李益敏, 向倩英, 邓选伦,等.基于优化MaxEnt模型的怒江州滑坡易发性评价[J].河南理工大学学报（自然科学版）,doi:10.16186/j.cnki.1673-9787.2023070010

LI Y M, XIANG Q Y, DENG X L, et al.Evaluation of landslide susceptibility in Nujiang prefecture based on optimized MaxEnt model[J].Journal of Henan Polytechnic University(Natural Science) ,doi:10.16186/j.cnki.1673-9787.2023070010

基于优化MaxEnt模型的怒江州滑坡易发性评价(网络首发)

李益敏1,2, 向倩英3, 邓选伦1, 冯显杰3

1.云南大学 地球科学学院，云南 昆明  650500;2.云南大学 云南省高校国产高分卫星遥感地质工程研究中心，云南 昆明  650500;3.云南 大学 国际河流与生态安全研究院，云南 昆明  650500

摘要: 目的 怒江州是典型的高山峡谷地区，地质灾害（滑坡）频发，严重制约着当地的发展，为解决这一问题，方法 综合考虑怒江州实际情况，从气象水文、地形地貌、地层岩性、植被生态和人类活动 5 个方面选取坡向、高程等 14 个影响因子判断相关性，构建评价指标体系，对最大熵（MaxEnt）模型的特征类（feature combination，FC）和正则化乘数（regularization multiplier，RM）参数进行优化，对比优化前后小样本赤池信息量准则（akaike information criterion，AICc）、遗漏率（omission rate，OR）和 AUC（area under curve）值，然后基于优化的最大熵（MaxEnt）模型预测滑坡灾害的发生，实现怒江州滑坡易发性评价。结果 结果表明：优化后的 MaxEnt 模型在研究区滑坡易发性预测中适用性优秀（AUC=0.913）；运用刀切法（Jackknife）计算各影响因子对易发性的影响程度，高程（S3，23.2%）、坡度（S9，22.4%）、居民点密度（S5，14.2%）、距河流距离（S13，13.7%）、距道路距离（S4，9.6%）和岩性（S7，8.7%）是位列前六的因子，累计贡献度达 91.8%；极高、高、中、低滑坡易发性等级的空间占比分别为 4.88%，8.96%，18.40%，67.76%，县域中极高和高易发区占比最大的是泸水市，整体上，极高、高易发区主要沿河流和道路分布于峡谷中，低易发区主要分布于人类活动少、河谷不发育的区域。结论 优化后的 MaxEnt 模型更适合怒江州滑坡易发性预测，研究结果可为怒江州防灾减灾与土地利用规划提供参考。

关键词:怒江州;最大熵（MaxEnt）模型;滑坡;易发性

中图分类号：O224;P642.22

doi:10.16186/j.cnki.1673-9787.2023070010

基金项目: 国家自然科学基金资助项目（41161070）； 云南省科技厅-云南大学联合基金重点资助项目（2019FY003017）； 云南大学大湄公河次区域气候变化研究省创新团队项目（2019HC027）； 中国地质调查局项目（DD20221824）

收稿日期:2023-07-06

修回日期:2023-09-14

网络首发日期: 2024-01-02

Evaluation of landslide susceptibility in Nujiang prefecture based on optimized MaxEnt model（Online）

LI Yimin1,2, XIANG Qianying3, DENG Xuanlun1, FENG Xianjie3

1.School of Earth Sciences，Yunnan University，Kunming  650500，Yunnan，China;2.Yunnan University Engineering Research Center of High-resolution Satellite Remote Sensing，Yunnan University，Kunming  650500，Yunnan，China;3.Institute of International Rivers and Ecological Security，Yunnan University，Kunming  650500，Yunnan，China

Abstract:Nujiang Prefecture is a typical alpine valley region with frequent geological disasters, which seriously restricts the local development. Therefore, it is urgent to carry out research on the prediction of landslide disaster susceptibility and the main influencing factors in this region. In this paper, 14 influencing factors such as meteorology, hydrology, landform and vegetation ecology in Nujiang Prefecture were comprehensively considered, and the occurrence of landslide disaster was predicted based on the optimized MaxEnt model to realize the evaluation of landslide susceptibility in Nujiang Prefecture. The results show that: The optimized MaxEnt has excellent applicability in predicting landslide susceptibility in the study area (AUC=0.913). The Jackknife method was used to calculate the influence of various influencing factors on landslide susceptibility, such as elevation (S3, 23.2%), slope (S9, 22.4%), settlement density (S5, 14.2%), distance from river (S13, 13.7%), distance from road (S4, 9.6%) and lithology (S7, 8.7%) were the top six factors, with a cumulative contribution of 91.8%. The spatial distribution proportions of four landslide susceptibility levels from high to low are 4.88%, 8.96%, 18.40% and 67.76%, respectively. Lushui City is the county with the largest proportion of extremely high and high susceptibility areas.In the overall spatial pattern, the extremely high and highly prone areas are mainly distributed in canyons along with rivers and roads, while the low prone areas are mainly distributed in the areas with little human activities and undeveloped valleys. Based on the evaluation results of landslide susceptibility in Nujiang Prefecture, this paper can provide scientific basis for disaster prevention and reduction and land use planning in this region.

Key words:Nujiang State;maximum entropy（MaxEnt） model;landslide;susceptibility

CLC：O224;P642.22