Cross-dataset benchmarking of machine learning models for marine and atmospheric environmental prediction
PLOS One · 12.06.2026 · 21 (6) · e0351325
DOI: 10.1371/journal.pone.0351325 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 12.06.2026. Verfasst von Xuehua Zhou und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, North China Institute of Aerospace Engineering, Langfang, China. Hauptthemen laut MEDLINE: Atmosphere, Environmental Monitoring, Machine Learning, Oceans and Seas. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: North China Institute of Aerospace Engineering, Science Research Project of Hebei Education Department.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Computer Science and Engineering, North China Institute of Aerospace Engineering, Langfang, China.
- College of Intelligence and Computing, Tianjin University, Tianjin, China.
ORCID-Profile: Hanming Zhang, Huijuan Wang
Förderung
- North China Institute of Aerospace Engineering
- Science Research Project of Hebei Education Department
Zitieren
APA
Zhou, X., Zhang, H., Du, T., Yuan, Q., & Wang, H. (2026). Cross-dataset benchmarking of machine learning models for marine and atmospheric environmental prediction. PLOS One, 21(6), e0351325. https://doi.org/10.1371/journal.pone.0351325
Vancouver
Zhou X, Zhang H, Du T, Yuan Q, Wang H. Cross-dataset benchmarking of machine learning models for marine and atmospheric environmental prediction. PLOS One. 2026;21(6):e0351325. doi:10.1371/journal.pone.0351325
BibTeX
@article{Zhou2026,
author = {Zhou, Xuehua and Zhang, Hanming and Du, Tiantian and Yuan, Quanbo and Wang, Huijuan},
title = {Cross-dataset benchmarking of machine learning models for marine and atmospheric environmental prediction},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {6},
pages = {e0351325},
doi = {10.1371/journal.pone.0351325}
}
EUVIMED