diff --git a/src/core/modeling/modeling_batch.py b/src/core/modeling/modeling_batch.py
index 2079f81..1597033 100644
--- a/src/core/modeling/modeling_batch.py
+++ b/src/core/modeling/modeling_batch.py
@@ -288,11 +288,24 @@ class WaterQualityModelingBatch:
         # 提取所有目标列（从0列到feature_start_index-1列）
         y_dict = {}
         target_columns = data.columns[:feature_start_index]
-        
-        print(f"检测到的目标列: {list(target_columns)}")
-        
+        print(f"检测到的潜在目标列: {list(target_columns)}")
+
+        # 新增：跳过非预测目标的系统保留列
+        ignore_cols = {'ID', 'id', 'Id', 'Longitude', 'Latitude', 'Lon', 'Lat', 'longitude', 'latitude', 'lon', 'lat', 'Station', 'station'}
+
         for col_name in target_columns:
+            # 过滤黑名单列
+            if col_name in ignore_cols:
+                print(f"  跳过目标列 '{col_name}': 属于系统保留列或空间坐标")
+                continue
+
             y_series = data[col_name]
+
+            # 过滤非数值类型列 (避免将纯文本备注等拿去回归)
+            if not pd.api.types.is_numeric_dtype(y_series):
+                print(f"  跳过目标列 '{col_name}': 非数值类型")
+                continue
+
             # 检查是否有非空值
             if not y_series.isna().all():
                 y_dict[col_name] = y_series
diff --git a/src/new/views/step8_view.py b/src/new/views/step8_view.py
index 9f9e5bf..d067c6f 100644
--- a/src/new/views/step8_view.py
+++ b/src/new/views/step8_view.py
@@ -141,10 +141,10 @@ class Step8View(BaseView):
 
         # 输出文件路径
         self.output_path = FileSelectWidget(
-            "输出文件:",
-            "CSV Files (*.csv);;All Files (*.*)",
+            "输出模型目录:",
+            "All Files (*.*)",
         )
-        self.output_path.line_edit.setPlaceholderText("自动生成，或手动指定输出文件路径...")
+        self.output_path.line_edit.setPlaceholderText("自动生成模型存放目录...")
         layout.addWidget(self.output_path)
 
         # 启用步骤
@@ -301,17 +301,11 @@ class Step8View(BaseView):
         step6_training_csv = os.path.join(step6_dir, "training_spectra.csv").replace("\\", "/")
         if not self.training_csv_file.get_path():
             self.training_csv_file.set_path(step6_training_csv)
-        # 自动填输出路径
-        indices_dir = _resolve_subdir(work_dir, "indices")
-        os.makedirs(indices_dir, exist_ok=True)
-        training_csv = self.training_csv_file.get_path()
-        if training_csv:
-            basename = os.path.splitext(os.path.basename(training_csv))[0]
-            output_file = f"{basename}_indices.csv"
-        else:
-            output_file = "training_spectra_indices.csv"
-        output_path = os.path.join(indices_dir, output_file).replace("\\", "/")
-        self.output_path.set_path(output_path)
+
+        # ⬇️ 修复：生成标准的输出目录路径
+        models_dir = _resolve_subdir(work_dir, "8_Modeling")
+        os.makedirs(models_dir, exist_ok=True)
+        self.output_path.set_path(models_dir)
 
     # ------------------------------------------------------------------
     # 执行入口