基于SMOTE策略的數(shù)據(jù)不完整時滑坡易發(fā)性評價

打開文本圖片集

關(guān)鍵詞：滑坡易發(fā)性；不完整滑坡數(shù)據(jù);隨機(jī)森林；神經(jīng)網(wǎng)絡(luò)；合成少數(shù)過采樣;黃河上游中圖分類號：TV62;TV882.1 文獻(xiàn)標(biāo)志碼：A doi：10.3969/j.issn.1000-1379.2025.07.009引用格式：，，，等.基于 SMOTE策略的數(shù)據(jù)不完整時滑坡易發(fā)性評價[J].人民黃河，2025，47（7）：50-58.

Landslide Susceptibility Assessment Using SMOTE Strategy Under Incomplete Data Conditions

MENG Jinhao’，SUN Benbo1，WANG Juan1，HUANG Chengfang1.2 （1. School of Water Conservancy and Transportation， Zhengzhou University， Zhengzhou 45ooo1，China; 2. School of Architecture，Zhengzhou University，Zhengzhou 450oo1，China）

Abstract：Thesstfslidetiliipoasiseolalserredool，utlepe dataareofenmissngocomplete，makingitdifultfocelearingmodelstocoductauateandreliablesusptibitoeling. Basedonrandomforest（RF）andartficialneuralnetwork（AN）odels，tispperdisusedteaccuracyhangesoflandslidesuseptibility assessment results and susceptibility zoning characteristics under diferent missing ratios （ 10%-50% ） and regional missing conditions. Afterexpandingthesamplebyusingthesynthticminortyoversamplingtechique（SMOTE），tepredictionresultswerecomparedandanalyzedtoverifyteectivenessofsmpleexpansion.Theesultsshowthatwithteincreaseoftheproportionofmisingsamples，eodel accuracygradualldecrease，utthedcreaseilimitedTepredictedareasofteRFandANNmodelsintehgh-riskareasabovethe higher level are reduced by up to 7.0% and 5.5% respectively. Under regional missing conditions，the accuracy of the evaluation results varies greatly，and the maximum predicted area of high-level prone areas is reduced by 11.1% and 11.2% respectively. After expanding the sample，the accuracy of the evaluation results decreases slightly with the increase of the supplement ratio. When 50% of the samples are supplemented，the predicted areas of the high-risk areas of the two models are reduced by 14.0% and 19.5% respectively. Generating landslide samplesasedonthe SMOTEtrategycanprovideanefectivemethodforlandslidesusceptibilityevaluationmodelinginareas withising landslide data.

Key words：landslidesusceptibilt；incompleteladslidedata；randomforest；neuralnetwork；sytheticminorityoversampling；uppe Yellow River

0 引言

黃河流域地質(zhì)運(yùn)動活躍、地貌演化迅速、氣候區(qū)域差異顯著，導(dǎo)致流域重大災(zāi)害類型多樣[1]、分布廣且突發(fā)性強(qiáng)，威脅黃河流域生態(tài)環(huán)境與地質(zhì)安全[2]。（剩余11425字）