Evaluation of Landslide Susceptibility Based on Multi-objective Optimization Method

ZHANG Xingcun; JIANG Yulin; WANG Yujie; QI Zihan; WANG Yunqi

doi:10.13870/j.cnki.stbcxb.2024.01.030

您当前的位置：

首页 >

文章列表页 >

Evaluation of Landslide Susceptibility Based on Multi-objective Optimization Method

更新时间：2025-03-12

- Evaluation of Landslide Susceptibility Based on Multi-objective Optimization Method
- Vol. 38, Issue 1, Pages: 104-112(2024)
- 作者机构：
  
  北京林业大学水土保持学院重庆缙云山三峡库区森林生态系统国家定位观测研究站, 北京林业大学水土保持学院重庆三峡库区森林生态系统教育部野外科学观测研究站,北京,100083
- 作者简介：
- 基金信息：
- DOI：10.13870/j.cnki.stbcxb.2024.01.030
  CLC： P642.22
- Published：2024
- 稿件说明：
移动端阅览
ZHANG Xingcun, JIANG Yulin, WANG Yujie, et al. Evaluation of Landslide Susceptibility Based on Multi-objective Optimization Method[J]. 2024, 38(1): 104-112.
DOI：

ZHANG Xingcun, JIANG Yulin, WANG Yujie, et al. Evaluation of Landslide Susceptibility Based on Multi-objective Optimization Method[J]. 2024, 38(1): 104-112. DOI： 10.13870/j.cnki.stbcxb.2024.01.030.

摘要

[目的] 在滑坡易发性评价中

滑坡预测模型的选取和优化对运算过程的高效性和预测结果的准确性至关重要。针对现有单目标遗传优化算法(genetic algorithm

GA)易陷入早熟、局部搜索能力差、全局优化速度慢等问题

拟提出一种新的优化算法框架

将多目标遗传算法中的经典算法—带精英选择策略的非支配排序算法(the nondominated sorting genetic algorithm with an elite strategy

NSGA-Ⅱ)与常用机器学习模型[随机森林(random forest

RF)、支持向量机(support vector machine

SVM)]相结合

进行滑坡易发性预测。与单目标优化不同的是

NSGA-Ⅱ算法可同时进行特征选择和超参数优化

并使预测模型同时实现最优准确度、召回率、精密度和AUC(area under curve

AUC)。[方法] 以三峡库区重庆段为研究区

从模型精度评价、滑坡灾害易发性分区图、分区统计3个方面对4种优化模型(RF-GA、SVM-GA、RF-NSGA-II、SVM-NSGA-II)进行对比分析。[结果] NSGA-II较GA优化效果更明显

在模型评价和滑坡易发性分区方面

RF-NSGA-II模型具有更高的预测性能

4项评价值分别为80.91%

81.89%

80.07%

88.60%

证明NSGA-II优化算法的有效性;极低至极高危险区面积占比依次为23.06%

22.46%

22.96%

19.99%

11.53%

验证了RF-NSGA-II模型的可靠性。由RF-NSGA-II模型预测得到的易发性图表明

高和极高易发性区集中在研究区北部

且由东向西呈带状分布。[结论] 研究采取的基于多目标选择的RF-NSGA-II模型

为滑坡易发性评价中机器学习模型调优提供新思路。

Abstract

[Objective] In the landslide susceptibility assessment

the selection and optimization of the landslide prediction model are very important to the efficiency of the calculation process and the accuracy of the prediction results. Aiming at the problems that the existing single-objective genetic optimization algorithm (Genetic Algorithm

GA) is prone to premature maturity

poor local search ability

and slow global optimization speed

this paper develops a new optimization algorithm framework

which integrates the classic algorithm in the multi-objective genetic algorithm-Non-dominated sorting method with elite selection strategy (NSGA-II) combined with common machine learning algorithms

random forest (RF)

and support vector machine (SVM) to predict landslide susceptibility. Different from single objective optimization

NSGA-II algorithm can perform feature selection and hyper-parameter optimization simultaneously

and make the prediction model achieve optimal accuracy

recall

precision and AUC (area under curve

AUC) at the same time. [Methods] Taking the Chongqing section of the Three Gorges reservoir area as the study area

the four optimized models (RF-GA

SVM-GA

RF-NSGA-II. and SVM-NSGA-II) were compared and analyzed in three aspects: model accuracy evaluation

landslide hazard susceptibility zoning map

and zoning statistics. [Results] NSGA-II was more effective than GA optimization

and in terms of model evaluation and landslide susceptibility zoning

the RF-NSGA-II model had higher predictive performance

with four evaluation values of 80.91%

81.89%

80.07% and 88.60% respectively

proving the effectiveness of the NSGA-II optimization algorithm; the area share of very low to very high hazard zones were in the order of 23.06%

22.46%

22.96%

19.99%

and 11.53%

which verified the reliability of the RF-NSGA-II model. The susceptibility map predicted by the RF-NSGA-II model showed that the high and extremely high susceptibility areas were concentrated in the north and distributed in bands from east to west. [Conclusion] RF-NSGA-II algorithm based on multi-objective selection provides a new idea for the optimization of machine learning model for landslide risk assessment.

关键词

Keywords

references

陈世发.南方红壤区典型流域土壤侵蚀格局与风险评价[D].福州:福建师范大学,2018. CHEN S F. Evaluation of soil erosion patterns and risk in typical watershed of southern red soil region[D].Fuzhou: Fujian Normal University,2018.

史志华,刘前进,张含玉,等.近十年土壤侵蚀与水土保持研究进展与展望[J].土壤学报,2020,57(5):1117-1127. SHI Z H, LIU Q J, ZHANG H Y, et al. Study on soil erosion and conservation in the past 10 years: Progress and prospects[J].Acta Pedologica Sinica,2020,57(5):1117-1127.

赵楠,李明明,方珂,等.雨强与水土保持措施对西南植烟红壤Cu、Mo和Zn流失的影响[J]. 水土保持学报,2023,37(5):305-311,319. ZHAO N, LI M M, FANG K, et al. Effects of rain intensity and soil and water conservation measures on the loss of Cu, Mo and Zn in tobacco planting red soil in southwest China[J].Journal of Soil and Water Conservation,2023,37(5):305-311,319.

张科利,蔡强国,柯奇画.中国土壤侵蚀研究重大成就及未来关键领域[J].水土保持通报,2022,42(4):373-380. ZHANG K L, CAI Q G, KE Q H. Major achievements and future key fields of soil erosion research in China[J].Bulletin of Soil and Water Conservation,2022,42(4):373-380.

郭思琪,韩磊,赵永华,等.秦岭地区土壤侵蚀时空变化及景观格局[J].生态学杂志,2019,38(7):2167-2176. GUO S Q, HAN L, ZHAO Y H, et al. Spatiotemporal variation and landscape pattern of soil erosion in Qinling Mountains[J].Chinese Journal of Ecology, 2019,38(7):2167-2176.

黄硕文,李健,张欣佳,等.河南省近十年来土壤侵蚀时空变化分析[J].农业资源与环境学报,2021,38(2):232-240. HUANG S W, LI J, ZHANG X J, et al. Analysis of spatial and temporal changes in soil erosion in Henan Province over the last ten years[J].Journal of Agricultural Resources and Environment, 2021,38(2):232-240.

张百平.中国南北过渡带研究的十大科学问题[J].地理科学进展,2019,38(3):305-311. ZHANG B P. Ten major scientific issues concerning the study of China's north-south transitional zone[J].Progress in Geography,2019,38(3):305-311.

刘佳杰. 全球气候变化背景下秦巴山地朱鹮适生区变化研究[D].河南开封:河南大学, 2021. LIU J J. Study on the changes of suitable area of

Crested Ibis

in Qinba Mountain under the background of global climate change[D].Kaifeng, Henan: Henan University,2021.

党广善,刘世生,宋振威.陇南市水土流失变化趋势及原因分析[J].农业科技与信息,2022(14):45-48. DANG G S, LIU S S, SONG Z W. Change trend and cause analysis of soil erosion in Longnan City[J].Agricultural Science-Technology and Information, 2022(14):45-48.

高艳丽,李红波.汉江流域景观格局变化对土壤侵蚀的影响[J].生态学报,2021,41(6):2248-2260. GAO Y L, LI H B. Influence of landscape pattern change on soil erosion in Han River Basin[J]. Acta Ecologica Sinica,2021,41(6):2248-2260.

李艳红. 秦巴山地土壤侵蚀多维变化研究[D].河南开封:河南大学,2020. LI Y H. Study on multidimensional changes of soil erosion in Qinba Mountains[D].Kaifeng, Henan:Henan University,2020.

赵芳,张百平,朱连奇,等.秦巴山地垂直带谱结构的空间分异与暖温带—亚热带界线问题[J].地理学报,2019,74(5):889-901. ZHAO F, ZHANG B P, ZHU L Q, et al. Spectra structures of altitudinal belts and their significance for determining the boundary between warm temperate and subtropical zones in the Qinling-Daba Mountains[J].Acta Geographica Sinica,2019,74(5):889-901.

刘俊杰,潘自武,秦奋,等.基于MODIS的秦巴山地气温估算与山体效应分析[J].地理研究,2020,39(3):735-748. LIU J J, PAN Z W, QIN F, et al. Estimation of air temperature based on MODIS and analysis of mass elevation effect in the Qinling-Daba Mountains[J].Geographical Research, 2020,39(3):735-748.

陈超男,朱连奇,田莉,等.秦巴山区植被覆盖变化及气候因子驱动分析[J].生态学报,2019,39(9):3257-3266. CHEN C N, ZHU L Q, TIAN L, et al. Spatial-temporal changes in vegetation characteristics and climate in the Qinling-Daba Mountains[J].Acta Ecologica Sinica,2019,39(9):3257-3266.

章文波,谢云,刘宝元.利用日雨量计算降雨侵蚀力的方法研究[J].地理科学,2002,22(6):705-711. ZHANG W B, XIE Y, LIU B Y. Rainfall erosivity estimation using daily rainfall amounts[J].Scientia Geographica Sinica,2002,22(6):705-711.

邹玉霞,樊国中,刘淑婧,等.1960—2017年重庆市不同量级降雨侵蚀力R值的时空变化特征[J].水土保持学报,2022,36(6):41-48. ZOU Y X, FAN G Z, LIU S J, et al. Spatio-temporal variations of rainfall erosivity R values of different magnitudes in Chongqing from 1960 to 2017[J].Journal of Soil and Water Conservation,2022,36(6):41-48.

邵祎婷,何毅,穆兴民,等.秦巴山区降雨侵蚀力时空变化特征[J].长江流域资源与环境,2019,28(2):416-425. SHAO Y T, HE Y, MU X M, et al. Spatiotemporal variation of rainfall erosivity in Qin-Ba Mountains region[J].Resources and Environment in the Yangtze Basin, 2019,28(2):416-425.

WILLIAMS J, NEARING M, NICKS A, et al. Using soil erosion models for global change studies[J].Journal of Soil and Water Conservation,1996,51:381-385.

ZHANG H M, WEI J C, YANG Q K, et al. An improved method for calculating slope length (λ) and the LS parameters of the Revised Universal Soil Loss Equation for large watersheds[J].Geoderma,2017,308:36-45.

李天奇.东北黑土区侵蚀沟成因与模型研究[D].北京:中国科学院研究生院,2012. LI T Q, A cause study and module simulation of gully erosion in black soil region[D].Beijing: Chinese Academy of Sciences,2012.

蔡崇法,丁树文,史志华,等.应用USLE模型与地理信息系统IDRISI预测小流域土壤侵蚀量的研究[J].水土保持学报, 2000,14(2):19-24. CAI C F, DING S W, SHI Z H, et al. Study of applying USLE and geographical information system IDRISI to predict soil erosion in small watershed[J].Journal of Soil Water Conservation,2000,14(2):19-24.

水利部.土壤侵蚀分类分级标准:SL 190-2007[S].北京:中国水利水电出版社,2008. Ministry of Water Resources. Soil erosion classification standard: SL 190-2007[S]Beijing: China Water Resources and Hydropower Press,2008.

黄振华,余健,房莉,等.基于InVEST模型的青弋江流域土壤侵蚀与影响因素研究[J].水土保持学报,2023,37(5):189-197. HUANG Z H, YU J, FANG L, et al. Research on soil erosion and influencing factors in Qingyi River Basin based on InVEST model[J].Journal of Soil and Water Conservation,2023,37(5):189-197.

何莎莎,朱文博,崔耀平,等.基于InVEST模型的太行山淇河流域土壤侵蚀特征研究[J].长江流域资源与环境,2019,28(2):426-439. HE S S, ZHU W B, CUI Y P, et al. Study on soil erosion characteristics of Qihe Watershed in Taihang Mountains based on the InVEST model[J].Resources and Environment in the Yangtze Basin,2019,28(2):426-439.

陕西省水利厅.2020年陕西省水土保持公报[Z].西安:2020. Shaanxi Provincial Department of Water Resources. Shaanxi Provincial soil and water conservation bulletin in 2020[Z]. Xi'an,2020.

汤国安,杨勤科,张勇,等.不同比例尺DEM提取地面坡度的精度研究:以在黄土丘陵沟壑区的试验为例[J].水土保持通报,2001,21(1):53-56. TANG G A, YANG Q K, ZHANG Y, et al. Research on accuracy of slope derived from DEMs of different map scales[J].Bulletin of Soil and Water Conservation,2001,21(1):53-56.

MA X F, ZHAO C Y,ZHU J T. Aggravated risk of soil erosion with global warming: A global meta-analysis[J].Catena,2021,200(1):105-129.

朴世龙,张新平,陈安平,等.极端气候事件对陆地生态系统碳循环的影响[J].中国科学:地球科学,2019,49(9):1321-1334. PIAO S L, ZHANG X P, CHEN A P, et al. Effects of extreme climate events on carbon cycle of terrestrial ecosystem[J].Scientia Sinica (Terrae),2019,49(9):1321-1334.

Views

1042

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Spatiotemporal Variation Characteristics and Driving Factors of Soil Erosion in Ecological Barrier Zone of Three Gorges Reservoir Area

Seasonal Changes of Soil Water Content and Controlling Factors in a Small Watershed in the Water-wind Erosion Crisscross Region of the Loess Plateau

Related Author

HU Ruyuan

YANG Jia

ZHAO Haiping

GOU Mengmeng

LIU Changfu

XIAO Wenfa

XU Lan

WANG Yunqiang

Related Institution

Key Laboratory of Forest Ecology and Environment of National Forestry and Grassland Administration， Ecology and Nature Conservation Institute， Chinese Academy of Forestry

Hubei Zigui Three Gorges Reservoir Area Forest Ecosystem Observation and Research Station， Zigui

School of Ecology and Environment， Central South University of Forestry and Technology

State Key Laboratory of Loess and Quaternary Geology, Institute of Earth Environment, Chinese Academy of Sciences, Xian

University of Chinese Academy of Sciences

⁰