基于机器学习的紫色土坡面水沙预测模型研究
作者:
基金项目:

国家自然科学基金项目(U2040208、52009104)和陕西省水利科技计划项目(2022slkj-04)资助


Research on Water and Sand Prediction Model of Purple Soil Slope Based on Machine Learning
Author:
Fund Project:

Supported by the National Natural Science Foundation of China (Nos.U2040208, 52009104); Shaanxi Provincial Water Conservancy Science and Technology Project (No.2022slkj-04)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [33]
  • |
  • 相似文献
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    为了精准预测土壤侵蚀变化、科学合理地预防水土流失的发生,为紫土坡地水土流失防治提供参考,基于典型紫土径流小区43场降雨资料,降雨量、历时和I30为特征指标,采用K-means聚类算法对降雨分类;使用随机森林(Randomforest,RF)算法评估各影响因子对径流深(H)、土壤流失量(S)的重要性,结合通径分析法进行重要因子筛选;将筛选所得关键因子作为模型输入变量,H、S为输出,使用BP神经网络构建预测模型。结果表明:(1)划分出3种雨型,B雨型(短历时、大雨强、小雨量)是主要降雨类型,A雨型(长历时、中雨强、大雨量)最剧烈。(2)各雨型下特征因子对H、S的重要程度明显不同。A雨型下T对S重要程度最高(31%),各因素对H的重要程度相对均匀;B雨型下各因素对S的影响差异小,F对H的重要程度最高(29%)。在C雨型下,Pr对H、S的重要程度最高(33%、36%)。(3)三种雨型下的H、S均受到Pr的显著影响,B、C雨型下的H、S分别同时受F和Vs、Ph的影响显著。(4)利用BP神经网络对H、S的预测精度均较高,Nash-Suttclife效率系数均高于0.95,且对H的预测模型精确度高于对S的预测模型。

    Abstract:

    Purple soil is one of the unique soils in China. Because of its low degree of soil development and poor soil erosion resistance, soil erosion in the purple soil area is very serious, which seriously hinders local agriculture and economic development. 【Objective】 To accurately predict soil erosion changes, we need to scientifically and rationally prevent the occurrence of soil erosion, provide a reference for the prevention and control of soil erosion on purple soil slopes, and promote research on soil and water conservation in purple soil areas. 【Method】 Based on the rainfall data of 43 typical purple soil run-off communities, rainfall, duration and I30 are used as characteristic indicators, and the K-means clustering algorithm was used to classify rainfall; the Random forest (RF) algorithm was used to evaluate the importance of each influencing factor on the depth of run-off (H) and soil loss (S), and the important factor screening was carried out in combination with the path analysis method. The key factors obtained from the screening were used as the input variables of the model, with H and S as the outputs. Also, a predictive model was constructed using BP neural network. 【Result】 The results showed that:(1) The erosive rainfall in the purple mound area in the southwest can be divided into three categories. Among them, the A rain type had a long duration, medium rain intensity, heavy rain volume, the lowest frequency of occurrence, and the greatest erosion, which was an important rain type that caused slope erosion in the area; the B rain type had a short duration, heavy rain, and light rain volume, and the most frequent occurrence, which was the main rain type that caused slope erosion in the area; and the C rain type, which had a medium duration, medium rain intensity, and medium rainfall, which occurred more frequently and also made a greater contribution to slope erosion in the area. (2) The importance of characteristic factors to H and S under each rain type was significantly different. For rain type A, the rain duration (T) was the most important to S (31%), and the importance of each factor to H was relatively uniform. Under rain type B, the influence of each factor on S was small, and the rainfall erosion force (F) was the most important to H (29%). Also, the degree of importance was the highest (29%). Under the rain type C, rainfall (Pr) was the most important to H and S(33%, 36%). (3) The H and S under the three rain types were significantly affected by Pr and the H and S under the B and C rain types were most significantly affected by F, vegetation cover (Vs), and average plant height (Ph) at the same time. (4) The prediction accuracy of H and S using the BP neural network was high, the efficiency coefficient of Nash-Suttclife is higher than 0.95, and the accuracy of the prediction model for H was higher than that of the prediction model for S. 【Conclusion】 Research on the purple soil mound area in the southwest needs to focus on preventing soil erosion caused by high-frequency heavy rainfall. In this study, the two models that used rainfall and other factors to calculate H and S had high forecasting capabilities, which provide technical support for soil erosion prediction to achieve accurate forecasting of soil erosion.

    参考文献
    [1] He X B, Bao Y H, Nan H W, et al. Tillage pedogenesis of purple soils in southwestern China[J]. Journal of Mountain Science, 2009, 6(2):205-210.
    [2] Zhao X J, Liu D H. Soil management and soil and water conservation of dry farming in the purple hilly area of Sichuan;2002 Academic Annual Conference of China Association for Science and Technology, Chengdu, Sichuan, China, F, 2002[C].赵燮京, 刘定辉. 四川紫色丘陵区旱作农业的土壤管理与水土保持[C]//加入WTO和中国科技与可持续发展——挑战与机遇、责任和对策(下册). 成都, 2002:83-84.
    [3] Liu L, Zheng F L. Summary of the research on purple soil erosion[J]. Journal of Anhui Agricultural Sciences, 2006, 34(12):2804-2805. [刘力, 郑粉莉. 紫色土土壤侵蚀研究进展[J]. 安徽农业科学, 2006, 34(12):2804-2805.]
    [4] Zhu B, Wang T, Kuang F H, et al. Measurements of nitrate leaching from a hillslope cropland in the central Sichuan Basin, China[J]. Soil Science Society of America Journal, 2009, 73(4):1419-1426.
    [5] Wang Z. Study on influencing factors of erosion and sediment yield[J]. China Science and Technology Information, 2008(6):27-29, 31. [王政. 侵蚀产沙的影响因素研究[J]. 中国科技信息, 2008(6):27-29, 31.]
    [6] Gao M R, Liu G C, Zhu B. Study on process of runoff in different three tillage systems in hilly area, Sichuan Province[J]. Journal of Soil Water Conservation, 2000, 14(S1):118-121. [高美荣, 刘刚才, 朱波. 四川紫色土丘陵区不同耕作制的产流过程初步分析[J]. 水土保持学报, 2000, 14(S1):118-121.]
    [7] Ma X, Zheng J K, Wang W W, et al. Characteristics of the runoff and sediment yield of sloping farmland in the purple soil area under different rainfall patterns[J]. Journal of Soil and Water Conservation, 2017, 31(2):17-21. [马星, 郑江坤, 王文武, 等. 不同雨型下紫色土区坡耕地产流产沙特征[J]. 水土保持学报, 2017, 31(2):17-21.]
    [8] Sun L L, Cha X, Huang S Y, et al. Effects of different rainfall intensity on the slope erosion process in purple soil[J]. Journal of Soil and Water Conservation, 2018, 32(5):18-23. [孙丽丽, 査轩, 黄少燕, 等. 不同降雨强度对紫色土坡面侵蚀过程的影响[J]. 水土保持学报, 2018, 32(5):18-23.]
    [9] Wang Y K, Wang Y Q, Fu B, et al. A study on the process simulation of soil erosion by rainfall on the purple soil slopes[J]. Journal of Mountain Science, 2006, 24(5):597-600. [王玉宽, 王勇强, 傅斌, 等. 紫色土坡面降雨侵蚀试验研究[J]. 山地学报, 2006, 24(5):597-600.]
    [10] Huo Y M, Bi H X, Zhu Y J, et al. Erosion process and its affecting factors of southern typical clay slope under simulated rainfall condition[J]. Journal of Soil and Water Conservation, 2015, 29(4):23-26, 84. [霍云梅, 毕华兴, 朱永杰, 等. 模拟降雨条件下南方典型粘土坡面土壤侵蚀过程及其影响因素[J]. 水土保持学报, 2015, 29(4):23-26, 84.]
    [11] Liu D, She D, Yu S E, et al.. Rainfall intensity and slope gradient effects on sediment losses and splash from a saline-sodic soil under coastal reclamation[J]. Catena, 2015, 128:54-62.
    [12] Wang X T, Wang Y K, Fu B, et al. Experimental study on runoff characteristics of slope land in Sichuan Basin[J]. Journal of Soil and Water Conservation, 2006, 20(5):9-11, 19. [王先拓, 王玉宽, 傅斌, 等. 川中丘陵区紫色土坡耕地产流特征试验研究[J]. 水土保持学报, 2006, 20(5):9-11, 19.]
    [13] Zhang B, Jiang G Y, Chen Z F, et al. Factors of soil erodibility of purplish soil in hilly region[J]. Acta Pedologica Sinica, 2010, 47(2):354-358. [张兵, 蒋光毅, 陈正发, 等. 紫色丘陵区土壤可蚀性因子研究[J]. 土壤学报, 2010, 47(2):354-358.]
    [14] Liu J G, Zhang X C, Li L, et al. Research of effect of vegetation coverage on soil and water loss in purple soil slope land[J]. Research of Soil and Water Conservation, 2015, 22(3):16-20, 27. [刘纪根, 张昕川, 李力, 等. 紫色土坡面植被覆盖度对水土流失影响研究[J]. 水土保持研究, 2015, 22(3):16-20, 27.]
    [15] Mondal A, Murthy K R, Ghosh A, et al. Robust image segmentation using global and local fuzzy energy based active contour[C]//2016 IEEE International Conference on Fuzzy Systems(FUZZ-IEEE). Vancouver, BC, Canada. IEEE, 2016:1341-1348.
    [16] Qian S Y, Liu H H, Li D Y. Research and application of improved K-means algorithm in text clustering[J]. DEStech Transactions on Computer Science and Engineering, 2018, 47(11):161-166.
    [17] Rodriguez-Galiano V, Mendes M P, Garcia-Soldado M J, et al. Predictive modeling of groundwater nitrate pollution using Random Forest and multisource variables related to intrinsic and specific vulnerability:A case study in an agricultural setting(Southern Spain) [J]. Science of the Total Environment, 2014, 476/477:189-206.
    [18] Anne, Puissant,. Object-oriented mapping of urban trees using Random Forest classifiers[J]. International Journal of Applied Earth Observation and Geoinformation, 2014, 26:235-245.
    [19] Marakhimov, Avazjon. Convergence analysis of feedforward neural networks with backpropagation[J]. Bulletin of National University of Uzbekistan(Mathematics and Natural Sciences), 2019, 2(2):1-1.
    [20] Nash J E, Sutcliffe J V. River flow forecasting through conceptual models part I-A discussion of principles[J]. Journal of Hydrology, 1970, 10(3):282-290.
    [21] Wischmeier W H, Smith D D. Rainfall energy and its relationship to soil loss[J]. Transactions, American Geophysical Union, 1958, 39(2):285.
    [22] Dudoit S, Fridlyand J. A prediction-based resampling method for estimating the number of clusters in a dataset[J]. Genome Biology, 2002, 3(7):1-21.
    [23] dos Santos J C N, de Andrade E M, Medeiros P H A, et al. Effect of rainfall characteristics on runoff and water erosion for different land uses in a tropical semiarid region[J]. Water Resources Management, 2017, 31(1):173-185.
    [24] Zhu Q, Guo J X, Guo X, et al. Research on influencing factors of soil erosion based on random forest algorithm-A case study in upper reaches of Ganjiang River Basin[J]. Bulletin of Soil and Water Conservation, 2020, 40(2):59-68. [朱青, 国佳欣, 郭熙, 等. 基于随机森林算法的土壤侵蚀影响因子研究——以赣江上游流域为例[J]. 水土保持通报, 2020, 40(2):59-68.]
    [25] Ma B, Li Z B, Ma F, et al. Effects of maize plants on the redistribution of water under simulated rainfall conditions[J]. Acta Ecologica Sinica, 2015, 35(2):497-507. [马波, 李占斌, 马璠, 等. 模拟降雨条件下玉米植株对降雨再分配过程的影响[J]. 生态学报, 2015, 35(2):497-507.]
    [26] Zhang J Y, Wang J H, Cheng X F, et al. Effects of rainfall on slope runoff and sediment yield under different crop measures in the Jiangzi River minor watershed[J]. Journal of Soil and Water Conservation, 2021, 35(2):8-14. [张嘉懿, 汪军红, 程先富, 等. 降雨对江子河小流域不同农作物措施坡面产流产沙的影响[J]. 水土保持学报, 2021, 35(2):8-14.]
    [27] Xiang Y G, Zhang D, Chen F, et al. Effect of rainfall and slope on runoff and sediment production of tobacco slope farmland[J]. Southwest China Journal of Agricultural Sciences, 2021, 34(5):1121-1127. [向宇国, 张丹, 陈凡, 等. 降雨和坡度对植烟坡耕地产流产沙的影响[J]. 西南农业学报, 2021, 34(5):1121-1127.]
    [28] Foster G R, Lombardi F, Moldenhauer W C. Evaluation of rainfall-runoff erosivity factors for individual storms[J]. Transactions of the ASAE, 1982, 25(1):124-129.
    [29] Ma H. Application of WEPP in soil and water loss in a small purple soil watershed in central SiChuan[D]. Beijing:Beijing Forestry University, 2010. [马浩. WEPP模型在川中紫色土区小流域水土流失中的应用[D]. 北京:北京林业大学, 2010.]
    [30] Yan D C, Wen A B, Zhang Z Q, et al. Using study of sloping WEPP model in Sichuan hilly basin[J]. Journal of Soil and Water Conservation, 2007, 21(5):42-45, 63. [严冬春, 文安邦, 张忠启, 等. 坡面版WEPP模型在川中丘陵区的应用研究[J]. 水土保持学报, 2007, 21(5):42-45, 63.]
    [31] Zhao J T, Ma Y X, Shi Y, et al. Prediction of soil erosion evolution in counties in the loess hilly region based on ANN-CA model[J]. Science of Soil and Water Conservation, 2021, 19(6):60-68.
    [32] Yu G Q, Li Z B, Lu K X, et al. Piecewise prediction model for erosion and sediment yielding of individual rainfall events in small watershed on loess plateau[J]. Acta Pedologica Sinica, 2010, 47(4):604-610. [于国强, 李占斌, 鲁克新, 等. 黄土高原小流域次降雨侵蚀产沙分段预报模型研究[J]. 土壤学报, 2010, 47(4):604-610.]
    [33] Jia Y Y, Zheng F L, Yang Q K. Distributed water erosion prediction model for small watershed in Loess Plateau[J]. Journal of Hydraulic Engineering, 2005, 36(3):328-332. [贾媛媛, 郑粉莉, 杨勤科. 黄土高原小流域分布式水蚀预报模型[J]. 水利学报, 2005, 36(3):328-332.]
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

陈琦涛,王添,李占斌,张皎,李鹏,李斌斌.基于机器学习的紫色土坡面水沙预测模型研究[J].土壤学报,2024,61(2):424-433. DOI:10.11766/trxb202207020361 CHEN Qitao, WANG Tian, LI Zhanbing, ZHANG Jiao, LI Peng, Li Binbin. Research on Water and Sand Prediction Model of Purple Soil Slope Based on Machine Learning[J]. Acta Pedologica Sinica,2024,61(2):424-433.

复制
分享
文章指标
  • 点击次数:245
  • 下载次数: 1331
  • HTML阅读次数: 745
  • 引用次数: 0
历史
  • 收稿日期:2022-06-22
  • 最后修改日期:2023-02-15
  • 录用日期:2023-06-15
  • 在线发布日期: 2023-07-17
  • 出版日期: 2024-03-15
文章二维码