Monitoring water quality parameters of freshwater aquaculture ponds using UAV-based multispectral images

• Published in: Ecological indicators 2024-10, Vol.167, p.112644, Article 112644
• Main Authors: Liu, Xingyu, Wang, Yancang, Chen, Tianen, Gu, Xiaohe, Zhang, Lan, Li, Xuqing, Tang, Ruiyin, He, Yuejun, Chen, Guangxin, Zhang, Baoyuan
• Format: Article
• Language: English
• Subjects: Freshwater aquaculture; Stacking learning; UAV; Water quality
• ISSN: 1470-160X
• DOI: 10.1016/j.ecolind.2024.112644

•The Stacking model can quickly and accurately estimate Chl-a and Turbidity.•Stacking models perform better than single machine learning models.•UAV-based multispectral imaging performs well to monitor water quality in aquaculture.•Successfully mapped the spatial and temporal distribution of Chl-a and Turbidity. Monitoring water quality is crucial for water exchange, precise feeding, and quality control of water products in freshwater aquaculture. In light of the issue of spatial heterogeneity in freshwater aquaculture pond waters and the constraints of conventional sensor detection techniques and traditional machine learning models. In this study, UAV multispectral images were combined with four machine learning algorithms (Ridge, XGBoost, CatBoost, RF) and the Stacking model to model the estimation of Chlorophyll a (Chl-a) and Turbidity and map their spatial distribution. The findings indicate that, in contrast to machine learning models, the Stacking model of water quality parameter performs better with higher accuracy. Meanwhile,for Chl-a and Turbidity the optimal sub-model combination in the Stacking model varies, with the most effective estimation model for Chl-a concentration identified as RF-XGB-Ridge (R2 = 0.84, RMSE=1.882 µg/L, MAE=3.433 µg/L and Slope = 0.791). As to Turbidity, the RF-CAB-Ridge model demonstrates superior performance, with macro-averaged precision (macro-p) of 93.3 %, macro-averaged recall (macro-R) of 88.8 %, macro-averaged F1-score (macro-F1) of 0.895, and Kappa coefficient of 0.813. Furthermore, the results of the joint analyses, which included measured samples and management measures at the test site, demonstrated that the spatial distribution maps of Chl-a and Turbidity were in alignment with the current status of water quality at the test site. This consistency was observed across both temporal and spatial scales. The results demonstrate that the integration of UAV multispectral images with the Stacking model can enhance the precision of water quality parameter models, facilitates the examination of the spatial and temporal distribution of water quality parameters and the underlying influencing factors, and advances the capability for dynamic monitoring of water quality parameters in freshwater aquaculture regions. Concurrently, it offers fundamental theoretical and methodological assistance for the precise regulation of water quality in freshwater aquaculture ponds and the formulation of optimal production management stra