Broad-UNet: Multi-scale feature learning for nowcasting tasks
| Autor: | Fernández, Jesús García, Mehrkanoon, Siamak, Sub Algorithmic Data Analysis, Algorithmic Data Analysis |
|---|---|
| Přispěvatelé: | Sub Algorithmic Data Analysis, Algorithmic Data Analysis, RS: FSE DACS, Dept. of Advanced Computing Sciences, RS: FSE DACS Mathematics Centre Maastricht |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
I.2 Computer Science - Machine Learning Nowcasting I.5 Computer science Cognitive Neuroscience Pooling Convolutional neural network Cloud cover forecasting computer.software_genre U-net Machine Learning (cs.LG) Artificial Intelligence Image Processing Computer-Assisted Humans Pyramid (image processing) Weather NEURAL-NETWORK Artificial neural network business.industry Deep learning Satellite imagery Data mining Artificial intelligence Scale (map) business computer Feature learning Precipitation forecasting |
| Zdroj: | Neural Networks, 144, 419. Elsevier Limited Neural Networks, 144, 419-427. Elsevier Science |
| ISSN: | 0893-6080 |
| Popis: | Weather nowcasting consists of predicting meteorological components in the short term at high spatial resolutions. Due to its influence in many human activities, accurate nowcasting has recently gained plenty of attention. In this paper, we treat the nowcasting problem as an image-to-image translation problem using satellite imagery. We introduce Broad-UNet, a novel architecture based on the core UNet model, to efficiently address this problem. In particular, the proposed Broad-UNet is equipped with asymmetric parallel convolutions as well as Atrous Spatial Pyramid Pooling (ASPP) module. In this way, The the Broad-UNet model learns more complex patterns by combining multi-scale features while using fewer parameters than the core UNet model. The proposed model is applied on two different nowcasting tasks, i.e. precipitation maps and cloud cover nowcasting. The obtained numerical results show that the introduced Broad-UNet model performs more accurate predictions compared to the other examined architectures. 9 pages, 11 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect