Home // COCE 2024, The First International Conference on Technologies for Marine and Coastal Ecosystems // View article

Physics-Regularized Buoy Forecasts: A Multi-Hyperparameter Approach Using Bounded Random Search

Authors:
Austin Schmidt
Pujan Pokhrel
Md Meftahul Ferdaus
Mahdi Abdelguerfi
Elias Ioup
David Dobson

Keywords: Surrogate; HYCOM; ERA5; Deep Learning; GRU.

Abstract:
One challenge in oceanographic analysis is the need for accurate initial conditions collected from physical buoys. Temporary sensor outages or noisy conditions can hinder the data collection process. Machine learning surrogate models offer short-term coverage during outages. This study presents a methodology for regularizing machine learning models that predict buoy observations by utilizing multiple data sources. A previous work introduced a ratio-coupling hyperparameter to combine numerically modeled data and ocean observations when calculating training loss. However, applying one ratio across all features failed to capture the unique characteristics of different data sources. To overcome this limitation, this work investigates a multiple-hyperparameter loss function to independently manage the contribution of each data source per feature. A bounded random grid search explores the hyperparameter space to find ratios which produce superior results compared to the single-ratio approach. Surrogate models are validated at the same 88 fixed locations as the previous paper for a direct comparison. The experimental results suggest that this multi-ratio methodology can offer more reliable forecasts over a 24-hour period by applying the correct weight for each pairing of observed feature and numerical model source.

Pages: 14 to 22

Copyright: Copyright (c) IARIA, 2024

Publication date: November 17, 2024

Published in: conference

ISBN: 978-1-68558-325-5

Location: Valencia, Spain

Dates: from November 17, 2024 to November 21, 2024