A Novel Multi-Input Multi-Output Recurrent Neural Network Based on Multimodal Fusion and Spatiotemporal Prediction for 0–4 Hour Precipitation Nowcasting
Open Access
- 29 November 2021
- journal article
- research article
- Published by MDPI AG in Atmosphere
- Vol. 12 (12) , 1596
Abstract
Multi-source meteorological data can reflect the development process of single meteorological elements from different angles. Making full use of multi-source meteorological data is an effective method to improve the performance of weather nowcasting. For precipitation nowcasting, this paper proposes a novel multi-input multi-output recurrent neural network model based on multimodal fusion and spatiotemporal prediction, named MFSP-Net. It uses precipitation grid data, radar echo data, and reanalysis data as input data and simultaneously realizes 0–4 h precipitation amount nowcasting and precipitation intensity nowcasting. MFSP-Net can perform the spatiotemporal-scale fusion of the three sources of input data while retaining the spatiotemporal information flow of them. The multi-task learning strategy is used to train the network. We conduct experiments on the dataset of Southeast China, and the results show that MFSP-Net comprehensively improves the performance of the nowcasting of precipitation amounts. For precipitation intensity nowcasting, MFSP-Net has obvious advantages in heavy precipitation nowcasting and the middle and late stages of nowcasting.Keywords
Funding Information
- National Natural Science Foundation of China (41975066)
This publication has 28 references indexed in Scilit:
- Computer Vision in Precipitation Nowcasting: Applying Image Quality Assessment Metrics for Training Deep Neural NetworksAtmosphere, 2019
- All convolutional neural networks for radar-based precipitation nowcastingProcedia Computer Science, 2019
- Application of machine learning to an early warning system for very short-term heavy rainfallJournal of Hydrology, 2019
- Short-Term Rainfall Forecasting Using Multi-Layer PerceptronIEEE Transactions on Big Data, 2018
- Evaluation of the ability of the Weather Research and Forecasting model to reproduce a sub-daily extreme rainfall event in Beijing, China using different domain configurations and spin-up timesHydrology and Earth System Sciences, 2018
- An overview of multi-task learningNational Science Review, 2017
- Operational Application of Optical Flow Techniques to Radar-Based Rainfall NowcastingAtmosphere, 2017
- Japanese early-warning for debris flows and slope failures using rainfall indices with Radial Basis Function NetworkLandslides, 2010
- Using Temporal Modes of Rainfall to Evaluate the Performance of a Numerical Weather Prediction ModelMonthly Weather Review, 2004
- CMORPH: A Method that Produces Global Precipitation Estimates from Passive Microwave and Infrared Data at High Spatial and Temporal ResolutionJournal of Hydrometeorology, 2004