| 基于粒子群算法优化BP神经网络的土壤含水量短期预测模型 |
| |
| 引用本文： | 牛曼丽,李新旭,张彦军,雷喜红,王艳芳,李蔚.基于粒子群算法优化BP神经网络的土壤含水量短期预测模型[J].蔬菜,2020(8):24-30. |
| |
| 作者姓名： | 牛曼丽 李新旭 张彦军 雷喜红 王艳芳 李蔚 |
| |
| 作者单位： | 北京市农业技术推广站,北京 100029;北京市科学技术情报研究所,北京 100044 |
| |
| 基金项目： | 果类蔬菜产业技术体系北京市创新团队（BAIC01-2020）。 |
| |
| 摘 要： | 为提高土壤含水量预测精度,基于物联网监测数据,提出了粒子群算法(PSO)优化BP神经网络的土壤含水量预测方法。首先应用主成分分析法筛选出影响土壤含水量的关键影响因子,然后构建8-5-1的BP神经网络拓扑结构,应用粒子群算法优化BP神经网络的初始权值和阈值。结果表明:与传统BP神经网络相比,新模型优化了网络结构,避免了陷入局部最优解,具有良好的预测效果;模型的评价指标平均绝对误差、平均绝对百分误差、误差均方根分别为0.259 2、0.010 5和0.135 6,与单一BP神经网络相比,预测精度更高,可满足实际的土壤含水量预测的需要。
|
| 关 键 词： | 土壤含水量 主成分分析 粒子群算法 BP神经网络 模型 |
Short-term Prediction Model of Soil Water Content Based on BP Neural Network Optimized by PSO |
| |
| NIU Manli,LI Xinxu,ZHANG Yanjun,LEI Xihong,WANG Yanfang,LI Wei.Short-term Prediction Model of Soil Water Content Based on BP Neural Network Optimized by PSO[J].Vegetables,2020(8):24-30. |
| |
| Authors: | NIU Manli LI Xinxu ZHANG Yanjun LEI Xihong WANG Yanfang LI Wei |
| |
| Institution: | 1. Beijing Agricultural Technology Extension Station, Beijing 100029, China; 2. Beijing Institute of Science and Technology Information, Beijing 100044, China |
| |
| Abstract: | Abstract: In order to improve the prediction accuracy of soil water content, based on the monitoring data of the Internet of Things, the prediction method of soil water content of BP neural network optimized by particle swarm optimization algorithm (PSO) was proposed. Firstly, the principal component analysis method was used to ensure the key infl uencing factors affecting soil moisture content, and then the 8-5-1 BP neural network topology structure was constructed, and the particle swarm algorithm was used to optimize the initial weight and threshold of the BP neural network. The results showed that the new model optimized the network structure and avoided the local optimal solution, showing good prediction effects. The mean absolute error (MAE), mean absolute percentage error (MAPE) and root mean square error (RMSE) of the model were 0.259 2, 0.010 5 and 0.135 6, respectively. Compared with single BP neural network, the prediction accuracy of the new model was better, which could meet the practical needs for soil moisture prediction. |
| |
| Keywords: | Keywords: soil water content principal component analysis particle swarm optimization BP neural network model |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《蔬菜》浏览原始摘要信息 |
| 点击此处可从《蔬菜》下载免费的PDF全文 |
|
