期刊文献+

基于ME-BiLSTM模型的苜蓿叶面积指数预测方法

Prediction Method of Alfalfa Leaf Area Index Based on ME-BiLSTM Model
下载PDF
导出
摘要 连续时序的叶面积指数(Leaf Area Index,LAI)可反映苜蓿长势的变化情况,预测苜蓿未来时段的LAI对指导田间管理决策具有重要作用。针对LAI数据采集困难,导致苜蓿时序LAI存在训练数据不足的问题,该文以生长天数为自变量,采用修正的Logistic模型对实测苜蓿LAI变化的动态过程进行建模,根据LAI模拟曲线进行数据插补,从而构建宁夏引黄灌区试验区3年的逐日苜蓿LAI数据集。在插补数据集的基础上,为解决苜蓿刈割后数据突变问题,提出了一种ME-BiLSTM模型。该模型集成移动累计和检验方法(MOSUM)以及基于双向长短期记忆网络(BiLSTM)的编码器-解码器神经网络。MOSUM方法可以实现LAI数据集中突变点检测,并剔除包含突变点训练批次,同时应用改进的BiLSTM模型进行预测。结果表明:ME-BiLSTM模型能较好地进行苜蓿LAI未来曲线变化的预测,其决定系数(R^(2))、均方根误差(RMSE)值分别为0.9985和0.0722。对于苜蓿生长的各个茬次,预测模型对于第1茬、第4茬的预测精度最高,第2茬和第3茬的预测精度稍有降低。 The continuous temporal Leaf Area Index(LAI)reflects the changes in alfalfa growth.Predicting future LAI in alfalfa plays a crucial role in guiding field management decisions.Aiming at the problem of insufficient training data for alfalfa temporal LAI due to difficulties in LAI data collection,we employ the growth days as independent variables and utilize a modified Logistic model to dynamically model the observed changes in alfalfa LAI.By interpolating data based on the simulated LAI curve,a three-year daily alfalfa LAI dataset for the Ningxia Yellow River Irrigation District experimental area is constructed.To address abrupt data changes after alfalfa cutting,we introduce the ME-BiLSTM model which integrates the Moving Sum and Moving Average(MOSUM)method with a Bidirectional Long Short-Term Memory(BiLSTM)encoder-decoder neural network.The MOSUM detects mutation points in the LAI dataset and eliminates training batches containing these points,followed by predictions using the improved BiLSTM model.It is demonstrated that the ME-BiLSTM model predicts future alfalfa LAI curve changes effectively,with coefficient of determination(R^(2))and root mean square error(RMSE)values of 0.9985 and 0.0722,respectively.The first and fourth alfalfa growth cycles have the best predictive model accuracy,whereas the second and third cycles have slightly lower accuracy.
作者 杨松涛 葛永琪 王静 刘瑞 YANG Song-tao;GE Yong-qi;WANG Jing;LIU Rui(School of Information Engineering,Ningxia University,Yinchuan 750021,China)
出处 《计算机技术与发展》 2024年第5期183-189,共7页 Computer Technology and Development
基金 国家自然科学基金地区科学基金项目(62262052,62162052) 宁夏回族自治区重点研发计划(2021BEB04016,2022BDE03007) 宁夏自然科学基金(2021AAC03041,2022AAC03004)。
关键词 苜蓿 叶面积指数 LOGISTIC模型 MOSUM 双向长短期记忆网络 alfalfa leaf area index Logistic model MOSUM bidirectional long short-term memory network
  • 相关文献

参考文献10

二级参考文献190

共引文献81

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部