[1]王彤彤,翟军海,何欢,等.BP神经网络和SVM模型对施加生物炭土壤水分预测的适用性[J].水土保持研究,2017,24(03):86-91.
　WANG Tongtong,ZHAI Junhai,HE Huan,et al.Applicability of BP Neural Network Model and SVM Model to Predicting Soil Moisture Under incorporation of Biochar into Soils[J].Research of Soil and Water Conservation,2017,24(03):86-91.
点击复制

BP神经网络和SVM模型对施加生物炭土壤水分预测的适用性

《水土保持研究》[ISSN:1005-3409/CN:61-1272/P] 卷: 24 期数: 2017年03期 页码: 86-91 栏目: 出版日期: 2017-06-28
Title:
Applicability of BP Neural Network Model and SVM Model to Predicting Soil Moisture Under incorporation of Biochar into Soils
作者:
王彤彤1, 翟军海3, 何欢4, 郑纪勇1,2, 涂川5
1. 西北农林科技大学 资源环境学院, 陕西 杨凌 712100;
2. 中国科学院 水利部 水土保持研究所 黄土高原土壤侵蚀与旱地农业国家重点实验室, 陕西 杨凌 712100;
3. 陕西省农业厅, 西安 710003;
4. 西北农林科技大学 理学院, 陕西 杨凌 712100
Author(s):
WANG Tongtong1, ZHAI Junhai3, HE Huan4, ZHENG Jiyong1,2, TU Chuan5
1. College of Natural Resources and Environment, Northwest A & F University, Yangling, Shaanxi 712100, China;
2. State Key Laboratory of Soil Erosion and Dryland Farming on the Loess Plateau, Institute of Soil and Water Conservation, CAS & MWR, Yangling, Shaanxi 712100, China;
3. Agriculture Department of Shaanxi Province, Xi’an 710003, China;
4. College of Science, Northwest A & F University, Yangling, Shaanxi 712100, China
关键词:
土壤水分; 生物炭; 模型预测; SVM模型; BP神经网络
Keywords:
soil moisture; biochar; prediction model; SVM model; BP neural network model
分类号:
S152.7
摘要:
生物炭作为土壤改良剂对半干旱区土壤水分有良好的吸持作用，为确定施加生物炭对土壤水分预测模型适用性的影响，依托黄土高原半干旱区固原生态站开展了小区定位试验。向土壤中施加不同种类及比例的生物炭，定期监测土壤水分含量；考虑土壤含水量的非线性特征以及生物炭对土壤水分的影响，选取BP神经网络和SVM支持向量机两种模型，建立施加生物炭土壤水分预测模型。计算预测值，并与实测值对比，分析相对误差；利用RMSE、MRE、MAE和R2评估BP神经网络和SVM模型的精度。结果表明；BP神经网络预测值的平均相对误差为3.78%，最大误差为13.14%；SVM模型的平均相对误差为0.56%，最大误差为2.42%。SVM模型的RMSE、MRE、MAE值（分别为0.34~0.17，0.07，0.56~1.27）均小于BP神经网络的（分别为1.04~1.16，0.47~0.68，3.78~4.57），且决定系数R2值SVM模型（0.96~0.99）大于BP神经网络（0.56~0.64）。BP神经网络和SVM模型均能很好地预测施加生物炭的土壤水分，但SVM模型预测结果更加稳定，精度较高，更适于施加生物炭土壤水分的预测。该研究可为半干旱地区生物炭还田土壤水分的预测及管理提供理论依据。
Abstract:
As a soil amendment, biochar has a good effect on the soil moisture in the semi-arid area. In order to know the effect of adding biochar on soil water content prediction model, a district positioning experiment was carried out in semi-arid Guyuan ecology research station on the Loess Plateau. In the experiment, different kinds and amounts of biochar were added to soil and the soil water contents were monitored regularly. In consideration of soil water nonlinear characteristic and random effect of adding biochar, BP Neural Network model and SVM (Support Vector Machine) model were selected to build water content prediction model for biochar-added soil and the applicability of the two models were finally evaluated according to the measured data and predicted data by using RMSE, MRE, MAE and R2 to assess the precision. The results showed that the average relative error value of BP Neural Network model was 3.78% and the max relative error value was 13.14%, while the average relative error value of SVM model was 0.56% and the max relative error value was 2.42%, respectively. The RMSE, MRE, MAE value of SVM model(0.34~0.17, 0.07 and 0.56~1.27, respectively) were less than BP Neural Network model(1.04~1.16, 0.47~0.68 and 3.78~4.57 respectively), and the R2 value of SVM model (0.96~0.99) were greater than BP Neural Network model(0.56~0.64), respectively. BP Neural Network model and SVM model both performed well in predicting soil water content and the prediction results of SVM model were more steady and precise. So the SVM model is the appropriate model to predict water content in biochar-added soil. The reuslt can provide theoretical evidence for prediction and management of moisture in the biochar-added soil in the semi-arid area.

参考文献/References:

[1] 傅伯杰,杨志坚,王仰麟,等.黄土丘陵坡地土壤水分空间分布数学模型[J].中国科学:D辑,2001,31(3):185-191.
[2] 白天路,杨勤科,申佳.黄土高原丘陵沟壑小流域土壤水分垂直分布变异特征及影响因子[J].生态学杂志,2009(12):2508-2514.
[3] 刘志鹏,邵明安.黄土高原小流域土壤水分及全氮的垂直变异[J].农业工程学报,2010,26(5):71-77.
[4] 李光,应杰,刘长荣.土壤水分预测模型的研究[J].南水北调与水利科技,2010,8(4):95-98.
[5] 刘洪斌,武伟,魏朝富,等.土壤水分预测神经网络模型和时间序列模型比较研究[J].农业工程学报,2003,19(4):33-36.
[6] Downer C W, Ogden F L. Prediction of runoff and soil moistures at the watershed scale:Effects of model complexity and parameter assignment[J]. Water Resources Research, 2003,39(3):276-290.
[7] 陈天华,唐海涛.基于ARM和GPRS的远程土壤墒情监测预报系统[J].农业工程学报,2012,28(3):162-166.
[8] 许秀英,衣淑娟,黄操军.土壤含水量预报现状综述[J].农机化研究,2013,35(7):11-15.
[9] 尹健康,陈昌华,邢小军,等.基于BP神经网络的烟田土壤水分预测[J].电子科技大学学报,2010,39(6):891-895.
[10] 张强,黄生志,陈晓宏.基于支持向量机的土壤湿度模拟及预测研究[J].土壤学报,2013,50(001):59-67.
[11] Marris E. Putting the carbon back:Black is the new green[J]. Nature,2006,442(7103):624-626.
[12] Shrestha G, Traina S J, Swanston C W. Black carbon’s properties and role in the environment:a comprehensive review[J]. Sustainability, 2010,2(1):294-320.
[13] Ahmad M, Rajapaksha A U, Lim J E, et al. Biochar as a sorbent for contaminant management in soil and water:A review[J]. Chemosphere, 2014,99(3):19-33.
[14] 陈温福,张伟明,孟军.生物炭与农业环境研究回顾与展望[J].农业环境科学学报,2014,33(5):821-828.
[15] 王丹丹,郑纪勇,颜永毫,等.生物炭对宁南山区土壤持水性能影响的定位研究[J].水土保持学报,2013,27(2):101-104.
[16] Karhu K, Mattila T, Bergström I, et al. Biochar addition to agricultural soil increased CH4 uptake and water holding capacity:Results from a short-term pilot field study[J]. Agriculture, Ecosystems & Environment, 2011,140(1):309-313.
[17] Basso A S, Miguez F E, Laird D A, et al. Assessing potential of biochar for increasing water-holding capacity of sandy soils[J]. Gcb Bioenergy, 2013, 5(2):132-143.
[18] 王彤彤,张剑,涂川,等.IPSO-BP神经网络在渭河天水段水质评价中的应用[J].环境科学与技术,2013,36(8):175-181.
[19] Guyon I, Weston J, Barnhill S, et al. Gene selection for cancer classification using support vector machines[J]. Machine Learning,2002,46(1/3):389-422.
[20] Support vector machines:theory and applications[M]. Springer Science & Business Media, 2005.
[21] Shahraiyni H, Ghafouri M, Shouraki S, et al. Comparison between active learning method and support vector machine for runoff modeling[J]. Journal of Hydrology and Hydromechanics,2012,60(1):16-32.
[22] Brereton R G, Lloyd G R. Support vector machines for classification and regression[J]. Analyst, 2010, 135(2):230-267.
[23] 张兰影,庞博,徐宗学,等.基于支持向量机的石羊河流域径流模拟适用性评价[J].干旱区资源与环境,2013,27(7):113-118.
[24] 丁铁山,董汝瑞,温季.基于支持向量机理论的土壤水分预测模型研究[J].人民黄河,2011,33(3):68-73.
[25] 王慧勤,雷刚.基于LIBSVM的风速预测方法研究[J].科学技术与工程,2011,11(22):5440-5442.
[26] Chang C C, Lin C J. LIBSVM:a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology,2011,2(3):389-396.
[27] Chih-Chung Chang and Chih-Jen Lin. LIBSVM -A Library for Support Vector Machines[EB/OL]. http://www.csie.ntu.edu.tw/-cjlin/libsvm/index.html, 2015-12-14.
[28] 王彤彤,吴旺旺,张小平,等.甘肃省能源利用碳足迹估算与分析[J].湖北农业科学,2016,55(2):349-353.
[29] Gill M K, Asefa T, Kemblowski M W, et al. Soil moisture prediction using support vector machines1[J]. Journal of the American Water Resources Association,2006,42(4):1033-1046.
[30] 聂春燕,胡克林,邵元海,等.基于支持向量机和神经网络的土壤水力学参数预测效果比较[J].中国农业大学学报,2010(6):102-107.

相似文献/References:

[1]史彦江,宋锋惠,罗青红,等.伊犁河流域油葵种植地产流产沙试验研究[J].水土保持研究,2011,18(02):40.
　SHI Yan-jiang,SONG Feng-hui,LUO Qing-hong,et al.Experimental Study on Generation of Runoff and Sediment on the Slope Grown Oil Sunflower in Ili River Basin[J].Research of Soil and Water Conservation,2011,18(03):40.
[2]苏嫄,焦菊英,马祥华.黄土丘陵沟壑区主要群落地上生物量季节变化及其与土壤水分的关系[J].水土保持研究,2012,19(06):7.
　SU Yuan,JIAO Ju-ying,MA Xiang-hua.Seasonal Variation of Aboveground Biomass of Main Plant Communities and Its Relationship with Soil Moisture in the Hill-gully Loess Plateau[J].Research of Soil and Water Conservation,2012,19(03):7.
[3]王巧利,贾燕锋,王宁,等.黄土丘陵沟壑区自然恢复坡面植物根系的分布特征[J].水土保持研究,2012,19(05):16.
　WANG Qiao-li,JIA Yan-feng,WANG Ning,et al.Distribution of Root on Vegetation Recovery Slope in the Hilly and Gully Loess Plateau[J].Research of Soil and Water Conservation,2012,19(03):16.
[4]许浩,蒋齐,潘占兵,等.黄土丘陵区降雨、土壤水分和苗木成活率的关系[J].水土保持研究,2012,19(05):202.
　XU Hao,JIANG Qi,PAN Zhan-bing,et al.Relationship of Rainfall, Soil Moisture and Seedling Survival Rate in Loess Hilly Region[J].Research of Soil and Water Conservation,2012,19(03):202.
[5]邝高明,朱清科,刘中奇,等.黄土丘陵沟壑区微地形对土壤水分及生物量的影响[J].水土保持研究,2012,19(03):74.
　KUANG Gao-ming,ZHU Qing-ke,LIU Zhong-qi,et al.Effect of Microrelief on the Soil Water and Vegetation Arrangement in Loess Hilly and Gully Region[J].Research of Soil and Water Conservation,2012,19(03):74.
[6]鲁瑞洁,唐清亮,桑艳礼,等.青海湖克土沙区不同类型沙丘土壤水分的动态变化[J].水土保持研究,2012,19(02):111.
　LU Rui-jie,TANG Qing-liang,SANG Yan-li,et al.Dynamic Changes of Soil Moisture in Different Dunes of Ketu Sand Land in Qinghai Lake Basin[J].Research of Soil and Water Conservation,2012,19(03):111.
[7]展秀丽,严平,王宁,等.青海湖防沙工程措施区土壤水分及入渗特征初步研究[J].水土保持研究,2012,19(01):33.
　ZHAN Xiu-li,YAN Ping,WANG Ning,et al.Preliminary Study on Soil Water and Permeability Characteristics of Desertification Combating Areas Exerted by Engineering Measures around Qinghai Lake[J].Research of Soil and Water Conservation,2012,19(03):33.
[8]文曼,郑纪勇.生物炭不同粒径及不同添加量对土壤收缩特征的影响[J].水土保持研究,2012,19(01):46.
　WEN Man,ZHENG Ji-yong.Effects of Different Sizes of Biochar and Their Additiont Rates on Soil Shrinkage Characteristics[J].Research of Soil and Water Conservation,2012,19(03):46.
[9]邵明安,陈志雄.SPAC中的水分运动[J].水土保持研究,1991,(01):3.
　Shao Mingan,Chen Zhixiong.WATER MOVEMENT IN SPAC[J].Research of Soil and Water Conservation,1991,(03):3.
[10]刘向东,吴钦孝,赵鸿雁,等.黄土丘陵区油松人工林和山杨林林冠对降水的再分配及其对土壤水分的影响[J].水土保持研究,1991,(02):9.
　Liu Xiangdong,Wu Qinxiao,Zhao Hongyan,et al.REDISTRIBUTION OF PRECIPITATION BY CANOPIES OF ARTIFICIAL CHINESE PINES AND MOUNTAIN POPLARS AND ITS INFLUENCE ON SOIL MOISTURE IN LOESS HILLY REGION[J].Research of Soil and Water Conservation,1991,(03):9.

备注/Memo

收稿日期:2016-05-20;改回日期:2016-06-14。
基金项目:国家自然科学基金“生物炭对黄土高原不同质地土壤水文过程影响及机理的定位研究”（41571225）
作者简介:王彤彤(1993-),男,甘肃天水人,硕士研究生,研究方向为土壤污染与修复。E-mal:tongtwang@163.com
通讯作者:郑纪勇(1974-),男,山东聊城人,博士,副研究员,主要从事农田生态系统研究。E-mal:zhjy@ms.iswc.ac.cn

更新日期/Last Update: 1900-01-01