不同栅格尺寸下输电线路地质灾害易发性评价

Evaluation of geological disaster susceptibility of transmission lines under different grid resolutions

输电线路的安全运行对国家经济建设与发展具有重要意义,而针对输电线路进行地质灾害易发性评价的研究较少。以京津冀地区的输电线路为例,选取高程、坡度、坡向、地形起伏度、地层岩性、距断层距离、距水系距离、土地利用类型8个指标因子,采用频率比法对各指标因子进行分级,构建易发性评价体系。再利用不同的机器学习模型,使用不同尺寸的栅格单元作为评价单元对研究区进行易发性评价。最后,选取精度最高的机器学习模型与传统的层次分析法完成研究区易发性区划图。研究结果表明:贝叶斯网络模型在区域输电线路易发性评价中的应用效果最好,模型性能最强,最高AUC值为0.876。与传统的层次分析法相比,BN模型在研究区易发性制图中的效果更好,精度更高。此外,采用50 m的栅格作为评价单元在研究区易发性评价中取得了最好的应用效果,研究成果为输电线路地质灾害易发性评价以及栅格尺寸的选用提供了思路以及参考。

[Objective]The safe operation of transmission lines is of great significance for national economic construction and development,but there were few studies on the evaluation of geological hazards susceptibility to transmission lines.[Methods]This study focuses on the Beijing-Tianjin-Hebei region as an example,where eight index factors,including elevation,slope,aspect,terrain relief,stratigraphic lithology,distance from fault,distance from water system,and land use type were selected.The frequency ratio method was used to classify each index factor to construct a susceptibility evaluation system.Then used different machine learning models and grid of different spatial resolutions as evaluation units to evaluate the susceptibility of the study area.Finally,the machine learning model with the highest accuracy and the traditional Analytic Hierarchy Process(AHP)were selected to complete the susceptibility zoning map of the study area.[Results]The research results show that the Bayesian Network model(Bayesian Network,BN)had the best application effect and the strongest model performance in the susceptibility evaluation of regional transmission lines,and the maximum AUC value was 0.876.The BN model outperformed the traditional AHP model,displaying superior precision in susceptibility mapping in the study area.[Conclusion]In addition,emplpying 50 m grid as the evaluation unit had achieved the best application effect in the evaluation of transmission line geological disaster susceptibility,which provided ideas and references for transmission line geological disaster evaluation and grid resolution selection.