Comparative evaluation of deterministic and Bayesian neural networks for chlorophyll-a time series forecasting in eutrophic lakes: A case study of Dianchi Lake, China
Environmental Research · 2026-09 · 306 · 125082
DOI: 10.1016/j.envres.2026.125082 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Environmental Research, 2026-09. Verfasst von Jiafan Yang und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Environment and Climate, Jinan University, Guangzhou, 511443, China. Hauptthemen laut MEDLINE: Lakes, Neural Networks, Computer, Environmental Monitoring, Eutrophication. Die Arbeit nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Reliable forecasting of chlorophyll-a concentration is essential for early warning of harmful algal blooms in eutrophic lakes. However, most deep learning approaches provide only deterministic point estimates without quantifying predictive uncertainty. This study compared four neural network architectures (MLP, LSTM, and their Bayesian variants via Monte Carlo dropout) for multi-step chlorophyll-a forecasting in Dianchi Lake, China. Models were trained on 1461 daily observations of eight physicochemical variables (seven environmental predictors plus chlorophyll-a) spanning 2022 to 2025. The dataset was chronologically split into 70% training and 30% testing, with the final 20% of the training set withheld as a validation set. Bayesian-LSTM achieved the best performance across all forecast horizons, maintaining R2=0.678 at 7-day lead time while producing calibrated uncertainty estimates. Predictive uncertainty decomposition revealed a systematic shift from epistemic-dominated uncertainty at short lead times to aleatoric-dominated uncertainty at longer horizons. This shift highlights distinct management pathways: improving short-term forecasts via denser monitoring data versus addressing irreducible stochasticity for longer horizons. These findings demonstrate that integrating recurrent networks with MC dropout offers a practical, uncertainty-aware framework for probabilistic water quality forecasting in eutrophic lakes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- College of Environment and Climate, Jinan University, Guangzhou, 511443, China.
- College of the Environment and Ecology, Xiamen University, Xiamen, 361102, China.
- Tianjin Municipal Engineering Design & Research Institute Co., LTD, Tianjin, 300392, China. Electronic address: liyong_tmedi@163.com.
- College of the Environment and Ecology, Xiamen University, Xiamen, 361102, China. Electronic address: liangzhongyao@xmu.edu.cn.
- College of Environmental Sciences and Engineering, State Environmental Protection Key Laboratory of All Material Fluxes in River Ecosystems, Institute of Tibetan Plateau, Peking University, Beijing, 100871, China.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Yang, J., Huang, Y., Zhu, Z., Li, Y., Liang, Z., & Liu, Y. (2026). Comparative evaluation of deterministic and Bayesian neural networks for chlorophyll-a time series forecasting in eutrophic lakes: A case study of Dianchi Lake, China. Environmental Research, 306, 125082. https://doi.org/10.1016/j.envres.2026.125082
Vancouver
Yang J, Huang Y, Zhu Z, Li Y, Liang Z, Liu Y. Comparative evaluation of deterministic and Bayesian neural networks for chlorophyll-a time series forecasting in eutrophic lakes: A case study of Dianchi Lake, China. Environmental Research. 2026;306:125082. doi:10.1016/j.envres.2026.125082
BibTeX
@article{Yang2026,
author = {Yang, Jiafan and Huang, Yusheng and Zhu, Zihao and Li, Yong and Liang, Zhongyao and Liu, Yong},
title = {Comparative evaluation of deterministic and Bayesian neural networks for chlorophyll-a time series forecasting in eutrophic lakes: A case study of Dianchi Lake, China},
journal = {Environmental Research},
year = {2026},
volume = {306},
pages = {125082},
doi = {10.1016/j.envres.2026.125082}
}
EUVIMED