ISSN 1003-8035 CN 11-2852/P
  • 中国科技核心期刊
  • CSCD收录期刊
  • Caj-cd规范获奖期刊
欢迎扫码关注“i环境微平台”

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

滑坡多发区第四系堆积层厚度智能预测与影响因素分析

孟佳佳 吴益平 柯超 苗发盛

孟佳佳,吴益平,柯超,等. 滑坡多发区第四系堆积层厚度智能预测与影响因素分析−以重庆万州铁峰乡为例[J]. 中国地质灾害与防治学报,2023,34(2): 1-10 doi: 10.16031/j.cnki.issn.1003-8035.202202008
引用本文: 孟佳佳,吴益平,柯超,等. 滑坡多发区第四系堆积层厚度智能预测与影响因素分析−以重庆万州铁峰乡为例[J]. 中国地质灾害与防治学报,2023,34(2): 1-10 doi: 10.16031/j.cnki.issn.1003-8035.202202008
MENG Jiajia,WU Yiping,KE Chao,et al. Intelligent prediction and analysis of influencing factors of Quaternary accumulation layer thickness in landslide-prone areas: A case study in the Tiefeng area of Wanzhou District, Chongqing City[J]. The Chinese Journal of Geological Hazard and Control,2023,34(2): 1-10 doi: 10.16031/j.cnki.issn.1003-8035.202202008
Citation: MENG Jiajia,WU Yiping,KE Chao,et al. Intelligent prediction and analysis of influencing factors of Quaternary accumulation layer thickness in landslide-prone areas: A case study in the Tiefeng area of Wanzhou District, Chongqing City[J]. The Chinese Journal of Geological Hazard and Control,2023,34(2): 1-10 doi: 10.16031/j.cnki.issn.1003-8035.202202008

滑坡多发区第四系堆积层厚度智能预测与影响因素分析

doi: 10.16031/j.cnki.issn.1003-8035.202202008
基金项目: 国家自然科学基金项目(41977244;42007267)
详细信息
    作者简介:

    孟佳佳(1999-),女,河南开封人,硕士研究生,主要从事地质灾害预测预报研究。E-mail:jjm@cug.edu.cn

    通讯作者:

    吴益平(1971-),女,浙江杭州人,教授,博士生导师,从事地质灾害预测预报与风险评价研究。E-mail:ypwu@cug.edu.cn

  • 中图分类号: P642.22

Intelligent prediction and analysis of influencing factors of Quaternary accumulation layer thickness in landslide-prone areas: A case study in the Tiefeng area of Wanzhou District, Chongqing City

  • 摘要: 堆积层厚度是区域工程地质调查的基础数据,对识别滑坡具有重要意义,在滑坡的稳定性评价和风险评估中发挥着重要的作用。传统的空间插值方法对外界因素考虑不足,难以满足精度要求。文章以三峡库区万州区铁峰乡为研究对象,在实地调查的基础上,总结提出了堆积层的成因模式,并据此添加区域堆积层厚度控制点;基于Apriori算法挖掘影响因子与堆积层厚度分布之间的关联准则,利用已知样本点采用三种机器学习方法建立模型,最后将模型应用于整个区域得到堆积层厚度分布图,并对结果进行对比分析。结果表明:选取的13种影响因子中6种因子与堆积层厚度表现出较强的相关性;数据挖掘显示坡度和地形起伏是影响堆积层厚度空间分布差异的主要因素。3种机器学习模型中GWO-SVM模型的预测结果与实际最为吻合。研究结果揭示了区域第四系堆积层的成因机制,为机器学习技术在堆积层厚度预测领域奠定了基础。
  • 图  1  Apriori算法示意图

    Figure  1.  Schematic diagram of Apriori algorithm

    图  2  万州区位置及铁峰乡滑坡分布图

    Figure  2.  Location of Wanzhou District and distribution of landslides in Tiefeng Township

    图  3  残坡积示意图

    Figure  3.  Schematic diagram of residual slope

    图  4  顺向坡远程滑动堆积示意图

    Figure  4.  Schematic diagram of long-distance sliding accumulation along the slope

    图  5  顺向坡近距离滑动堆积示意图

    Figure  5.  Schematic diagram of close range sliding accumulation along the slope

    图  6  顺向坡侧向崩塌堆积示意图

    Figure  6.  Schematic diagram of lateral collapse and accumulation along the slope

    图  7  软弱相间岩层分布模式示意图

    Figure  7.  Schematic diagram of the distribution mode of soft and weak alternating rock formation

    图  8  各因子统计图

    Figure  8.  Statistical chart of each factor

    图  9  各模型测试结果对比(测试样本)

    Figure  9.  Comparison of test results of each model (test samples)

    图  10  各模型的区域堆积层厚度预测结果

    Figure  10.  Prediction results of regional accumulation layer thickness of each model

    表  1  各因子与堆积层厚度相关性指标

    Table  1.   Correlation index between each factor and accumulation layer thickness

    因子GRAMIC
    因子1坡度0.69230.6977
    因子2坡向0.68780.5285
    因子3流向0.86730.4696
    因子4高程0.70500.0752
    因子5汇水条件0.63490.0417
    因子6地形起伏0.68560.6933
    因子7地层0.75460.0486
    因子8距水系距离0.63660.0525
    因子9距陡崖距离0.60630.0637
    因子10剖面曲率0.69530.2141
    因子11平面曲率0.67830.0784
    因子12斜坡结构0.63640.3271
    因子13植被覆盖0.64400.0943
    下载: 导出CSV

    表  2  各因子属性指标

    Table  2.   Attribute indicators of each factor

    因子属性类别
    因子1坡度0~20°F11
    20°~40°F12
    >40°F13
    因子2坡向337.5°~67.5°F21
    67.5°~157.5°F22
    157.5°~247.5°F23
    247.5°~337.5°F24
    因子3流向1&2F31
    4&8F32
    16&32F33
    64&128F34
    因子6地形起伏0~2F61
    2~4F62
    >4F63
    因子10剖面曲率0~20F101
    20~40F102
    40~60F103
    >60F104
    因子12斜坡结构顺向坡F121
    逆向坡F122
    斜交坡F123
    下载: 导出CSV

    表  3  堆积层厚度关联准则

    Table  3.   Association criterion of accumulation layer thickness

    规则 ID规则支持度/% 置信度/%
    1YZ3=F31 & YZ6=F62 & YZ2=F21$\Rightarrow $HD50.08100.00
    2YZ3=F31 & YZ2=F21 & YZ1=F12$\Rightarrow $HD50.08100.00
    3YZ2=F22 & YZ3=F34 & YZ1=F11$\Rightarrow $HD30.08100.00
    4YZ2=F22 & YZ3=F34 & YZ6=F61$\Rightarrow $HD30.08100.00
    5YZ3=F34 & YZ1=F12 & YZ2=F24$\Rightarrow $HD20.17100.00
    6YZ2=F23 & YZ10=F102 & YZ1=F11$\Rightarrow $HD20.08100.00
    7YZ10=F102 & YZ2=F22 & YZ1=F11$\Rightarrow $HD20.08100.00
    8YZ3=F31 & YZ6=F63$\Rightarrow $HD118.58100.00
    9YZ3=F31 & YZ1=F13 & YZ6=F63$\Rightarrow $HD117.18100.00
    10YZ2=F22 & YZ1=F13 & YZ6=F63$\Rightarrow $HD117.01100.00
    下载: 导出CSV

    表  4  各模型预测精度对比

    Table  4.   Comparison of prediction accuracy of each model

    预测模型MSERMSEQC平均厚度/m
    PSO-SVM401.221.420.470.791.49
    GA-SVM198.571.000.230.761.76
    GWO-SVM152.240.870.190.831.83
    下载: 导出CSV
  • [1] 王强,吴炳方,朱亮. 土壤厚度研究进展[J]. 安徽农业科学,2012,40(9):5273 − 5277. [WANG Qiang,WU Bingfang,ZHU Liang. Review of soil depth[J]. Journal of Anhui Agricultural Sciences,2012,40(9):5273 − 5277. (in Chinese with English abstract) doi: 10.3969/j.issn.0517-6611.2012.09.071
    [2] 李岩,尚士友,阿拉塔其其格,等. 典型草原栗钙土层厚度空间插值方法研究[J]. 中国农机化学报,2015,36(1):344 − 348. [LI Yan,SHANG Shiyou,A Lataqiqige,et al. Research of spatial interpolation methods of typical grassland chestnut soil thickness[J]. Journal of Chinese Agricultural Mechanization,2015,36(1):344 − 348. (in Chinese with English abstract) doi: 10.13733/j.jcam.issn.2095-5553.2015.01.090
    [3] 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 swarm optimization in estimation slope soil thickness[J]. Journal of Civil,Architectural & Environmental Engineering,2018,40(6):60 − 66. (in Chinese with English abstract)
    [4] SCARPONE C,SCHMIDT M G,BULMER C E,et al. Modelling soil thickness in the critical zone for Southern British Columbia[J]. Geoderma,2016,282:59 − 69. doi: 10.1016/j.geoderma.2016.07.012
    [5] PRADHAN A M S,KIM Y T. Development and evaluation of relative relief based soil thickness model:A comparative study in hilly terrain,south Korea[J]. KSCE Journal of Civil Engineering,2021,25(6):2186 − 2198. doi: 10.1007/s12205-021-1379-9
    [6] LI X C,LUO J H,JIN X L,et al. Improving soil thickness estimations based on multiple environmental variables with stacking ensemble methods[J]. Remote Sensing,2020,12(21):3609. doi: 10.3390/rs12213609
    [7] 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. (in Chinese with English abstract)
    [8] 段贵娟,李飒,孙立强,等. 基于水平相关距离的土层厚度区域评价方法研究[J]. 水力发电学报,2021,40(2):177 − 186. [DUAN Guijuan,LI Sa,SUN Liqiang,et al. Study of soil thickness regional evaluation using horizontal scales of fluctuation[J]. Journal of Hydroelectric Engineering,2021,40(2):177 − 186. (in Chinese with English abstract) doi: 10.11660/slfdxb.20210218
    [9] 邵晨灿,向喜琼. 基于成因分类的土层厚度空间分布研究[J]. 中国水运(下半月),2021,21(3):115 − 117. [SHAO Chencan,XIANG Xiqiong. Study on spatial distribution of soil thickness based on genetic classification[J]. China Water Transport,2021,21(3):115 − 117. (in Chinese)
    [10] WANG Q,WU B F,STEIN A,et al. Soil depth spatial prediction by fuzzy soil-landscape model[J]. Journal of Soils and Sediments,2018,18(3):1041 − 1051. doi: 10.1007/s11368-017-1779-0
    [11] AKUMU C E,WOODS M,JOHNSON J A,et al. GIS-fuzzy logic technique in modeling soil depth classes:Using parts of the Clay Belt and Hornepayne region in Ontario,Canada as a case study[J]. Geoderma,2016,283:78 − 87. doi: 10.1016/j.geoderma.2016.07.028
    [12] CHENG W,ZHU A X,QIN C Z,et al. Updating conventional soil maps by mining soil-environment relationships from individual soil polygons[J]. Journal of Integrative Agriculture,2019,18(2):265 − 278. doi: 10.1016/S2095-3119(18)61938-0
    [13] AGRAWAL R, IMIELIŃSKI T, SWAMI A. Mining association rules between sets of items in large databases[C]//Proceedings of the 1993 ACM SIGMOD international conference on Management of data. Washington, D. C. , USA. New York: ACM, 1993: 207-216.
    [14] VAPNIK V N. The nature of statistical learning theory[M]. New York: Springer , 2000.
  • 加载中
图(10) / 表(4)
计量
  • 文章访问数:  290
  • HTML全文浏览量:  445
  • PDF下载量:  87
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-02-10
  • 修回日期:  2022-04-07
  • 网络出版日期:  2023-04-11
  • 刊出日期:  2023-04-25

目录

    /

    返回文章
    返回