基于集成学习和考虑滑坡负样本的滑坡易发性评价

打开文本图片集

关键词：滑坡易发性；集成学习；信息量法；滑坡负样本；黄河上游中图分类号：TP181;P642.22;TV882.1 文献标志码：A doi：10.3969/j.issn.1000-1379.2025.07.019引用格式：，，，等.基于集成学习和考虑滑坡负样本的滑坡易发性评价[J].人民黄河，2025，47（7）：116-123

Landslide Susceptibility Evaluation Based on Integrated Learning and Considering Landslide Negative Samples

ENG Yuanxun1， ZHOU Kangkang1，HU Shaowei1， ZHANG Haichao²，YU Guoqing³， XU Lukai 3 ，PENG Hao² （1.College of Water Conservancy and Transportation， Zhengzhou University，Zhengzhou 45ooo1，China; 2.Power China Guiyang Engineering Corporation Limited， Guiyang 55O081， China; 3.Yellow River Institute of Hydraulic Research，YRCC，Zhengzhou 45OOO3，China）

Abstract：TevaluatioflndslidesuseptibitisofgeatgficanforgioaldisasterpreventionditigatioIviefei suesthatesinglecaifeintelandslidesuseptibilityvaluatiousingmacinlangalgodporpresn，dleo ofnegativesamplesoflanslidesaselatielybirarylndslidsuscetilityeaationoelaspropod，hchombdl tionmethodofnegativesamplesoflandslidesbasedonteinformationquantymetodwithmachineleaingintegrationalgorithms.Taking thesectionfromLijaxiatoGongboxiainteuppereachsoftheYllowRiverasthestudyaea3evaluationfactorssuchaselevation， slopegradientndpreipitaoneresecedasthevalatofctorsforlndslidurceresetionetdsfrgieples flandslides，namelyuferzon，lowslopeadientandifoatioquantityereadoptedBylingtheladslidesuscebilityevuationmodelsoftheasficationndessontree（AR）andeeitegatedlngrits（Bagng，oosting，ndadofor est），theperfomaeofteeuatiooelsunderdientintegatedeaingagritsanddintselectionetdsfotie plesoflandslideswasaalyzd.Thsultssowtatteintegatedleaigalgoritcasignificantlyimprovetepeformanceofthesingle baseclssifierandteiprovemenefetofteBoostingalgoiisteostpromientTeselectionmetodofegatiesamplebased onthe informationquantitytakesmostoftheevaluationfactorsintofullconsideration，andthereliabilityofthemodelishigher.

Keywords：landslidesusceptibility；integratedlearning；informationvaluemethod；landslidenegativesamples；upperreachesofthe Yellow River

0 引言

黄河上游李家峡至公伯峡区间地质结构复杂、昼夜温差大、生态环境脆弱、河流下切作用强烈，众多因素导致该区域地质灾害发生频繁[1]，防治形势严峻。（剩余10835字）