基于CNN-LSTM的黄淮海地区冬小麦产量预测模型
Winter Wheat Yield Prediction Model in the Yellow-Huaihe-Haihe River Region Based on CNN-LSTM
乔壮 1仇海全 2吴燕 1马帅龙1
作者信息
- 1. 安徽科技学院 机械工程学院,安徽 滁州 233100
- 2. 安徽科技学院 信息与网络工程学院,安徽 蚌埠 233030;安徽科技学院 数字乡村建设与治理安徽省哲学社会科学重点实验室,安徽 滁州 233100
- 折叠
摘要
冬小麦是我国最主要的粮食作物之一,准确预测其产量对于指导农业生产、保障粮食安全具有重要意义.利用CNN的特征提取能力和LSTM在捕捉时间序列长期依赖关系方面的优势,提出了CNN-LSTM预测模型.以黄淮海地区 35 个区县 2015-2022 年冬小麦产量和相关气象指标构建数据集,使用该模型对所选地区冬小麦产量进行预测.结果表明,CNN-LSTM预测模型精度优于其他模型,测试集中R2 达到96.91%,充分展现出该模型对于冬小麦产量预测的有效性.
Abstract
Winter wheat is one of the most crucial cereal crops in China,and the accurate prediction of its yield plays a significant role in guiding agricultural production and ensuring food security.This paper leverages the feature extraction capability of CNN and the advantage of LSTM in capturing long-term dependencies in time series to propose a CNN-LSTM prediction model.A dataset was constructed using the winter wheat yield and related meteorological indicators from 35 counties in the Yellow-Huaihe-Haihe River area from 2015 to 2022.This model was then applied to predict the winter wheat yield in the selected areas.The results indicate that the accuracy of the CNN-LSTM prediction model surpasses that of other models,with an R2 of 96.91%in the test set,thoroughly demonstrating the model's effectiveness in predicting the yield of winter wheat.
关键词
冬小麦/产量预测/卷积神经网络/长短期记忆神经网络Key words
winter wheat/yield prediction/convolutional neural network/long short-term memory network引用本文复制引用
基金项目
安徽省教育厅高校自然科学研究重点项目(2023AH051874)
安徽省教育厅高校自然科学研究重点项目(2022AH051651)
出版年
2024