Spatiotemporal neural network with attention mechanism for El Niño forecasts
Kim, J.; Kwon, M.; Kim, S.-D.; Kug, J.-S.; Ryu, J.-G.; Kim, J. (2022). Spatiotemporal neural network with attention mechanism for El Niño forecasts. NPG Scientific Reports 12(1): 7204. https://dx.doi.org/10.1038/s41598-022-10839-z
In: Scientific Reports (Nature Publishing Group). Nature Publishing Group: London. ISSN 2045-2322; e-ISSN 2045-2322, more
|   |
| Authors | | Top |
- Kim, J.
- Kwon, M.
- Kim, S.-D.
|
- Kug, J.-S.
- Ryu, J.-G.
- Kim, J.
|
|
| Abstract |
To learn spatiotemporal representations and anomaly predictions from geophysical data, we propose STANet, a spatiotemporal neural network with a trainable attention mechanism, and apply it to El Niño predictions for long-lead forecasts. The STANet makes two critical architectural improvements: it learns spatial features globally by expanding the network’s receptive field and encodes long-term sequential features with visual attention using a stateful long-short term memory network. The STANet conducts multitask learning of Nino3.4 index prediction and calendar month classification for predicted indices. In a comparison of the proposed STANet performance with the state-of-the-art model, the accuracy of the 12-month forecast lead correlation coefficient was improved by 5.8% and 13% for Nino3.4 index prediction and corresponding temporal classification, respectively. Furthermore, the spatially attentive regions for the strong El Niño events displayed spatial relationships consistent with the revealed precursor for El Niño occurrence, indicating that the proposed STANet provides good understanding of the spatiotemporal behavior of global sea surface temperature and oceanic heat content for El Niño evolution. |
|
