滑坡易发性预测线性致灾因子最佳缓冲距离分析——以江西省瑞金市为例

Optimal Buffer Distance Analysis of Linear Hazard Factors for Landslide Susceptibility Prediction:A Case of Ruijin City in Jiangxi Province

线性致灾因子是滑坡易发性预测的环境要素。线性致灾因子缓冲距离的设置对基于机器学习算法的滑坡易发性预测精度有重要影响。以瑞金市为例,在不同单环缓冲距离下建立滑坡密度与线性致灾因子距离的Pearson相关性模型,获得最相关单环缓冲距离线性致灾因子组合。利用随机森林算法建立滑坡易发性预测模型,对比最相关单环缓冲距离和相同单环缓冲距离线性致灾因子组合的预测精度。研究表明,最相关单环缓冲距离组合的预测精度高于相同单环缓冲距离组合,印证了利用相关性获得线性致灾因子缓冲距离方法的合理性。

The linear hazard factors are the environmental elements for landslide susceptibility prediction.The buffer distance of linear hazard factors has an important influence on the prediction accuracy of landslide susceptibility based on machine learning algorithms.Taking Ruijin city as an example,the Pearson correlation models of landslide density and distance from linear hazard factors under different single belt butter distances were established,and the combination of linear hazard factors with the most relevant single belt butter distance was obtained.The prediction model of landslide susceptibility was established using the Random Forest algorithm,and the prediction accuracy of the combination of linear hazard factors with the most relevant single belt buffer distance was compared with that of the combination of linear hazard factors with the same single belt buffer distance.The results show that the model prediction accuracy of the combination of linear hazard factors with the most relevant single belt buffer distance was higher than that of the combination of linear hazard factors with the same single belt buffer distance,which indicated that the method of obtaining the linear hazard factor buffer distance using correlation analysis was reasonable.