基于VMD和LSTM的农产品价格预测
Price Forecasting of Agricultural Products Based on VMD and LSTM

现今的气候变化和环境问题对农业生产造成了越来越大的影响，而农产品价格的波动对农业生产者和消费者都具有直接的经济影响。通过研究农产品价格预测，可以帮助人们更好地应对环境变化带来的挑战。为提高短期价格预测精度，提出了一个基于变分模态分解(Variational Mode Decomposition, VMD)和长短期记忆网络(Long Short-Term Memory, LSTM)的多通道短期价格预测模型。该模型利用VMD将原始时间序列数据分解为一系列不同特征的模态函数，并对每个模态分量分别使用长短期记忆网络进行特征分析预测，最后对各模态分量下的预测结果进行整合。实例测试结果表明，VMD-LSTM模型的预测准确度高于LSTM，具有不错的实用效果。
Nowadays, climate change and environmental issues are increasingly impacting agricultural production, while fluctuations in agricultural product prices directly affect both producers and consumers economically. Studying agricultural price prediction can help people better cope with challenges brought by environmental changes. To improve the accuracy of short-term price forecasting, a multi-channel model based on Variational Mode Decomposition (VMD) and Long Short-Term Memory (LSTM) is proposed. This model utilizes VMD to decompose original time series data into a series of modal functions with different characteristics. Each modal component is then analyzed and predicted using LSTM for feature extraction. Finally, the predictions from each modal component are integrated. Results from empirical testing indicate that the VMD-LSTM model outperforms LSTM alone in terms of prediction accuracy and demonstrates promising practical utility.