Abstract
Algal blooms have become a critical environmental issue worldwide, with chlorophyll-a (Chl-a) serving as a key biological indicator for assessing bloom intensity and providing essential insights into bloom dynamics. Based on four field investigations conducted in the Danjiangkou Reservoir between 2023 and 2024, this study utilized data on Chl-a, nutrients (total nitrogen, total phosphorus, ammonia nitrogen, etc.), water temperature, and light intensity to develop a Chl-a concentration prediction model using the XGBoost algorithm. The Shapley Additive Explanations method was further employed to quantitatively evaluate the relative contributions of environmental variables to Chl-a in the Danjiangkou Reservoir area and the Hanjiang Reservoir area. The results showed that the XGBoost model achieved high accuracy in modeling Chl-a concentrations (R2 > 0.8). In the Hanjiang Reservoir, water temperature and light intensity were identified as the dominant factors influencing Chl-a, together accounting for over 58% of its variation, highlighting the leading role of physical conditions in algal growth. In contrast, in the Danjiang Reservoir, water temperature, total phosphorus, and ammonia nitrogen were the primary drivers, jointly contributing approximately 62.2%, indicating a stronger influence of nutrient availability. This study elucidates the major environmental drivers affecting Chl-a levels in the Danjiangkou Reservoir and provides important implications for safeguarding water quality in the water source area of the South-to-North Water Diversion Project.
Funding
This research was financially support by the Major Science and Technology Project of the Ministry of Water Resources (SKS-2022058), and Basic Research Project of China Institute of Water Resources and Hydropower Research (WE110145B0032023).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
Reprints and permissions
About this article
Cite this article
Sun, W., Wu, W., Liu, X. et al. Identifying the key environmental drivers of chlorophyll-a in the Danjiangkou reservoir using interpretable machine learning.
Sci Rep (2026). https://doi.org/10.1038/s41598-026-49236-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-49236-1
Keywords
- Eutrophication
- Machine-learning
- Shapley additive explanations
- Chlorophyll-a
- Danjiangkou reservoir
Source: Ecology - nature.com
