摘要
为提高土壤墒情预测精度,提出了一种基于遗传算法(GA)、改进粒子群算法(IPSO)、误差反向传播(BP)神经网络和支持向量机(SVM)的土壤墒情组合预测模型(GAIPSOBP-SVM)。该模型首先在BP神经网络的权阈值选择中同时引入GA和IPSO构成GAIPSOBP模型,然后对GAIPSOBP和SVM模型分别进行训练和数据仿真,最后利用建立的加权模型对GAIPSOBP和SVM模型的土壤墒情预测结果进行组合。以安庆市8个监测站某时段内农田土壤墒情数据为例,分别按隔日、两日后和三日后三种时间跨度进行土壤墒情预测,并对照BP、GA-BP、PSO-BP、IPSO-BP、GAIPSOBP和SVM模型,验证和比较提出的GAIPSOBP-SVM模型的土壤墒情预测精度。结果表明,GAIPSOBP-SVM模型的土壤含水量预测相对误差平均值最小。GAIPSOBP与SVM模型组合的GAIPSOBP-SVM模型提高了土壤墒情的预测精度,更适合于土壤墒情的短期预测,该方法可为农业节水灌溉方案的制定提供技术支撑。
In order to improve the forecast accuracy of soil moisture,a combined forecasting model GAIPSOBPSVM for soil moisture is proposed based on genetic algorithm(GA),improved particle swarm optimization(IPSO),BP neural network and support vector machine(SVM).The model introduced GA and IPSO into the weight threshold selection of BP neural network to form a GAIPSOBP model,and then the GAIPSOBP and SVM models were trained and simulated separately.Finally,an established weighted model was used to combine the soil moisture forecast results of the GAIPSOBP and SVM models.Taking the farmland soil moisture data of 8 monitoring stations in Anqing city within a certain period as an example,the soil moisture was predicted in three time spans of after one day,after two days and after three days separately,and the forecast accuracy of soil moisture between the proposed GAIPSOBP-SVM model and the comparison models BP,GA-BP,PSO-BP,IPSO-BP,GAIPSOBP and SVM were verified and compared.The comparison results showed that the average value of relative error of soil water content forecast accuracy of the proposed GAIPSOBP-SVM model was the smallest.The GAIPSOBP-SVM model based on the combination of GAIPSOBP and SVM model improves the forecast accuracy of soil moisture,and is more suitable for short-term forecast of soil moisture.The proposed method could provide technical support for the formulation of water-saving irrigation schemes in agriculture.
作者
薛明
韦波
李娟
陈慈豪
黄敏慧
邹林芯
XUE Ming;WEI Bo;LI Juan;CHEN Ci-hao;HUANG Min-hui;ZOU Lin-xin(Guangxi Key Laboratory of Spatial Information and Geomatics,Guilin University of Technology,Guilin 541004,China;College of Geomatics and Geoinformation,Guilin University of Technology,Guilin 541004,China)
出处
《土壤通报》
CAS
CSCD
北大核心
2021年第4期793-800,共8页
Chinese Journal of Soil Science
基金
国家自然科学基金项目(41961063,41461085)
“广西八桂学者”专项经费(2019-79)
广西空间信息与测绘重点实验室基金项目(16-380-25-04)
桂林理工大学博士基金项目(1996015)资助。
关键词
误差反向传播神经网络
遗传算法
改进粒子群算法
支持向量机
组合预测模型
土壤墒情预测
Error Back Propagation Neural Network
Genetic Algorithm
Improved Particle Swarm Optimization Algorithm
Support Vector Machine
Combined Forecasting Model
Soil Moisture Forecast
