LAUSR

BACKGROUND Tea garden pest control is a crucial aspect of ensuring tea quality. In this context, the time series prediction of insect pests in tea gardens holds paramount significance. However, deep learning-based time series prediction techniques are rapidly advancing and research into their use in tea garden pest prediction is limited. The current study investigates the time series of whitefly populations in the Tea Expo Garden, Jurong City, Jiangsu Province employing three deep learning algorithms namely Informer, Long Short-Term Memory Network (LSTM), and LSTM-attention for prediction. RESULTS The comparative analysis of the three deep learning algorithms revealed optimal results for the LSTM-attention with an average root mean square error (RMSE) of 2.84 and average mean absolute error (MAE) of 2.52 in 7 days prediction length, respectively. For a prediction length of 3 days, LSTM also achieved the best performance, with an average RMSE of 2.60 and an average MAE of 2.24. CONCLUSION These findings suggest that different prediction lengths influence the model performance in tea garden pest time series prediction. Additionally, deep learning could be applied satisfactorily in predicting time series of insect pests in tea gardens based on LSTM-attention. Thus, this study provides a theoretical basis for the research on the time series of pest and disease infestations in tea plants. This article is protected by copyright. All rights reserved.