Name
Abstract | ||
|---|---|---|
Multi-step prediction of sea surface temperature (SST) is a challenging problem because small errors in its shortrange forecasts can be compounded to create large errors at longer ranges. In this paper, we propose a hierarchical LSTM framework to improve the accuracy for long-term SST prediction. Our framework alleviates the error accumulation problem in multi-step prediction by leveraging outputs from an ensemble of physically-based dynamical models. Unlike previous methods, which simply take a linear combination of the outputs to produce a single deterministic forecast, our framework learns a nonlinear relationship among the ensemble member forecasts. In addition, its multi-level structure is designed to capture the temporal autocorrelation between forecasts generated for the same lead time as well as those generated for different lead times. Experiments performed using SST data from the tropical Pacific ocean region show that the proposed framework outperforms various baseline methods in more than 70% of the grid cells located in the study region. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/DSAA.2019.00018 | 2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA) |
Keywords | Field | DocType |
sea surface temperature,time series,LSTM | Linear combination,Nonlinear system,Grid cell,Sea surface temperature,Computer science,Algorithm,Lead time,Tropical pacific,Autocorrelation | Conference |
ISSN | ISBN | Citations |
2472-1573 | 978-1-7281-4494-8 | 0 |
PageRank | References | Authors |
0.34 | 2 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xi Liu | 1 | 11 | 3.45 |
| Tyler Wilson | 2 | 2 | 2.08 |
| Pang-ning Tan | 3 | 2542 | 162.00 |
| Lifeng Luo | 4 | 23 | 6.40 |