Data Driven Deep Learning for Correcting Global Climate Model Projections of SST and DSL in the Bay of Bengal

2025-04-29

AI Summary

CMIP6 global climate models exhibit substantial biases in sea surface temperature (SST) and dynamic sea level (DSL) projections over the Bay of Bengal, with root-mean-square errors (RMSEs) of 1.2 °C and 1.1 m, respectively, during 2015–2024. To address this, we develop the first deep neural network model specifically designed for joint bias correction of SST and DSL in this region. Our method employs climatological anomaly preprocessing, phased training—historical (1950–2014) and future (2015–2023 validation/test)—and integration of ORAS5 ocean reanalysis data. Relative to the conventional empirical quantile mapping (EDCDF) approach, our model reduces SST and DSL RMSE by 0.15 °C and 0.3 m, respectively. Furthermore, it reveals previously unresolved dynamical features of oceanic variability at monthly-to-decadal timescales post-correction. We generate high-fidelity, bias-corrected projections for 2024–2100, enabling improved assessments of monsoonal precipitation changes and marine fishery productivity impacts in the Bay of Bengal.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Climate change alters ocean conditions, notably temperature and sea level. In the Bay of Bengal, these changes influence monsoon precipitation and marine productivity, critical to the Indian economy. In Phase 6 of the Coupled Model Intercomparison Project (CMIP6), Global Climate Models (GCMs) use different shared socioeconomic pathways (SSPs) to obtain future climate projections. However, significant discrepancies are observed between these models and the reanalysis data in the Bay of Bengal for 2015-2024. Specifically, the root mean square error (RMSE) between the climate model output and the Ocean Reanalysis System (ORAS5) is 1.2C for the sea surface temperature (SST) and 1.1 m for the dynamic sea level (DSL). We introduce a new data-driven deep learning model to correct for this bias. The deep neural model for each variable is trained using pairs of climatology-removed monthly climate projections as input and the corresponding month's ORAS5 as output. This model is trained with historical data (1950 to 2014), validated with future projection data from 2015 to 2020, and tested with future projections from 2021 to 2023. Compared to the conventional EquiDistant Cumulative Distribution Function (EDCDF) statistical method for bias correction in climate models, our approach decreases RMSE by 0.15C for SST and 0.3 m for DSL. The trained model subsequently corrects the projections for 2024-2100. A detailed analysis of the monthly, seasonal, and decadal means and variability is performed to underscore the implications of the novel dynamics uncovered in our corrected projections.

Problem

• Correcting SST and DSL biases in CMIP6 GCMs for Bay of Bengal
• Reducing RMSE between climate models and reanalysis data
• Improving future climate projections using deep learning

Innovation

• Data-driven deep learning corrects climate model biases
• Deep neural model trained with historical and reanalysis data
• Reduces RMSE for SST and DSL projections significantly