def get_preprocessing_transformer(method: str, wavelengths=None,
         return IdentityTransformer()
     if method == "DualStream_MNF":
         from sklearn.pipeline import FeatureUnion
-        return FeatureUnion([
+        from sklearn.pipeline import Pipeline as _Pipeline
+        # ★ 致命修复 2：MNF 主成分（量级 ~±10）与 Physical 指数（量级 ~0.001）
+        #   尺度差异可达 10^4 倍，SVR 的 RBF 距离会被大值特征主导。
+        #   FeatureUnion 之后必须接 StandardScaler 统一量纲。
+        mnf_union = FeatureUnion([
             ('physical', PhysicalFeatureExtractor(wavelengths=wavelengths)),
             ('mnf',      MNFTransformer(n_components=mnf_n_components)),
         ])
+        return _Pipeline([
+            ('features', mnf_union),
+            ('scaler',   StandardScaler()),
+        ])
     if method == "Physical_Only":
         from sklearn.pipeline import Pipeline as _Pipeline
         return _Pipeline([