wzy-warehouse
220 lines
8.0 KiB
YAML
220 lines
8.0 KiB
YAML
# 离散化规则配置
|
||
# 定义所有连续因子的分箱规则
|
||
# 包含暴雨灾害链和地震灾害链的全部因子
|
||
#
|
||
# 2026-06-11: 基于1365个样本（796隐患点+569风险点）的实际数据分布
|
||
# 连续因子采用分位数分箱（等频分箱），分类因子基于实际编码映射
|
||
|
||
# ============================================
|
||
# 暴雨触发层离散化规则（保持气象标准不变）
|
||
# ============================================
|
||
|
||
rain_intensity:
|
||
description: "降雨强度等级"
|
||
unit: "mm/h"
|
||
# 中国气象局降雨等级标准
|
||
bins: [0, 0.2, 5, 15, 30, 70, 140, 99999]
|
||
labels: [no_rain, light, moderate, heavy, storm, downpour, extreme]
|
||
|
||
duration:
|
||
description: "持续时间"
|
||
unit: "h"
|
||
bins: [1, 3, 12, 99999]
|
||
labels: [short, medium, long]
|
||
|
||
accum_rain:
|
||
description: "累计降雨量"
|
||
unit: "mm"
|
||
# 中国气象局降水等级标准
|
||
bins: [0, 10, 25, 50, 100, 99999]
|
||
labels: [trace, light, moderate, heavy, extreme]
|
||
|
||
# ============================================
|
||
# 地震触发层离散化规则
|
||
# ============================================
|
||
|
||
magnitude:
|
||
description: "地震震级"
|
||
unit: "Richter"
|
||
# 基于Keefer (1984) 地震触发地质灾害的震级阈值
|
||
bins: [0, 4.0, 5.0, 6.0, 7.0, 8.0, 10.0]
|
||
labels: [minor, light, moderate, strong, major, great]
|
||
|
||
epicenter_distance:
|
||
description: "震中距"
|
||
unit: "km"
|
||
# 地震地质灾害影响范围（Keefer 1984）
|
||
bins: [0, 30, 100, 300, 99999]
|
||
labels: [very_near, near, moderate, far]
|
||
|
||
seismic_intensity:
|
||
description: "地震烈度"
|
||
unit: "中国烈度表"
|
||
# GB 18306-2015 中国地震动参数区划图
|
||
bins: [0, 5, 7, 9, 12, 99]
|
||
labels: [minor, light, moderate, severe, extreme]
|
||
|
||
# ============================================
|
||
# 环境层离散化规则（暴雨/地震共享）
|
||
# 基于1201个样本的分位数分箱
|
||
# ============================================
|
||
|
||
elevation:
|
||
description: "高程"
|
||
unit: "m"
|
||
# 数据: [354, 1926], 均值789.36±325.64
|
||
# 分位数: [354, 482, 637, 817, 1074, 1926]
|
||
bins: [354, 482, 637, 817, 1074, 1926]
|
||
labels: [very_low, low, medium, high, very_high]
|
||
|
||
slope:
|
||
description: "坡度"
|
||
unit: "度"
|
||
# 数据: [0.0, 47.0], 均值10.46±9.12
|
||
# 分位数: [0.0, 2.0, 6.0, 11.0, 17.0, 47.0]
|
||
bins: [0.0, 2.0, 6.0, 11.0, 17.0, 47.0]
|
||
labels: [very_low, low, medium, high, very_high]
|
||
|
||
aspect:
|
||
description: "坡向"
|
||
unit: "度"
|
||
# 数据: [0.86, 359.12], 均值173.47±104.96, 偏度0.126
|
||
# 分位数: [0.86, 57.39, 135.0, 230.19, 297.83, 359.12]
|
||
bins: [0.86, 57.39, 135.0, 230.19, 297.83, 359.12]
|
||
labels: [flat, north, east, south, west]
|
||
|
||
soil_type:
|
||
description: "土壤分类（中国土壤分类系统）"
|
||
unit: "3位数编码"
|
||
# 中国土壤分类系统25个亚类，本数据库出现8种
|
||
# 编码规则：1xx淋溶土、2xx钙层/均腐土、4xx初育土
|
||
mapping:
|
||
110: brown_soil # 棕壤（淋溶土，秦岭北麓山地）
|
||
120: brown_soil # 暗棕壤（淋溶土，高海拔山地）
|
||
130: yellow_brown # 黄棕壤（淋溶土，暖温带过渡区）
|
||
150: yellow_brown # 黄褐土（淋溶土，黄土塬区）
|
||
210: cinnamon # 褐土（钙层土，黄土塬区主要旱作土壤）
|
||
240: black_lu # 黑垆土（均腐土，古土壤残余）
|
||
410: alluvial # 新积土（初育土，渭河冲积平原）
|
||
420: aeolian # 风沙土（初育土，风积沙质土壤）
|
||
255: unknown # GIS背景值（1个样本）
|
||
default: cinnamon # 褐土占比最大（38.8%），作为默认值
|
||
|
||
lithology:
|
||
description: "岩性（中国地质分类）"
|
||
unit: "分类代码"
|
||
mapping:
|
||
1: acid_rock # 酸性侵入岩（花岗岩等，SiO₂>66%）
|
||
3: basic_rock # 基性侵入岩（辉长岩等，SiO₂ 45-52%）
|
||
4: basic_rock # 基性火山岩（玄武岩等，合并入基性岩）
|
||
5: carbonate # 碳酸盐岩（石灰岩、白云岩）
|
||
10: metamorphic # 变质岩（片麻岩、大理岩）
|
||
11: mixed_clastic # 混合碎屑沉积岩（砂岩+泥岩互层）
|
||
13: terrigenous # 陆源碎屑岩（砂岩、粉砂岩）
|
||
14: unconsolidated # 松散堆积物（黄土、冲洪积）
|
||
255: unknown # 无数据（GIS栅格背景值）
|
||
default: unconsolidated
|
||
|
||
landuse:
|
||
description: "土地利用类型"
|
||
unit: "分类代码"
|
||
mapping:
|
||
1: forest # 林地（GIS栅格编码1）
|
||
2: farmland # 农田（GIS栅格编码2）
|
||
3: urban # 城市（GIS栅格编码3）
|
||
4: water # 水域（GIS栅格编码4）
|
||
5: barren # 裸地（GIS栅格编码5）
|
||
8: farmland # 耕地（GIS栅格编码8，合并入农田）
|
||
default: farmland
|
||
|
||
terrain:
|
||
description: "地形分类（中国地形分类体系）"
|
||
unit: "分类代码"
|
||
mapping:
|
||
1: mountain # 断裂山麓地带（秦岭北麓）
|
||
2: plain # 平坦平原（渭河平原）
|
||
3: deep_valley # 高山深峡谷（秦岭腹地）
|
||
4: hill # 丘陵（黄土塬）
|
||
5: gentle_hill # 低缓丘陵（塬边过渡带）
|
||
6: low_mountain # 低山（骊山等）
|
||
7: flat_plain # 平缓平原（冲积平原）
|
||
255: unknown # 无数据（GIS栅格背景值）
|
||
default: hill
|
||
|
||
impervious:
|
||
description: "不透水率"
|
||
unit: "小数比例（0-1）"
|
||
# 数据: [0.0, 1.0], 均值0.31±0.46
|
||
# 68.9%为0.0（无硬化地表），非零值右偏分布
|
||
# 分箱策略：0单独一类，其余4等分
|
||
bins: [0.0, 0.01, 0.25, 0.50, 0.75, 1.0]
|
||
labels: [none, very_low, low, medium, high]
|
||
|
||
ndvi:
|
||
description: "植被指数"
|
||
unit: "NDVI值（×1000缩放）"
|
||
# 数据: [-1.0, 5336.0], 均值2045.95±689.47
|
||
# 分位数: [-1.0, 1616.2, 1891.0, 2172.0, 2496.0, 5336.0]
|
||
bins: [-1.0, 1616.0, 1891.0, 2172.0, 2496.0, 5336.0]
|
||
labels: [very_low, low, medium, high, very_high]
|
||
|
||
sand_content:
|
||
description: "土壤含沙量"
|
||
unit: "百分比"
|
||
# 数据: [23.0, 255.0], 均值35.14±7.75
|
||
# 255为异常值（缺失值编码），正常范围[23, 52]
|
||
# 分位数(正常值): [23.0, 31.0, 34.0, 35.0, 38.0, 52.0]
|
||
bins: [23.0, 31.0, 34.0, 35.0, 38.0, 255.0]
|
||
labels: [very_low, low, medium, high, very_high]
|
||
|
||
ph:
|
||
description: "土壤PH值"
|
||
unit: "PH值（×10缩放，如71=7.1）"
|
||
# 数据: [60.0, 255.0], 均值71.82±6.91
|
||
# 255为异常值（缺失值编码），正常范围[59, 81]
|
||
# 分位数(正常值): [60.0, 67.0, 71.0, 74.0, 76.0, 81.0]
|
||
bins: [60.0, 67.0, 71.0, 74.0, 76.0, 255.0]
|
||
labels: [very_low, low, medium, high, very_high]
|
||
|
||
soil_moisture:
|
||
description: "土壤湿度"
|
||
unit: "小数比例（0-1）"
|
||
# 数据: [-1.0, 0.28], 均值0.15±0.08, 约10%为-1（缺失值）
|
||
# 正常值范围: [0.0, 0.28]
|
||
# 分位数(正常值): [0.0, 0.12, 0.14, 0.16, 0.19, 0.28]
|
||
# 分箱策略：-1视为缺失/极端干燥，其余4等分
|
||
bins: [-1.0, 0.0, 0.10, 0.14, 0.18, 0.28]
|
||
labels: [very_low, low, medium, high, very_high]
|
||
|
||
organic_carbon:
|
||
description: "有机碳"
|
||
unit: "百分比"
|
||
# 数据: [0.0, 65.0], 均值39.03±19.13
|
||
# 分位数: [0.0, 34.0, 42.0, 48.0, 53.0, 65.0]
|
||
bins: [0.0, 34.0, 42.0, 48.0, 53.0, 65.0]
|
||
labels: [very_low, low, medium, high, very_high]
|
||
|
||
dist_to_river:
|
||
description: "距离河道距离"
|
||
unit: "米"
|
||
# 数据: [12.21, 29968.26], 均值11378.07±6704.59
|
||
# 分位数: [12.21, 5409.3, 9522.82, 12667.75, 16952.46, 29968.26]
|
||
bins: [12.21, 5409.3, 9522.82, 12667.75, 16952.46, 29968.26]
|
||
labels: [very_close, close, moderate, far, very_far]
|
||
|
||
dist_to_fault:
|
||
description: "距离断裂带距离"
|
||
unit: "米"
|
||
# 数据: [1.72, 14685.31], 均值3527.70±3400.55
|
||
# 分位数: [1.72, 515.98, 1451.71, 3577.36, 6545.45, 14685.31]
|
||
bins: [1.72, 515.98, 1451.71, 3577.36, 6545.45, 14685.31]
|
||
labels: [very_close, close, moderate, far, very_far]
|
||
|
||
pipe_density:
|
||
description: "供水管网密度"
|
||
unit: "m/m²"
|
||
# 数据: [0.0, 0.07], 约83.9%为0.0，非零值分位数[0.000438, 0.007136, 0.015399, 0.024523, 0.065431]
|
||
# 分箱策略：0单独一类，其余3等分
|
||
bins: [0.0, 0.001, 0.010, 0.025, 0.065]
|
||
labels: [none, low, medium, high]
|