Testing a soil water erosion predictive model in an artificial grassland-in the hillgully Loess Plateau

Expand
  • College of Forestry,Gansu Agricultural University,Lanzhou 730000,Gansu,China;College of Information Science and Technology,Gansu Agricultural University, Lanzhou 730000,Gansu,China

Received date: 2019-04-10

  Revised date: 2019-09-29

  Online published: 2020-03-25

Supported by

甘肃农业大学学科建设基金(GAUXKJS2018254,GAU-XKJS-2018258);国家自然科学基金项目(31660348);甘肃省重点研发计划(18YF1NA070)资助

Abstract

Erosion caused by soil water is widespread in the hillgully Loess Plateau of central Gansu,China,but it is difficult to observe and predict.The objectives of this study were to establish a predictive model for soil water erosion based on a partial least squares algorithm (PLSR) and long short-term memory (LSTM),and to evaluate the models effectiveness using a back-propagation neural network,a recurrent neural network,and a LSTM neural network.The results were verified with experimental data from a runoff field of artificial grassland in the soil and water conservation experimental stations in Anjiagou,Dingxi City,from 2005 to 2016 (1-12 months).Input factors for the model were monthly precipitation,monthly erosive precipitation,monthly runoff,monthly rainfall intensity,runoff area,slope of runoff field,soil sand content,and clay sand content ,from which the model predicted monthly soil water erosion.The results revealed that the original eight input factors could be reduced to four by the PLSR algorithm in the prediction model,alleviating the requirement of the LSTM neural network model for a large number of samples.Our method improved both the prediction precision and the convergence rate of the soil water erosion model in artificial grassland by combining a PLSR algorithm with a LSTM neural network.The average relative error of our prediction results was less than 4%,and the correlation coefficients were higher for our model than for the three neural network models used for comparison.In addition,iteration times,root mean square error,and mean absolute error were lower than for the other neural network models.We found that slope had a significant effect on soil water erosion,but only when the monthly rainfall was more than 25 mm.Our PLSR-LSTM neural network model could be used to accurately predict soil water erosion in artificial grassland in the hill-gully Loess Plateau of central Gansu,and it could provide a new path toward accurate prediction of soil erosion in this area.

Cite this article

WANG Jun, LI Guang, NIE Zhi-gang, LIU Qiang .

Testing a soil water erosion predictive model in an artificial grassland-in the hillgully Loess Plateau[J]. Arid Land Geography, 2020 , 43(2) : 398 -405 . DOI: 10.12118/j.issn.1000-6060.2020.02.13

References

[1]王权威,唐莉.基于ABCBP的土壤侵蚀量预报模型研究[J].水利发电,2017,43(9):1-4.[WANG Quanwei,TANG Li.Study on soil erosion prediction model based on artificial bee colony algorithm and BP neural network[J].Water Power,2017,43(9):1-4.] [2]卫伟,陈利顶,傅伯杰,等.半干旱黄土丘陵沟壑区降水特征值和下垫面因子影响下的水土流失规律[J].生态学报,2006,26(11):3847-3853.[WEI Wei,CHEN Liding,FU Bojie,et al.Mechanism of soil and water loss under rainfall and earth surface characteristics in a semiarid loess hilly area[J].Acta Ecologica Sinica,2006,26(11):3847-3853.] [3]张兴奇,顾礼彬,张科利,等.坡度对黔西北地区坡面产流产沙的影响[J].水土保持学报,2015,29(4):18-22,72.[ZHANG Xingqi,GU Libin,ZHANG Keli,et al.Impacts of slope gradient on runoff and sediment in northwest Guizhou[J].Journal of Soil and Water Conservation,2015,29(4):18-22,72.] [4]和继军,蔡强国,刘松波.次降雨条件下坡度对坡面产流产沙的影响[J].应用生态学报,2012,23(5):1263-1268.[HE Jijun,CAI Qiangguo,LIU Songbo.Effects of slope gradient on slope runoff and sediment yield under different single rainfall conditions[J].Chinese Journal of Applied Ecology,2012,23(5):1263-1268.] [5]杨春霞,肖培青,甄斌,等.野外不同被覆坡面产流产沙特征[J].水土保持学报,2012,26(4):28-36.[YANG Chunxia,XIAO Peiqing,ZHEN Bin,et al.Characteristics on runoff and sediment yield in field prototype and different coverage slope[J].Journal of Soil and Water Conservation,2012,26(4):28-36.] [6]胡琳,苏静,桑永枝,等.陕西省降雨侵蚀力时空分布特征[J].干旱区地理,2014,37(6):1101-1107.[HU Lin,SU Jing,SANG Yongzhi,et al.Spatial and temporal characteristics of rainfall erosivity in Shaanxi Province[J].Arid Land Geography,2014,37(6): 1101-1107.] [7]王凯,陈璐,马金辉,等.TRMM数据在中国降雨侵蚀力计算中的应用[J].干旱区地理,2015,38(5): 948-959.[WANG Kai,CHEN Lu,MA Jinhui,et al.Calculation of rainfall erosivity in China with TRMM data[J].Arid Land Geography,2015,38(5):948-959.] [8]RENARD K G,FOSTER G R,WEESIES G A,et al.RUSLE:Revised universal soil loss equation[J].Journal of Soil and Water Conservation,1991,46(1):30-33. [9]王略,屈创,赵国栋.基于中国土壤流失方程模型的区域土壤侵蚀定量评价[J].水土保持通报,2018,38(1):122-125.[WANG Lue,QU Chuang,ZHAO Guodong.Quantitative assessment of regional soil erosion based on Chinese soil loss equation model[J].Bulletin of Soil and Water Conservation,2018,38(1):122-125.] [10]LANGK V M,KARLSSON L,LOUTFI A,et al.A review of unsupervised feature learning and deep learning for time-series modeling[J].Pattern Recognition Letters,2014,42(1):11-24. [11]LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-444. [12]范竣翔,李琦,朱亚杰,等.基于RNN的空气污染时空预报模型研究[J].测绘科学,2017,42(7):76-83.[FAN Junxiang,LI Qi,ZHU Yajie,et al.A spatio-temporal prediction framework for air pollution based on deep RNN[J].Science of Surveying and Mapping,2017,42(7):76-83.] [13]王鑫,吴际,刘超,等.基于LSTM循环神经网络的故障时间序列预测[J].北京航空航天大学学报,2018,44(4):772-782.[WANG Xin,WU Ji,LIU Chao,et al.Exploring LSTM based recurrent neural network for failure time series prediction[J].Journal of Beijing University of Aeronautics and Astronautics,2018,44(4):772-782.] [14]李世欣,温建,邵孝侯,等.偏最小二乘法与人工神经网络耦合的小流域产沙模型[J].海河大学学报,2010,38(2):149-152.[LI Shixin,WEN Jian,SHAO Xiaohou,et al.Sediment yield model for small watersheds based on coupling of partial least square regression and artificial neural network[J].Journal of Hohai University,2010,38(2):149-152.] [15]聂敏,刘志辉,刘洋,等.基于PCA和BP神经网络的径流预测[J].中国沙漠,2016,36(4):1144-1151.[NIE Min,LIU Zhihui,LIU Yang,et al.Runoff forecast based on principal component analysis and BP neural network[J].Journal of Desert Research,2016,36(4):1144-1151.] [16]张朋,卜崇峰,杨永胜,等.基于CCA 的坡面尺度生物结皮空间分布[J].生态学报,2015,35(16):5412-5420.[ZHANG Peng,BU Chongfeng,YANG Yongsheng,et al.The slope scale distribution regularity of biological soil crusts based on CCA[J].Acta Ecologica Sinica,2015,35(16):5412-5420.] [17]谢云,刘宝元,章文波.侵蚀性降雨标准研究[J].水土保持学报.2000,12(4):6-11.[XIE Yun,LIU Baoyuan,ZHANG Wenbo.Study on standard of erosive rainfall[J].Journal of Soil and Water Conservation,2000,12(4):6-11.] [18]张东平,孙克勤,潘效军,等.烟气脱硫系统增压风机仿真模型开发及应用[J].环境工程学报,2011,5(9):2082-2086.[ZHANG Dongping,SUN Keqin,PAN Xiaojun,et al.Development and application of boost fan simulation model for flue gas desulfurization system[J].Chinese Journal of Environmental Engineering,2011,5(9):2082-2086.] [19]GREFF K,SRIVASTAVA R K,KOUTNIK J,et al.LSTM:A search space odyssey[J].IEEE Transactions on Neural Networks & Learning Systems,2016,(99):1-11. [20]王旭东,严珂,陆慧娟,等.LSTM的单变量短期家庭电力需求预测[J].中国计量大学学报,2018,29(2):142-147.[WANG Xudong,YAN Ke,LU Huijuan,et al.Shortterm household electricity demand forecast based on LSTM single variable[J].Journal of China University of Metrology,2018,29(2):142-147.] [21]ABUDU S,CUI C L,KING J P,et al.Comparison of performance of statistical models in forecasting monthly streamflow of Kizil River China[J].Water Science and Engineering,2010,3(3):269-281. [22]刘婷,邵景安.基于BP神经网络的三峡库区土壤侵蚀强度模拟[J].自然资源学报,2018,33(4): 669-683.[LIU Ting,SHAO Jing’an.Simulation of soil erosion intensity in the three gorges reservoir area using BP neural network[J].Journal of Natural Resources,2018,33(4): 669-683.]
Outlines

/