Journal article
EfficientRainNet: Leveraging EfficientNetV2 for memory-efficient rainfall nowcasting
Environmental modelling & software : with environment data news, Vol.176, 106001
05/2024
DOI: 10.1016/j.envsoft.2024.106001
Abstract
Rainfall nowcasting is critical for timely weather predictions and emergency responses, particularly in flood-prone areas. Existing models, while accurate, often require substantial computational resources. Addressing this challenge, our study introduces EfficientRainNet, a neural network that leverages mobile inverted residual linear bottleneck blocks for memory-efficient rainfall nowcasting. Our evaluation, conducted over the State of Iowa, demonstrates that EfficientRainNet achieves accuracy comparable to that of the widely adopted encoder-decoder convolutional GRUs, yet with a substantially reduced model complexity, possessing less than 6% of the trainable parameters of the encoder-decoder convolutional GRUs and less than 9% of those of the compared Small Attention UNet. This lightweight design opens the possibility for deployment on edge devices, offering a scalable and accessible solution for real-time rainfall prediction. The results suggest further potential for extending the application of EfficientRainNet across broader regions and varied climatic conditions, harnessing its computational efficiency for widespread climate monitoring and forecasting.
•This study presents a resilient memory-wise efficient neural network architecture for rainfall nowcasting.•The neural network architecture this study presents was tested over a large basin in Iowa.•The study compared the proposed approach to state-of-the-art neural network approaches in the rainfall nowcasting literature.
Details
- Title: Subtitle
- EfficientRainNet: Leveraging EfficientNetV2 for memory-efficient rainfall nowcasting
- Creators
- Muhammed Sit - IIHR Hydroscience and Engineering, University of Iowa, Iowa City, IA, USABong-Chul Seo - IIHR Hydroscience and Engineering, University of Iowa, Iowa City, IA, USABekir Demiray - University of IowaIbrahim Demir - University of Iowa
- Resource Type
- Journal article
- Publication Details
- Environmental modelling & software : with environment data news, Vol.176, 106001
- DOI
- 10.1016/j.envsoft.2024.106001
- ISSN
- 1364-8152
- eISSN
- 1873-6726
- Publisher
- Elsevier Ltd
- Language
- English
- Date published
- 05/2024
- Academic Unit
- Electrical and Computer Engineering; Civil and Environmental Engineering; IIHR--Hydroscience and Engineering; Injury Prevention Research Center
- Record Identifier
- 9984572559902771
Metrics
13 Record Views