| 277 | 0 | 461 |
| 下载次数 | 被引频次 | 阅读次数 |
针对水稻种植过程中土壤水分含量难以准确预测问题，提出了一种基于集成XGBoost、WOA和GRU的稻田土壤水分含量组合预测模型XGBoost-WOA-GRU．首先，为简化模型，通过XGBoost特征重要性计算筛选影响稻田土壤水分的关键影响因子；然后，通过WOA确定GRU神经网络的神经元数量、学习率和样本批量等重要参数的最优组合；最后构建组合XGBoost-WOA-GRU模型对稻田土壤水分进行预测．仿真结果表明，与标准BP神经网络、SVR、GRU、XGBoost-GRU、XGBoost-GA-GRU、XGBoost-PSO-GRU等基线模型相比，模型XGBoostWOA-GRU的RMSE、MAE和R2均为最佳，表明所提出的组合模型具有较高预测准确率．
Abstract：To address the challenge of accurately predicting soil moisture content during rice cultivation,a combined prediction model,is proposed integrating XGBoost,WOA,and GRU,named XGBoostWOA-GRU.Firstly,to simplify the model,key influencing factors for paddy soil moisture were screened through XGBoost feature importance calculations.Then,the optimal combination of important parameters such as the number of neurons,learning rate,and sample batch size in the GRU neural network was determined through WOA.Finally,the integrated XGBoost-WOA-GRU model was constructed for paddy soil moisture prediction.Simulation results indicate that compared to baseline models such as standard BP neural networks,SVR,GRU,XGBoost-GRU,XGBoost-GA-GRU,and XGBoost-PSO-GRU,the XGBoost-WOA-GRU model achieves the best RMSE,MAE and R2,demonstrating the proposed combined model's high predictive accuracy.
[1]蔡昊炀，韩孟红，陈俊霖，等．不同灌溉用水量对水稻产量和水分利用效率的影响[J]．中国稻米，2024,30(5):103-106.
[2] XING H,ZHOU W,WANG C,et al.Excessive nitrogen application under moderate soil water deficit decreases photosynthesis,respiration,carbon gain and water use efficiency of maize[J].Plant Physiology and Biochemistry,2021,166:1065-1075.
[3]赵黎明，段绍彪，项洪涛，等．干湿交替灌溉与植物生长调节剂对水稻光合特性及内源激素的影响[J]．作物学报，2025,51(1):174-188.
[4] EL-MAGEED T A,EL-MAGEED S A,EL-SAADONY M T,et al.Plant growth-promoting rhizobacteria improve growth,morph-physiological responses,water productivity,and yield of rice plants under full and deficit drip irrigation[J].Rice,2022,15(1):16.
[5] JABED M A,MURAD M A A.Crop yield prediction in agriculture:a comprehensive review of machine learning and deep learning approaches,with insights for future research and sustainability[J].Heliyon,2024,10(24):e40836.
[6] ALVIM S J T,GUIMAR?ES C M,SOUSA E F,et al.Application of artificial intelligence for irrigation management:a systematic review[J].Engenharia Agrícola,2022,42:e20210159.
[7]崔嵩，吴锦，张乃丰，等．基于SCSSA-CNN-Bi LSTM模型的冬小麦生育期日土壤水分预测研究[J/OL]．灌溉排水学报（2025-07-14）.https://doi. org/10. 13522/j. cnki. ggps. 2025183.
[8]谢妍，贾志军，王二英，等．基于IPSO-BiLSTM和SVM的灌区农田土壤含水率预测研究[J]．节水灌溉，2024(12):63-71.
[9] HUANG Y.Improved SVM-based soil-moisture-content prediction model for tea plantation[J].Plants,2023,12(12):2309.
[10] FILIPOVI?N,BRDAR S,MIMI?G,et al.Regional soil moisture prediction system based on Long Short-Term Memory network[J].Biosystems engineering,2022,213:30-38.
[11]李学军，程红．基于LSTM算法的智能节水灌溉预测模型研究[J]．农机化研究，2022,44(03):22-27.
[12] NOSOUHIAN S,NOSOUHIAN F,KHOSHOUEI A K.A review of recurrent neural network architecture for sequence learning:comparison between LSTM and GRU[EB/OL].(2021-07-12).https://www. preprints. org/manuscript/202107. 0252/v1.
[13]王旭，托娅，李鑫，等．基于GRU的数据中心温度预测[J]．哈尔滨理工大学学报，2024,29(6):101-111.
[14]朱鑫，林琼，何淽琦，等．基于门控循环单元的基质栽培黄瓜结果期蒸散量预测模型[J]．福建农业学报，2024,39(5):532-539.
[15] LI W,WU H,ZHU N,et al.Prediction of dissolved oxygen in a fishery pond based on gated recurrent unit(GRU)[J].Information Processing in Agriculture,2021,8(1):185-193.
[16] BHAVANI A,RAMANA A V,CHAKRAVARTHY A S N.Comparative analysis between LSTM and GRU in stock price prediction[C]//2022 International Conference on Edge Computing and Applications.Tamilnadu:IEEE,2022:532-537.
[17] TAO H,AWADH S M,SALIH S Q,et al.Integration of extreme gradient boosting feature selection approach with machine learning models:application of weather relative humidity prediction[J].Neural Computing and Applications,2022,34(1):515-533.
[18]范竞敏，贺广林，王新刚，等．基于VMD-TCN-GRU-AM的超短期风电预测[J]．太阳能学报，2025,46(6):538-547.
[19]邢作霞，马岩溪，郭珊珊，等．基于WOA-GRU的风电机组发电机故障预警方法[J]．电机与控制学报，2025,29(6):54-62.
[20]胡聪，李汝彬，刘双印，等．基于Transformer-MultiScaleTCN的鹅舍湿度多步预测模型[J]．仲恺农业工程学院学报，2025,38(2):22-30.
基本信息:
中图分类号:TP18;S152.7;S511
引用信息:
[1]董佳琦,刘双印,周冰.基于XGBoost-WOA-GRU的稻田土壤水分含量预测[J].仲恺农业工程学院学报,2025,38(06):1-6.
基金信息:
国家自然科学基金项目（62373390）; 广东省自然科学基金重点项目（2022B1515120059）; 广州市科技计划项目（2023E04J1238,2023E04J1239）; 云浮市科技计划项目（2024020202,2022020303,2023020302）; 云浮市2023年产业创新团队项目（CYRC202301）; 全国高等院校计算机基础教育研究会计算机基础教育教学研究项目（2025-AFCEC-358）; 广州商学院2025年度校级教学质量与教学改革工程项目（2025ZLGC33）
2025-09-22
2025-09-22
2025-09-22