李清清,黄海峰,张瑞,易武,周红,邓志勇,董志鸿,柳青,易庆林

• 1:三峡大学湖北长江三峡滑坡国家野外科学观测研究站
• 2:三峡大学三峡库区地质灾害教育部重点实验室
• 3:三峡大学湖北省水电工程智能视觉监测重点实验室
• 4:宜昌市地质环境监测站

摘要(Abstract)：

【目的】第四系土体是土质滑坡的主要物源，其分布及厚度是开展土质滑坡隐患识别的重要基础。随着机器学习技术的兴起，图像分类技术与人工智能算法结合已成为遥感识别的主流。【方法】以三峡库首秭归向斜盆地为研究区，以Landsat-8影像为基础数据源，以区内现有土质滑坡数据构建样本，采用机器学习软件EnMAP-Box,建立第四系厚度及空间分布信息的随机森林分类模型，筛选出用于识别第四系土体厚度的最优特征子集，得出第四系相对厚度空间分布。【结果】结果表明：Landsat-8遥感影像的光谱特征、主成分、植被指数、湿度、坡度、绿度、均值等与第四系厚度具有强相关性，可作为识别第四系土体厚度的重要特征因子；随机森林模型能有效识别第四系土体厚度信息，且对岩质区提取精度较高；经实地调查验证，模型性能均衡，预测结果合理，可用于多植被中低山区环境的第四系识别。【结论】研究成果可为土质滑坡隐患识别和风险防控提供重要数据支撑。

关键词(KeyWords)： 第四系土体;滑坡;相对厚度;机器学习;空间信息提取;三峡库首

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金(U21A2031,42007237,42107489);; 三峡库区地质灾害教育部重点实验室开放基金(2020KDZ09);; 水电工程智能视觉监测湖北省重点实验室开放基金(2020SDSJ02)

作者(Author): 李清清,黄海峰,张瑞,易武,周红,邓志勇,董志鸿,柳青,易庆林

DOI: 10.13928/j.cnki.wrahe.2024.05.014

参考文献(References)：

• [1] 殷跃平.地质灾害风险调查评价方法与应用实践[J].中国地质灾害与防治学报，2022,33(4):5-6.YIN Yueping.Geological hazard risk investigation and evaluation method and application practice [J].The Chinese Journal of Geological Hazard and Control,202,33(4):5-6.
• [2] FUSCO F,MIRUS B B,BAUM R L,et al.Incorporating the effects of complex soil layering and thickness local variability into distributed landslide susceptibility assessments[J].Water,2021,13(5):713.
• [3] 陈佳，董世勇.重庆市三峡水库消落区管理现状与优化研究[J].水利发展研究，2022,22(2):77-82.CHEN Jia,DONG Shiyong.Research on the current situation and optimization of management in the Three Gorges Reservoir water consumption area in Chongqing [J].Water Resources Development Research,2022,22 (2):77-82.
• [4] 刘晓磊，赵志峰，周玉明，等.滨海地基土层的空间插值分析[J].工程地质报，2018,26(3):794-801.LIU Xiaolei,ZHAO Zhifeng,ZHOU Yuming,et al.Spatial interpolation analysis of coastal foundation soil [J].Journal of Engineering Geology,2018,26( 3):794801.
• [5] 王桂林，向林川，孙帆.粒子群优化协同克里金法在确定山地斜坡土层厚度中的应用 [J].土木建筑与环境工程，2018,40(6):60-66.WANG Guilin,XIANG Linchuan,SUN Fan.Application of cooperative Kriging method based on particle swar moptimization in estimation slope soil thickness [J].Journal of Civil,Architectural &.Environmental Engineering 2018,40(6):60-66.
• [6] XU L,HEROLD M,TSENDBAZAR N E,et al.Time series analysis for global land cover change monitoring:A comparison across sensors[J].Remote Sensing of Environment,2022,271:112905.
• [7] SHAFIQUE M,VAN DER MEIJDE M,ULLAH S.Regolith modeling and its relation to earthquake induced building damage:A remote sensing approach[J].Journal of Asian Earth Sciences,2011,42(1-2):65-75.
• [8] BASHARAT M,QASIM M,SHAFIQUE M,et al.Regolith thickness modeling using a GIS approach for landslide distribution analysis,NW Himalayas[J].Journal of Mountain Science,2018,15(11):2466-2479.
• [9] 宋盛渊，王清，潘玉珍，等.基于突变理论的滑坡危险性评价[J].岩土力学，2014,35(S2):422-428.SONG Shengyuan,WANG Qing,PAN Yuzhen,et al.Evaluation of landslide susceptibility degree based on catastrophe theory [J].Rock and Soil Mechanics,2014,35(S2):422-428.
• [10] FLORINSKY I V,EILERS R G,MANNING G R,et al.Prediction of soil properties by digital terrain modelling[J].Environmental Modelling & Software,2002,17(3):295-311.
• [11] 张瀚，桂蕾，王腾飞，等.基于BP神经网络的第四系覆盖物厚度预测及三维地质建模[J/OL].地球科学，2022.https://kns.cnki.net/KXReader/Detail?invoice=oMkvcwFilMRfk1QU%2BuuMQyy9LTGMPeCzv93vI7PDXd3nJVCdVCsg%2Bbkks45 GANdbypcfNME58G24%2BHSf6s8uPb%2FL1UlxjTJfZ7tIU282Bmm3YL5 E1%2F8vtwttYSYk9b1xYW1ihA2XFj1uBaqyVeqF8s3JqkYMZx1dG H5gXBJKKNg%3D&DBCODE=CAPJ&FileName=DQKX2022052 500D&TABLEName=capjlast&nonce=F38F2A9E33FE46 D59A2815 F94B238BE9&TIMESTAMP=1706512526284&uid=.ZHANG Han,GUI Lei,WANG Tengfei,et al.Prediction of Quaternary cover thickness and 3d geological modeling based on bp neural network [J/OL].Earth Sciences,2022.https://kns.cnki.net/KXReader/Detail?invoice=oMkvcwFilMRfk1QU%2BuuMQyy9LTG MPeCzv93vI7PDXd3nJVCdVCsg%2Bbkks45GANdbypcfNME58G 24%2BHSf6s8uPb%2FL1UlxjTJfZ7tIU282Bmm3YL5E1%2F8vtw ttYSYk9b1xYW1ihA2XFj1uBaqyVeqF8s3JqkYMZx1dGH5gXBJKKNg %3D&DBCODE=CAPJ&FileName=DQKX2022052500D&TABL EName=capjlast&nonce=F38F2A9E33FE46D59A2815F94B238BE9 &TIMESTAMP=1706512526284&uid=.
• [12] BUI E N,MORAN C J.A strategy to fill gaps in soil survey over large spatial extents:An example from the Murray-Darling basin of Australia[J].Geoderma,2003,111(1-2):21-44.
• [13] 叶润青，李士垚，牛瑞卿.面向地质灾害防治的第四系空间信息提取研究[J].安全与环境工程，2020,27(1):39-46.YE Runqing,LI Shiyao,NIU Ruiqing.Research on Quaternary spatial information extraction for prevention and control of geological hazards [J].Safety and Environmental Engineering,20,27(1):39-46.
• [14] 刘磊，殷坤龙，张俊.三峡库区万州主城区第四系堆积层厚度的估算方法及应用[J].地质科技情报，2016,35 (1):177-183.LIU Lei,YIN Kunlong,ZHANG Jun.Estimation method of the Quaternary deposits thickness and its application in Wanzhou Central District,Three Gorges Reservoir Region [J].Geological Science and Technology Information,2016,35(1):177-183.
• [15] JOHNSON D L,DOMIER J E J,JOHNSON D N.Animating the biodynamics of soil thickness using process vector analysis:a dynamic denudation approach to soil formation[J].Geomorphology,2005,67(1-2):23-46.
• [16] 柴波，殷坤龙.三峡库区巴东新城区库岸三叠系巴东组层间软弱带[J].工程地质报，2009,17(6):809-816.CHAI Bo,YIN Kunlong.Interlayer weak zone of the Triassic Badong Formation on the reservoir bank of Badong New City,Three Gorges Reservoir Area[J].Journal of Engineering Geology,2009,17(6):809-816.
• [17] 岑越，刘振平，刘建，等.奉节新铺滑坡裂缝位移与降雨天数相关性研究[J].水利水电技术(中英文),2022,53(2):133-141.CEN Yue,LIU Zhenping,LIU Jian,et al.Study on correlation between fracture displacement and rainfall days in Xinpu landslide in Fengjie [J].Water Resources and Hydropower Technology,2022,53(2):133-141.
• [18] VERIKAS A,GELZINIS A,BACAUSKIENE M.Mining data with random forests:A survey and results of new tests[J].Pattern recognition,2011,44(2):330-349.
• [19] WASKE B,VAN DER LINDEN S,OLDENBURG C,et al.ImageRF-A user-oriented implementation for remote sensing image analysis with Random Forests[J].Environmental Modelling & Software,2012,35:192-193.
• [20] 张开放，苏华友，窦勇.一种基于混淆矩阵的多分类任务准确率评估新方法[J].计算机工程与科学，2021,43(11):1910-1919.ZHANG Kaifang SU Huayou,DOU Yong.A new multi-classification task accuracy evaluation method basedon confusion matrix[J].Computer Engineering and Science,2021,43(11):1910-1919.
• [21] MACHIDON A L,DEL FRATE F,PICCHIANI M,et al.Geometrical approximated principal component analysis for hyperspectral image analysis[J].Remote Sensing,2020,12(11):1698.
• [22] 朱德军，李浩博，王晓明.GNSS 遥感技术在智慧水利建设中的应用展望[J].水利水电技术(中英文),2022,53(10):33-57.ZHU Dejun,LI Haobo,WANG Xiaoming.Application prospects of GNSS remote sensing technique in the development of smart water conservancy[J].Water Resources and Hydropower Engineering,2022,53(10):33-57.
• [23] 梁永荣，高军，严琳.基于 ZigBee Mesh 网络和 NB-IoT 城市地下空间传输系统的研究[J] .水利水电技术(中英文),2022,53 (8):71-77.LIANG Yongrong,GAO Jun,YAN Lin.Research of urban underground space transmission system based on ZigBee Mesh network and NB-IoT[J].Water Resources and Hydropower Engineering,2022,53(8):71-77.
• [24] 李博伦，遆超普，颜晓元.Landsat 8陆地成像仪影像的缨帽变换推导[J].测绘科学，2016,41(4):102-107.LI Bolun,TI Chaopu,YAN Xiaoyuan.Study of derivation of tasseled cap transformation for I andsat 8 OLI images [J].Science of Surveying and Mapping,2016,41(4):102-107.
• [25] 田庆久，闵祥军.植被指数研究进展[J].地球科学进展，1998(4):10-16.TIAN Qingjiu,MIN Xiangjun.Research progress of vegetation index [J].Advance in Earth Science,1998(4):10-16.
• [26] 何志远，钟九生，代仁丽.基于机器学习的综合干旱监测建模及在西南地区应用[J].水利水电技术(中英文),2022,53(2):43-51.HE Zhiyuan,ZHONG Jiusheng,DAI Renli.Integrated drought monitoring modeling based on machine learning and its application in Southwest China [J].Water Resources and Hydropower Technology,202,53(2):43-51.
• [27] VAN DER LINDEN S,RABE A,HELD M,et al.The EnMAP-Box:A toolbox and application programming interface for EnMAP data processing[J].Remote Sensing,2015,7(9):11249-11266.
• [28] SUESS S,VAN DER LINDEN S,OKUJENI A,et al.Using class probabilities to map gradual transitions in shrub vegetation from simulated EnMAP data[J].Remote Sensing,2015,7(8):10668-10688.