CTP: A hybrid CNN-Transformer-PINN model for ocean front forecasting

TL;DR

This paper introduces CTP, a hybrid deep learning model combining CNN, Transformer, and PINN techniques to improve ocean front forecasting accuracy and physical consistency over multiple steps.

Contribution

The paper presents a novel hybrid model that integrates CNN, Transformer, and PINN for ocean front prediction, addressing spatial and physical challenges of previous methods.

Findings

Achieves state-of-the-art performance in ocean front forecasting.

Outperforms baseline models in accuracy and stability.

Effective in multi-step predictions across different ocean regions.

Abstract

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.