Snow avalanche susceptibility mapping from tree-based machine learning approaches in ungauged or poorly-gauged regions
Snow avalanche susceptibility mapping from tree-based machine learning approaches in ungauged or poorly-gauged regions
复制标题
在未测量或测量不良的地区，通过基于树的机器学习方法绘制雪崩敏感性图
DOI：
10.1016/j.catena.2023.106997
复制
发表时间：
2023-02-15
期刊：
影响因子：
6.2
通讯作者：
Wang，Tingting
中科院分区：
文献类型：
--
作者：
Liu，Yang;Chen，Xi;Wang，Tingting
绘制雪崩易感性地图对于灾害管理至关重要，特别是在未测量或测量较差的地区。大多数现有的机器学习方法在多源、异构空间数据需求和过拟合方面存在不足。面对这些不足，本研究开发了四种新的基于树木的机器学习模型（Catboost、LightGBM、RF和XGBoost）来预测雪崩敏感性，并结合遥感图像（如Superview-1、Sentinel-2和校准的增强分辨率被动微波日亮度温度）、气象数据（如WRF模拟）、地形和中国天山有限观测数据的数据支持。在选择、培训和验证过程中有21个致病因素。然后，引入SHAP值来量化全球和局部尺度上雪崩可能性的基于变量的贡献份额。结果表明：(1)4种模型均具有较强的雪崩敏感性评价能力，其中Catboost模型的准确性（0.9249）、TPR（0.9920）、FAR（0.0080）、TNR（0.8904）、PPR（0.8229）、NPR（0.0046）、CSI（0.8175）、HSS（0.8404）优于其他模型；(2) Catboost提供了可靠的易感区图，中、高易感区占54.12%，主要集中在西部和东南部；(3)地形因子（与河流的距离、坡向和相对坡位）和气象因子（降水）对敏感性模拟最有效。以上结果表明，基于树的多源异构空间数据机器学习在无需太多野外观测的情况下获得高质量敏感性图的潜力巨大。这对于地形条件复杂、数据稀疏的地区的雪崩防治具有重要意义。
Mapping avalanche susceptibility is essential for disaster management, especially in ungauged or poorly-gauged regions. Most existing machine-learning methods have a shortfall in multi-source, heterogeneous spatial data requirements and overfitting. Faced with these deficiencies, this study has developed four novel tree-based machine-learning models (Catboost, LightGBM, RF, and XGBoost) to predict avalanche susceptibility, along with the data support of remote sensing images (e.g., Superview-1, Sentinel-2, and Calibrated Enhanced-Resolution Passive Microwave Daily Brightness Temperature), Meteorological data (e.g., WRF simulation), topography, and limited observation in Tianshan Mountains, China. There are 21 causative factors in the selection, training, and validation processes. Then, the SHAP value is introduced to quantify the variable-based share of contribution to the possibility of avalanches on both global and local scales. The results demonstrate the following: (1) All four models are potent in assessing avalanche susceptibility due to similar patterns, with Catboost being the best with its eight indices: Accuracy (0.9249), TPR (0.9920), FAR (0.0080), TNR (0.8904), PPR (0.8229), NPR (0.0046), CSI (0.8175), and HSS (0.8404) superior to others; (2) The Catboost provides a reliable susceptibility map illustrating moderate and high susceptible areas up to 54.12% of the total, mainly concentrated in the west and southeast; (3) Topographic factors (distance to rivers, aspect, and relative slope position) and meteorology (precipitation) are the most effective for susceptibility modeling. The results above indicate the significant potential of tree-based machine-learning with multi-source and heterogeneous spatial data in obtaining high-quality susceptibility maps without too much field observation. It is of great importance for avalanche prevention in regions with complex terrain conditions and sparse data.