Deep Learning-Based Statistical Downscaling of Sea Surface Temperature Using a Residual Corrective Neural Network

• URL: http://arxiv.org/abs/2608.10022v1
• Date: Sun, 09 Aug 2026 11:30:16 GMT
• Title: Deep Learning-Based Statistical Downscaling of Sea Surface Temperature Using a Residual Corrective Neural Network
• Abstract summary: This study proposes a novel deep learning framework that uses a U-Net to generate an initial high-resolution sea surface temperature estimate.<n>The framework efficiently downscales SST along the west coast of Australia.<n>This balance between computational efficiency and accuracy supports applications in coastal impact assessment and marine ecosystem studies.
• Score: 1.9345024654790872
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The large-scale oceanic and atmospheric forecasts provided by global climate models typically lack sufficient resolution to accurately capture the response of the coastal ocean to atmospheric forcing and coastal circulation that drive fine-scale SST variability. Dynamical downscaling is computationally prohibitive, when applied to extensive coastlines, predictive ensembles, or long time periods. Therefore, this work presents a statistical downscaling of sea surface temperature (SST) from the seasonal coupled ocean-atmosphere forecast system (ACCESS-S2) using machine learning techniques. This study proposes a novel deep learning framework that uses a U-Net to generate an initial high-resolution SST estimate, which is subsequently refined using a residual corrective approach. The target SST fields are derived from the Regional Ocean Modeling System (ROMS). This two step approach called Residual Corrective Neural Network (RCNN) progressively refines initial U-Net predictions by incorporating dynamically scaled residuals at each step, enabling accurate capture of broad patterns and fine-grained features such as eddies and fronts. We also introduce a custom loss-assisted RCNN variant to improve performance during extreme events, which may be absent from training data due to climate-driven shifts in SST extremes. The framework efficiently downscales SST along the west coast of Australia. A 2011 marine heatwave case study shows that the RCNN improves ACCESS-S2 SST predictions by increasing horizontal resolution from 25 km to 2 km, enabling identification of fine-scale anomalies unresolved in the ACCESS-S2 dataset. This balance between computational efficiency and accuracy supports applications in coastal impact assessment and marine ecosystem studies.

Related papers

• PCA-Enhanced Adaptive NVAR Framework for High-Resolution Sea Surface Temperature Forecasting in the East Sea [0.2446672595462589]
  Traditional numerical models provide reliable predictions but are expensive and often unsuitable for real-time forecasting.<n>This study builds on our proposed Adaptive Next-Generation Reservoir Computing framework.<n>We present a reduced-order forecasting framework that combines Singular Value Decomposition to predict SST dynamics in the East Sea.
  arXiv  Detail & Related papers  (2026-06-10T14:34:13Z)
• An Adaptive Spatiotemporal Clustering Framework for 3D Ocean Subsurface Temperature Reconstruction [31.24880527218282]
  This study proposes an adaptive framework to capture both structural dependencies and temporal variation patterns of ocean surface temperature (OST)<n>By incorporating this framework with various deep learning models, the OST field can be accurately reconstructed at a global scale.<n> Experimental results demonstrate that multiple deep learning methods using the framework largely outperform their original counterparts.
  arXiv  Detail & Related papers  (2026-04-21T09:32:37Z)
• OceanSAR-2: A Universal Feature Extractor for SAR Ocean Observation [55.978228064498865]
  We present OceanSAR-2, the second generation of our foundation model for SAR-based ocean observation.<n>Building on our earlier release, which pioneered self-supervised learning on Sentinel-1 Wave Mode data, OceanSAR-2 relies on improved SSL training and dynamic data curation strategies.
  arXiv  Detail & Related papers  (2026-01-12T10:20:43Z)
• Leveraging an Atmospheric Foundational Model for Subregional Sea Surface Temperature Forecasting [0.0]
  We adapt a deep learning model to predict sea temperature (SST) in the Canary Upwelling System.<n>By fine-tuning this model with high-resolution oceanographic reanalysis data, we demonstrate its ability to capture complex patterns.<n>The model successfully reproduces large-scale SST structures but faces challenges in capturing finer details in coastal regions.
  arXiv  Detail & Related papers  (2025-10-29T14:30:12Z)
• OKG-LLM: Aligning Ocean Knowledge Graph with Observation Data via LLMs for Global Sea Surface Temperature Prediction [70.48962924608033]
  This work presents the first systematic effort to construct an Ocean Knowledge Graph (OKG) specifically designed to represent diverse ocean knowledge for SST prediction.<n>We develop a graph embedding network to learn the comprehensive semantic and structural knowledge within the OKG, capturing both the unique characteristics of individual sea regions and the complex correlations between them. Finally, we align the learned knowledge with fine-grained numerical SST data and leverage a pre-trained LLM to model SST patterns for accurate prediction.
  arXiv  Detail & Related papers  (2025-07-31T02:06:03Z)
• ReconMOST: Multi-Layer Sea Temperature Reconstruction with Observations-Guided Diffusion [48.540756751934836]
  ReconMOST is a data-driven guided diffusion model framework for multi-layer sea temperature reconstruction.<n>Our method extends ML-based SST reconstruction to a global, multi-layer setting, handling over 92.5% missing data.
  arXiv  Detail & Related papers  (2025-06-12T06:27:22Z)
• Deep Learning Weather Models for Subregional Ocean Forecasting: A Case Study on the Canary Current Upwelling System [0.0]
  This work aims to adapt a graph neural network initially developed for global weather forecasting to improve subregional ocean prediction.<n>The model is trained with satellite data and compared to state-of-the-art physical ocean models to assess its performance in capturing ocean dynamics.<n>Our results show that the deep learning model surpasses traditional methods in precision despite some challenges in upwelling areas.
  arXiv  Detail & Related papers  (2025-05-30T10:10:40Z)
• Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation [67.23953699167274]
  Self-supervised learning (SSL) has enabled the development of vision foundation models for Earth Observation (EO)<n>In EO, this challenge is amplified by the redundancy and heavy-tailed distributions common in satellite imagery.<n>We propose a dynamic dataset pruning strategy designed to improve SSL pre-training by maximizing dataset diversity and balance.
  arXiv  Detail & Related papers  (2025-04-09T15:13:26Z)
• OceanNet: A principled neural operator-based digital twin for regional oceans [0.0]
  This study introduces OceanNet, a principled neural operator-based digital twin for ocean circulation. OceanNet is applied to the northwest Atlantic Ocean western boundary current (the Gulf Stream)
  arXiv  Detail & Related papers  (2023-10-01T23:06:17Z)
• Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling [58.456404022536425]
  State of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• Long-term drought prediction using deep neural networks based on geospatial weather data [75.38539438000072]
  High-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. We tackle drought data by introducing an end-to-end approach that adopts a systematic end-to-end approach. Key findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts.
  arXiv  Detail & Related papers  (2023-09-12T13:28:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.