fix: 推理端自适应反射率缩放 + Pipeline 列精确对齐

1. 自适应反射率量级缩放 (inference_pipeline/batch_inference/batch_inference_multi_data):
   - 检测光谱列 max > 10 时自动 ÷10000 统一到 0-1 区间
   - 三个推理入口全量同步保护

2. Pipeline 列精确对齐 (preprocess_spectra 两处):
   - 旧: not in 盲目排除多余列 → 140个光谱列被当多余移除
   - 新: 遍历 train_cols，精确字符串匹配 → math.isclose 浮点近似
        匹配列重命名为训练列名，缺失列补零
        最终 spectra[train_cols] 严格按训练顺序输出
   - 兼容路径同步修复

3. 误导性日志修正:
   - 改前: '正在应用预处理方法: D1' → 让用户以为推理端在手动做 D1
   - 改后: '[模型信息] 训练预处理方法: D1 — 由 Pipeline 内部自动执行'

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
+            # 旧兼容逻辑：WQI 自动补全（仅对旧裸模型生效；Pipeline 走 train_columns 对齐）
-            expected_features = getattr(model, 'n_features_in_', None)
+            if isinstance(model, Pipeline):
-            if expected_features is not None and spectra.shape[1] < expected_features:
+                train_cols = metadata.get('train_columns', None)
-                print(f"[特征补全] 检测到特征缺口：当前 {spectra.shape[1]} 列 "
+                if train_cols is not None and len(train_cols) > 0:
-                      f"< 模型期望 {expected_features} 列，正在计算 WQI 指数...")
+                    print(f"[兼容+Pipeline 列对齐] 训练列数: {len(train_cols)}, 推理当前列数: {spectra.shape[1]}")
-                try:
+                    spectra_cols = [str(c) for c in spectra.columns]
-                    from src.utils.water_index import WaterQualityIndexCalculator
+                    mapping = {}
-                    calc = WaterQualityIndexCalculator()
+                    unmatched = []
-                    formulas = calc.list_available()
+                    for tc in train_cols:
-                    if formulas:
+                        tc_str = str(tc)
-                        results_df = calc.calculate_many(formulas, spectra, fast=True)
+                        if tc_str in spectra_cols:
-                        if isinstance(results_df, pd.DataFrame) and not results_df.empty:
+                            mapping[tc_str] = tc_str
-                            original_col_count = spectra.shape[1]
+                        else:
-                            spectra = pd.concat([spectra, results_df], axis=1)
+                            unmatched.append(tc_str)
-                            print(f"[特征补全] 完成！扩充至 {spectra.shape[1]} 列 "
+                    still_unmatched = []
-                                  f"(+{spectra.shape[1] - original_col_count} WQI)")
+                    for tc_str in unmatched:
-                except Exception as e:
+                        tc_float = None
-                    print(f"[特征补全] 失败: {e}")
+                        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，
+        # ★ 特征列精确对齐：训练端可能包含 WQI 指数等衍生特征，
-        #   推理端需自动计算补齐（适用于新旧模型两条路径）
+        #   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 isinstance(model, Pipeline):
-        if expected_features is not None and spectra.shape[1] < expected_features:
+            # ── Pipeline 模型：用 train_columns 做精确列对齐 ──
-            print(f"[特征补全] 检测到特征缺口：当前 {spectra.shape[1]} 列 "
+            train_cols = metadata.get('train_columns', None)
-                  f"< 模型期望 {expected_features} 列，正在计算 WQI 指数...")
+            if train_cols is not None and len(train_cols) > 0:
-            try:
+                print(f"[Pipeline 列对齐] 训练列数: {len(train_cols)}, 推理当前列数: {spectra.shape[1]}")
-                from src.utils.water_index import WaterQualityIndexCalculator
+                # 构建 推理列名 → 训练列名 的映射
-                calc = WaterQualityIndexCalculator()
+                spectra_cols = [str(c) for c in spectra.columns]
-                formulas = calc.list_available()
+                mapping: Dict[str, str] = {}       # spectra_col_name → train_col_name
-                if formulas:
+                train_set = set(str(tc) for tc in train_cols)
-                    results_df = calc.calculate_many(formulas, spectra, fast=True)
+
-                    if isinstance(results_df, pd.DataFrame) and not results_df.empty:
+                # 第一遍：精确字符串匹配
-                        original_col_count = spectra.shape[1]
+                unmatched_train = []
-                        spectra = pd.concat([spectra, results_df], axis=1)
+                for tc in train_cols:
-                        print(f"[特征补全] 完成！扩充至 {spectra.shape[1]} 列 "
+                    tc_str = str(tc)
-                              f"(+{spectra.shape[1] - original_col_count} WQI)")
+                    if tc_str in spectra_cols:
-            except Exception as e:
+                        mapping[tc_str] = tc_str
-                print(f"[特征补全] 失败: {e}")
+                    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),