Dual memory scale network for multi-step time series forecasting in thermal environment of aquaculture facility: A case study of recirculating aquaculture water temperature

作者：

Highlights：

• Innovative network for agricultural thermal environment forecasting.

• Integrate dule-scale memory structure for multi-step time series prediction.

• Attention mechanism optimizes the coordination of dule-scale memory components.

• The proposed model achieves excellent performance on long-term prediction.

摘要

•Innovative network for agricultural thermal environment forecasting.•Integrate dule-scale memory structure for multi-step time series prediction.•Attention mechanism optimizes the coordination of dule-scale memory components.•The proposed model achieves excellent performance on long-term prediction.

论文关键词：Recirculating aquaculture water temperature,Thermal environment,Multi-step time series forecasting,Deep learning,Dual-scale memory,Attention mechanism

论文评审过程：Received 6 May 2021, Revised 2 July 2022, Accepted 16 July 2022, Available online 21 July 2022, Version of Record 30 July 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118218