Informer-LSTM融合算法在蓝莓基质温湿度预测中的研究与应用

打开文本图片集

中图分类号：TP391 文献标志码：A DOI： 10.13705/j. issn.1671-6841.2024109

文章编号：1671-6841（2026）01-0078-09

Abstract： To predict the temperature and humidity changes of blueberry substrate in greenhouses accurately，a prediction method combined Informer-LSTM algorithms was proposed for bluebery substrate temperature and humidity. Taking on-site environmental data from bluebery greenhouses as the research object，the LSTM algorithm captured the dependent relationships of time series data. It was combined with self-attention mechanisms to dynamically adjust atention weights. It enabled the model to focus on both its own attention features and LSTM features simultaneously，and the model's memory capacity was enhanced.After initial sequence generation，the LSTM algorithm was again applied to correct the shortterm attention of the model，improving its reaction speed. Experimental results demonstrated that the Informer-LSTM prediction model showed significant advantages in terms of prediction accuracy，robustness， and response speed. When sequential input data such as temperature and humidity changes significantly， the dynamic pattern changes within short-term input data were captured quickly. This model had strong practical value for assisting human decision-making and achieving intelligent control in smart greenhouse management.

Key words： smart agriculture; greenhouse blueberries； Informer model； LSTM model; temperature andhumidity prediction

0 引言

蓝莓，又名越橘或蓝浆果，是一种多年生植物，可为常绿或落叶灌木。（剩余15531字）