CTP: A hybrid CNN-Transformer-PINN model for ocean front forecasting
By: Yishuo Wang , Feng Zhou , Muping Zhou and more
Potential Business Impact:
Predicts ocean currents more accurately and reliably.
This paper proposes CTP, a novel deep learning framework that integrates convolutional neural network(CNN), Transformer architectures, and physics-informed neural network(PINN) for ocean front prediction. Ocean fronts, as dynamic interfaces between distinct water masses, play critical roles in marine biogeochemical and physical processes. Existing methods such as LSTM, ConvLSTM, and AttentionConv often struggle to maintain spatial continuity and physical consistency over multi-step forecasts. CTP addresses these challenges by combining localized spatial encoding, long-range temporal attention, and physical constraint enforcement. Experimental results across south China sea(SCS) and Kuroshio(KUR) regions from 1993 to 2020 demonstrate that CTP achieves state-of-the-art(SOTA) performance in both single-step and multi-step predictions, significantly outperforming baseline models in accuracy, $F_1$ score, and temporal stability.
Similar Papers
Channel, Trend and Periodic-Wise Representation Learning for Multivariate Long-term Time Series Forecasting
Computational Engineering, Finance, and Science
Predicts future events better by seeing patterns.
KunPeng: A Global Ocean Environmental Model
Machine Learning (CS)
Predicts ocean changes with amazing accuracy.
Physics-Informed Teleconnection-Aware Transformer for Global Subseasonal-to-Seasonal Forecasting
Machine Learning (Stat)
Predicts weather weeks to months ahead.