Year: 2025
Type: software-paper
Abstract: Our oceans play a critical role in regulating the Earth's climate and sustaining local economies through fisheries and tourism (Dyck & Sumaila, 2010;Moreno & Amelung, 2009).However, the vast size of the ocean means that observations are inherently sparse, posing significant challenges to contextualizing these observations on a global scale (Hauck et al., 2023).Ensemble-based machine learning approaches offer an exciting avenue to address this challenge.However, the complexity of implementing these algorithms, combined with the need for extensive preprocessing and post-processing, highlights the necessity for efficient, reproducible numerical tools.Here we provide a Python package for training, predicting, and post-processing a machine learning ensemble to facilitate the global interpolation of sparse observational datasets, such as those from oceanographic cruises.
DOI: 10.21105/joss.08755
Institution: University of Bristol
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4415156104