analiza aiqbench
This study applies Principal Component Analysis within an Adaptive Nonlinear Vector Autoregression framework to significantly improve long-term sea surface temperature forecasting efficiency. By compressing high-dimensional ocean data into a lower-dimensional latent space, the method suppresses error accumulation over 90-day horizons while maintaining millisecond inference speeds. The approach offers a scalable solution for operational oceanography where computational cost is a primary constraint.
PCA-Enhanced Adaptive NVAR Framework for High-Resolution Sea Surface Temperature Forecasting in the East Sea
arXiv:2606.12141v2 Announce Type: replace Abstract: Accurate forecasting of sea surface temperature (SST) is essential for marine ecosystem monitoring, climate assessment, fisheries management, and operational ocean forecasting. While numerical ocean models provide reliable predictions, they are computationally expensive, and conventional machine learning methods often suffer from high-dimensional inputs and error accumulation during long-term autonomous forecasting. This study extends our previously proposed Adaptive Nonlinear Vector Autoregression (Adaptive NVAR) framework to high-resolution real-world SST prediction by integrating Principal Component Analysis (PCA) through Singular Value Decomposition (SVD). Daily SST fields from the GLORYS12V1 reanalysis dataset covering the East Sea, Yellow Sea, and East China Sea are compressed into a lower-dimensional latent representation that preserves the dominant spatial variability. The proposed reduced-order framework is evaluated using autonomous rolling forecasts up to a 90-day horizon and compared with Standard NVAR (Next Generation Reservoir Computing) and a Persistence baseline. Across all three regions, Adaptive NVAR consistently suppresses long-term error accumulation, achieving up to 96.52% improvement in mean squared error relative to Persistence while maintaining stable predictive performance throughout extended forecasting. Although the adaptive architecture incurs a higher one-time offline optimization cost than Standard NVAR, inference is completed in milliseconds, making the proposed framework an efficient and scalable approach for long-term, high-resolution ocean state forecasting.
Abstract:Accurate forecasting of sea surface temperature (SST) is essential for marine ecosystem monitoring, climate assessment, fisheries management, and operational ocean forecasting. While numerical ocean models provide reliable predictions, they are computationally expensive, and conventional machine learning methods often suffer from high-dimensional inputs and error accumulation during long-term autonomous forecasting. This study extends our previously proposed Adaptive Nonlinear Vector Autoregression (Adaptive NVAR) framework to high-resolution real-world SST prediction by integrating Principal Component Analysis (PCA) through Singular Value Decomposition (SVD). Daily SST fields from the GLORYS12V1 reanalysis dataset covering the East Sea, Yellow Sea, and East China Sea are compressed into a lower-dimensional latent representation that preserves the dominant spatial variability. The proposed reduced-order framework is evaluated using autonomous rolling forecasts up to a 90-day horizon and compared with Standard NVAR (Next Generation Reservoir Computing) and a Persistence baseline. Across all three regions, Adaptive NVAR consistently suppresses long-term error accumulation, achieving up to 96.52% improvement in mean squared error relative to Persistence while maintaining stable predictive performance throughout extended forecasting. Although the adaptive architecture incurs a higher one-time offline optimization cost than Standard NVAR, inference is completed in milliseconds, making the proposed framework an efficient and scalable approach for long-term, high-resolution ocean state forecasting.
16 pages, 8 figures, 5 tables. Additional experiments added
Machine Learning (cs.LG)
arXiv:2606.12141 [cs.LG]
(or arXiv:2606.12141v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.12141 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 303 cuvinte
Subiecte conexe
PCA-Enhanced Adaptive NVAR Framework for High-Resolution Sea Surface Temperature Forecasting in the East Sea
arXiv · 12 iun. 2026
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · 21 mai 2026
A Mechanism-Coupled Split Window Network for Medium- to High-Resolution Land Surface Temperature Retrieval
arXiv · 8 iun. 2026
News
Quantum Computing Report · 25 iul. 2026