基于LSTM模型预测不同水保工程措施条件下土壤侵蚀量——以辽西北地区为例

李明伟

doi:10.13961/j.cnki.stbctb.20230508.010

您当前的位置：

首页 >

文章列表页 >

基于LSTM模型预测不同水保工程措施条件下土壤侵蚀量——以辽西北地区为例

试验研究

- 基于LSTM模型预测不同水保工程措施条件下土壤侵蚀量——以辽西北地区为例
- Estimating Soil Erosion Under Different Soil and Water Conservation Engineering Measures Using LSTM model—A Case Study in Northwest Liaoning Province
- 水土保持通报 2023年43卷第4期页码：162-169
- 作者机构：
  
  中煤科工集团沈阳设计研究院有限公司,辽宁,沈阳,110015
- 作者简介：
- 基金信息：
  
  中煤科工集团沈阳设计研究院有限公司科研基金项目“神东煤炭矿区采煤沉陷区耕地复垦技术研究”(NK002-2021)
- DOI：10.13961/j.cnki.stbctb.20230508.010
  中图分类号： S157.1
- 纸质出版：2023
- 稿件说明：
移动端阅览
李明伟. 基于LSTM模型预测不同水保工程措施条件下土壤侵蚀量——以辽西北地区为例[J]. 水土保持通报, 2023,43(4):162-169.

Li Mingwei. Estimating Soil Erosion Under Different Soil and Water Conservation Engineering Measures Using LSTM model—A Case Study in Northwest Liaoning Province[J]. Bulletin of Soiland Water Conservation, 2023, 43(4): 162-169.
李明伟. 基于LSTM模型预测不同水保工程措施条件下土壤侵蚀量——以辽西北地区为例[J]. 水土保持通报, 2023,43(4):162-169. DOI： 10.13961/j.cnki.stbctb.20230508.010.

Li Mingwei. Estimating Soil Erosion Under Different Soil and Water Conservation Engineering Measures Using LSTM model—A Case Study in Northwest Liaoning Province[J]. Bulletin of Soiland Water Conservation, 2023, 43(4): 162-169. DOI： 10.13961/j.cnki.stbctb.20230508.010.

摘要

[目的

]

准确模拟和预测不同水保工程措施下土壤侵蚀量，为辽西北地区精准预测土壤侵蚀量提供技术和理论依据。[方法

]

基于野外径流小区2011—2021年的监测数据，包括：最大30 min和60 min降雨强度(I

和I

)、降雨历时(T)、降雨量(P)和土壤侵蚀量，建立了长短期记忆神经网络(LSTM)分别对3种工程措施(水平槽、果树台田和梯田)下的土壤侵蚀量进行预测。并将LSTM预测结果与3个经典机器学习模型〔反向传播神经网络(BP)、随机森林(RF)和支持向量机(SVM)〕预测的结果进行对比。[结果

]

①在3种工程措施中，I

，I

，T和P对土壤侵蚀量的影响程度不同，但I

，I

和T对土壤侵蚀量的影响大于P。②利用BP模型预测土壤侵蚀量的相对均方根误差(NRMSE)均大于0.2。③相比于RF和SVM模型，LSTM模型在3种工程措施下(水平槽、果树台和梯田)预测土壤侵蚀量的NRMSE分别降低了约0.04～0.08，0.02～0.08，0.05～0.08。④利用I

和T作为LSTM模型的输入特征预测土壤侵蚀量的精度与使用I

，I

，T和P为输入特征时的预测精度相近。[结论

]

在辽西北地区3种水保工程措施中，利用LSTM模型基于最大30 min雨强和降雨历时对土壤侵蚀量进行预测，取得了较其他传统模型高的预测精度。这说明LSTM模型可在同类地区土壤侵蚀量的精准模拟和确定水土保持措施中推广和应用。

Abstract

[Objective] The soil erosion under different conservation engineering measures was precisely predicted in order to provide a technical and theoretical basis for formulating appropriate conservation measures in Northwest Liaoning Province. [Methods] We used experimental plot data from 2011 to 2021 that included maximum precipitation intensity in 30 and 60 minutes (I30 and I60)

precipitation duration (T)

and precipitation (P) to construct a long short-term memory neural network model (LSTM) to predict soil erosion under three different water-and-soil conservation measures (horizontal trough

fruit tree terrace

terrace). Results from the LSTM model were compared with the results of three classical machine learning models

i.e.

artificial neural networks (BP)

random forest (RF)

and support vector machine (SVM). [Results] ① The impacts of I30

I60

and P on soil erosion were different for the three different conservation conditions

but in general

I30

I60

and T had significant impacted on soil erosion. ② The normal relative mean square error (NRMSE) of the BP model under the three different water-and-soil conservation measures were all greater than 0.2. ③ Compared with the RF and SVM models

the LSTM model decreased NRMSE by 0.04~0.08

0.02~0.08

and 0.05~0.08 under the three different water-and-soil conservation measures

respectively. ④ The LSTM model based on only two input features (I30 and T) had a similar accuracy with the LSTM model based on four input features in predicting soil erosion. [Conclusion] The LSTM model was used to predict the soil erosion amount based on the maximum 30 min rainfall intensity and rainfall duration

and the prediction accuracy was higher than other traditional models. This shows that the LSTM model can be popularized and applied in the accurate simulation of soil erosion and the determination of soil and water conservation measures in similar areas.

关键词

Keywords

references

Zhao Jianlin, Wang Zhengang, Dong Yifan, et al. How soil erosion and runoff are related to land use, topography and annual precipitation: insights from a meta-analysis of erosion plots in China [J]. Science of the Total Environment, 2022,802:149665.

于珊.我国水土流失面积和强度继续保持“双降”[OL].北京:新华社,2022-06-28. http://www. gov. cn/xinwen/2022-06/28/content_5698072. htm.

陈钊柱,蔡卓杰,谢福倩,等.自然降雨对广西赤红壤坡地土壤侵蚀特征的影响[J].水土保持通报,2022,42(3):36-42.

林锦阔,李子君,许海超,等.降雨因子对沂蒙山区不同土地利用方式径流小区产流产沙的影响[J].水土保持通报,2016,36(5):7-12.

肖继兵,孙占祥,蒋春光,等.辽西地区农耕坡地土壤侵蚀影响因素及相关关系[J].水土保持学报,2015,29(5):13-19.

Nguyen K A, Chen W, Lin B S, et al. Comparison of ensemble machine learning methods for soil erosion pin measurements [J]. Isprs International Journal of Geo-Information, 2021,10(1)：42.

Zhang Hua, Lei Jinping, Wang Hao, et al. Study on dynamic changes of soil erosion in the North and South Mountains of Lanzhou [J]. Water, 2022,14(15):2388.

Sahour H, Gholami V, Vazifedan M, et al. Machine learning applications for water-induced soil erosion modeling and mapping [J]. Soil and Tillage Research, 2021,211：105032.

Rahmati O, Tahmasebipour N, Haghizadeh A, et al. Evaluation of different machine learning models for predicting and mapping the susceptibility of gully erosion [J]. Geomorphology, 2021,298：118-137.

Zhang Yonghong, Ge Taotao, Tian Wei, et al. Debris flow susceptibility mapping using machine-learning techniques in Shigatse area, China [J]. Remote Sensing, 2019,11(23)：2801.

Senanayake S, Pradhan B, Alamri A, et al. A new application of deep neural network(LSTM) and RUSLE models in soil erosion prediction [J]. Science of The Total Environment, 2022,845：157220.

Chen Zhijun, Zhu Zhenchuang, Jiang Hao, et al. Estimating daily reference evapotranspiration based on limited meteorological data using deep learning and classical machine learning methods [J]. Journal of Hydrology, 2020,591:125286.

李明伟.辽西地区不同水土保持措施条件下土壤侵蚀量与降雨因子关系研究[J].中国水土保持,2018(8)：29-33.

周志华.机器学习[M].北京：清华大学出版社,2016.

王升,付智勇,陈洪松,等.基于随机森林算法的参考作物蒸发蒸腾量模拟计算[J].农业机械学报,2017,48(3):302-309.

Dinh T V, Nguyen H, Tran X L, et al. Predicting rainfall-induced soil erosion based on a hybridization of adaptive differential evolution and support vector machine classification [J]. Mathematical Problems in Engineering, 2021, 2021:1-20.

冯禹,崔宁博,龚道枝,等.利用温度资料和广义回归神经网络模拟参考作物蒸散量[J].农业工程学报,2016,32(10):81-89.

Alhassan A M, Zainon W M N W. Brain tumor classification in magnetic resonance image using Hardswish-based RELU activation function-convolutional neural network [J]. Neural Computing and Applications, 2021,33(15):9075-9087.

张焕,张庆,于纪言.激活函数的发展综述及其性质分析[J].西华大学学报(自然科学版),2021,40(4):1-10.

刘定一,沈阳阳,詹天明,等.融合微博热点分析和LSTM模型的网络舆情预测方法[J].江苏大学学报(自然科学版),2021,42(5):546-553.

刘洁,陈晓宏,许振成,等.降雨变化对东江流域径流的影响模拟分析[J].地理科学,2015,35(4):483-490.

Zha Wenshu, Liu Yuping, Wan Yujin, et al. Forecasting monthly gas field production based on the CNN-LSTM model [J]. Energy, 2022,260:124889.

任雨之,郑江坤,付滟,等.不同耕种模式下降雨等级对紫色土坡耕地产流产沙的影响[J].中国水土保持科学,2020,18(3):90-98.

Feng Ziyi, Huang Guanhua, Chi Daocai. Classification of the complex agricultural planting structure with a semi-supervised extreme learning machine framework[J]. Remote Sensing, 2020,12(22):3708.

陈英义,程倩倩,方晓敏,等.主成分分析和长短时记忆神经网络预测水产养殖水体溶解氧[J].农业工程学报,2018,34(17):183-191.

浏览量

584

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

川中丘陵区小流域土壤侵蚀空间分异评价研究

黄土高原向阳沟流域水土保持措施效益分析

基于DEM的废弃矿山小流域地形特征分析

基于集对分析模型的水土保持工程效益后评价研究

2000—2023年吉林省黑土核心保护区撂荒耕地遥感监测及水土保持效应