• ▶ 2008-2024年被中国情报信息研究所评价中心评为“中国科技核心期刊”
  • ▶ 2019-2024年连续三届被中国科学院文献情报中心中国科学引文数据库CSCD(核心库)收录
  • ▶ 2021、2023年入编北京大学图书馆《中文核心期刊要目总览》
  • ▶ 2020-2024连续四年入选《科技期刊世界影响力指数(WJCI)报告》
杨轶航, 吕德生, 刘宁宁, 王振华,李 淼, 张金珠, 王东旺.基于多头LSTM模型的南疆枣树土壤墒情预测水资源与水工程学报[J].,2025,36(2):207-217
基于多头LSTM模型的南疆枣树土壤墒情预测
Soil moisture prediction of jujube trees in southern Xinjiang based on multihead LSTM model
  
DOI:10.11705/j.issn.1672-643X.2025.02.24
中文关键词:  土壤墒情预测  多头LSTM  麻雀搜索算法  k折交叉验证  南疆滴灌骏枣
英文关键词:prediction of soil moisture  multihead long short-term memory(M-LSTM)  sparrow search algorithm(SSA)  k-fold cross-validation  southern Xinjiang drip irrigation jujube
基金项目:国家重点研发计划项目(2022YFD1900405); 兵团科技成果转化引导计划项目(2023BA003); 国家“十四五”重点研发计划项目(2021YFD1900802-2); 兵团农业GG项目(2023AA305)
作者单位
杨轶航1,2,3,4, 吕德生1,2,3,4, 刘宁宁1,2,3,4, 王振华1,2,3,4,李 淼1,2,3,4, 张金珠1,2,3,4, 王东旺1,2,3,4 (1.石河子大学 水利建筑工程学院 新疆 石河子 832000 2.现代节水灌溉兵团重点实验室新疆 石河子 832000 3.兵团农业水肥高效关键装备技术创新中心 新疆 石河子 8320004.农业农村部西北绿洲节水农业重点实验室 新疆 石河子 832000) 
摘要点击次数: 25
全文下载次数: 3
中文摘要:
      在南疆枣业生产中,准确预测土壤墒情对于优化作物种植质量和制定灌溉计划至关重要。通过建立高精度的土壤墒情预测模型,为南疆枣树的灌溉管理提供了科学依据。基于2021和2022年的全生育期枣树在20、40、60、80 cm土层的土壤墒情数据、气象数据以及灌溉水量等小时级数据集,采用长短期记忆神经网络(LSTM)模型对各土层土壤墒情进行多步预测。引入了由4个单一LSTM模型组成的多头LSTM模型,旨在扩大预测范围并提高预测精度,并采用k折交叉验证结合麻雀搜索算法(SSA)对每个单一LSTM模型进行超参数调优,以提升模型的泛化能力和准确性。对各单一模型的输出进行加权平均,获得最终的预测结果。结果表明:在4个土层墒情均值数据集上,多头LSTM模型对未来1、12、24、48 h的土壤墒情预测的决定系数(R2)分别提升至0.951、0.932、0.870、0.815;多头LSTM模型可有效提升枣树土壤墒情的中长期预测精度,特别是在24和48 h的预测中,改进效果尤为明显,这为枣树的精细化灌溉管理提供了有力支持,可帮助农民更有效地利用水资源,减少浪费。
英文摘要:
      Accurate prediction of soil moisture is crucial for optimizing crop planting quality and irrigation schemes of jujube trees (Ziziphus jujuba Mill.). This study established a high-precision soil moisture prediction model to improve the irrigation management of jujube trees in southern Xinjiang. Based on hourly datasets of soil moisture content, meteorological data, and irrigation volume for jujube trees during the entire growing seasons of 2021 and 2022 at soil depths of 20, 40, 60, and 80 cm, a long short-term memory (LSTM) neural network model was used to perform multi-step predictions of soil moisture for each soil layer. To expand the model’s prediction range and improve prediction accuracy, a multihead LSTM (M-LSTM) model consisting of four individual LSTM models was introduced. k-fold cross-validation combined with the sparrow search algorithm (SSA) was used for hyperparameter tuning of each individual model to ensure the model’s generalization ability and accuracy. Finally, the final prediction result was obtained by performing a weighted average of the outputs from each individual model. The results show that the M-LSTM model improved the coefficient of determination (R2) of the soil moisture at 1, 12, 24, and 48 h to 0.951, 0.932, 0.870, and 0.815, respectively, according to the dataset of soil moisture content averages from four soil layers. The M-LSTM model effectively enhanced the medium- and long-term prediction accuracy of soil moisture for jujube trees, with particularly significant improvements in predictions at 24 and 48 h. These findings can provide a strong support for the precise irrigation management of jujube trees, thus improving water use efficiency and avoiding unnecessary water waste.
查看全文  查看/发表评论  下载PDF阅读器
关闭