Academic Journal
View in EDS

Cross-dataset benchmarking of machine learning models for marine and atmospheric environmental prediction.

Bibliographic Details
Title: Cross-dataset benchmarking of machine learning models for marine and atmospheric environmental prediction.
Authors: Zhou X; School of Computer Science and Engineering, North China Institute of Aerospace Engineering, Langfang, China., Zhang H; School of Computer Science and Engineering, North China Institute of Aerospace Engineering, Langfang, China., Du T; School of Computer Science and Engineering, North China Institute of Aerospace Engineering, Langfang, China., Yuan Q; College of Intelligence and Computing, Tianjin University, Tianjin, China., Wang H; School of Computer Science and Engineering, North China Institute of Aerospace Engineering, Langfang, China.
Source: PloS one [PLoS One] 2026 Jun 12; Vol. 21 (6), pp. e0351325. Date of Electronic Publication: 2026 Jun 12 (Print Publication: 2026).
Publication Type: Journal Article
Language: English
Journal Info: Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE
Imprint Name(s): Original Publication: San Francisco, CA : Public Library of Science
MeSH Terms: Atmosphere*/analysis , Environmental Monitoring*/methods , Machine Learning* , Oceans and Seas*, Benchmarking ; Ecosystem ; Prediction Algorithms ; Predictive Learning Models ; Wind
Abstract: Accurate prediction of marine and atmospheric environmental variables is important for climate adaptation, ecosystem management, and operational decision-making, yet practitioners still lack clear guidance on which machine-learning models are reliable across heterogeneous environmental tasks. We therefore developed a unified, leakage-aware benchmark across nine datasets, of which seven passed quality checks for modeling, spanning chlorophyll-a, wind speed, hydrographic observations, biotoxins, and bathymetry, and compared representative linear, tree-based, and sequence models under a common evaluation framework. Results show strong heterogeneity across tasks and model classes: tree ensembles are robust baselines for tabular problems, LSTM-based recurrent sequence modeling is most useful when temporal structure is central, and predictive skill depends more on target structure and covariate quality than on model complexity alone. Within the observational settings represented in this benchmark-predominantly Chinese coastal/estuarine and regional marine datasets, plus one atmospheric reanalysis wind task and one global cast archive-quality-controlled chlorophyll-a is comparatively predictable, whereas event-driven biotoxins and bathymetry inversion remain difficult under the current predictors. These findings provide practical guidance for researchers and environmental monitoring practitioners working in similar data regimes, but they should not be assumed to transfer automatically to untested regions such as the North Atlantic, the Mediterranean, or tropical open-ocean systems without further validation.
(Copyright: © 2026 Zhou et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
Competing Interests: The authors have declared that no competing interests exist.
References: J Environ Manage. 2025 Apr;380:125007. (PMID: 40101494)
Nature. 2015 May 28;521(7553):436-44. (PMID: 26017442)
Phys Rev Lett. 2002 Apr 29;88(17):174102. (PMID: 12005759)
J Mar Syst. 2009 Feb 20;76(1-2):4-15. (PMID: 28366997)
Sci Rep. 2025 May 5;15(1):15650. (PMID: 40325114)
Mar Environ Res. 2025 Aug;209:107170. (PMID: 40300328)
Sci Rep. 2025 Aug 28;15(1):31729. (PMID: 40877313)
Nature. 2019 Feb;566(7743):195-204. (PMID: 30760912)
PeerJ. 2024 May 8;12:e17361. (PMID: 38737741)
Nat Commun. 2023 Dec 5;14(1):7701. (PMID: 38052808)
Sci Total Environ. 2021 Nov 25;797:149040. (PMID: 34311376)
Environ Sci Pollut Res Int. 2024 Oct;31(48):58505-58526. (PMID: 39316212)
J Environ Manage. 2022 Sep 15;318:115636. (PMID: 35777152)
J Environ Manage. 2025 May;382:125441. (PMID: 40254001)
Sci Rep. 2025 Sep 1;15(1):32178. (PMID: 40890334)
Entry Date(s): Date Created: 20260612 Date Completed: 20260612 Latest Revision: 20260813
Update Code: 20260813
PubMed Central ID: PMC13262816
DOI: 10.1371/journal.pone.0351325
PMID: 42284340
Database: MEDLINE
Description
ISSN:1932-6203
DOI:10.1371/journal.pone.0351325