RCL-Learning: ResNet and convolutional long short-term memory-based spatiotemporal air pollutant concentration prediction model

作者：

Highlights：

• The review highlights model PM2.5 concentration prediction performance improvement and solving multi-step prediction problem.

• RCL-Learning effectively solving the problem of insufficient extraction of pollutants and meteorological data features in multiple cities.

• RCL-Learning yields higher-accuracy predictions by fully extracting spatiotemporal features.

• RCL-Learning has been applied as one of the practical auxiliary models in the national urban pollution prediction tasks.

摘要

•The review highlights model PM2.5 concentration prediction performance improvement and solving multi-step prediction problem.•RCL-Learning effectively solving the problem of insufficient extraction of pollutants and meteorological data features in multiple cities.•RCL-Learning yields higher-accuracy predictions by fully extracting spatiotemporal features.•RCL-Learning has been applied as one of the practical auxiliary models in the national urban pollution prediction tasks.

论文关键词：Deep learning,Residual network,Convolutional long short-term memory,Air pollutant concentration prediction

论文评审过程：Received 1 January 2021, Revised 27 June 2022, Accepted 28 June 2022, Available online 5 July 2022, Version of Record 11 July 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118017