Enhancing Extended Weather Forecasts in the TCWAGFS Model Using Deep Learning Method for SST Bias Correction

Katherine Shu-Min Li, Nadun Sinhabahu, Ben‐Jei Tsuang, Fang-Chi Wu, Wan‐Ling Tseng, Pei-Hsuan Kuo, Sying-Jyan Wang, Pang-Yen Liu, Jen–Her Chen, Bin-Ming Wang, Yung-Yao Lan, Sun‐Yuan Kung

Preprint · 24 June 2025 · Princeton University

Paper PDF

In one sentence. Bi-LSTM bias correction reduces the SST forecast error in TCWAGFS by 97% at day 10 (0.38 K to 0.01 K), improving extended-range forecasts tied to MJO and ENSO.

Abstract

Abstract. The extended weather (> 7 days) and the seasonal climate predictions are highly dependent on the status of Madden Julian Oscillation (MJO) and El Niño-Southern Oscillation (ENSO). Both the evolutions of MJO and ENSO are found to be correlated to the anomalies of the global sea surface temperature (SST). To decrease the predicting SST bias (BiasSST) in a coupled ocean-atmosphere global model, we evaluate nine well-developed machine learning algorithms. By using the Bi-directional Long Short-Term Memory (Bi-LSTM) algorithm, it is found the bias can be reduced significantly. For example, the Root Mean Squared Error on Day 10 forecast (denoted as D10) is reduced to 0.01 K by the Bi-LSTM algorithm while the original bias is 0.38 K by the Taiwan Central Weather Administration Global Forecast System (TCWAGFS), of which the error is reduced by 97 %.

Labels

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.