An enhanced deep learning approach to assessing inland lake water quality and its response to climate and anthropogenic factors

• Published in: Journal of hydrology (Amsterdam) Vol. 620; p. 129466
• Main Authors: Guo, Hongwei, Zhu, Xiaotong, Jeanne Huang, Jinhui, Zhang, Zijie, Tian, Shang, Chen, Yiheng
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.05.2023
• Subjects: Deep learning; Landsat; Remote sensing; Sentinel-2; Water quality; Deep learning; Remote sensing; Water quality; Landsat; Sentinel-2
• ISSN: 0022-1694; 1879-2707
• DOI: 10.1016/j.jhydrol.2023.129466

[Display omitted] •An enhanced deep learning approach was proposed to remotely assess water quality.•The approach outperformed other candidate algorithms in water quality mapping.•Merged OLI/MSI data supports water quality detecting with repeat cycle <3 days.•Model physical interpretability was explored to split the estimating interactions.•Impacts of 12 natural and anthropogenic factors on water quality were clarified. Remote sensing has long been used for inland water quality monitoring. However, due to the complex correlation between water quality parameters (WQPs) and water optical properties, the interactions of WQPs, and the impacts of climate, using remote sensing reflectance (Rrs) to adequately estimate WQPs is still a grand challenge. Deep learning has the potential in capturing the correlation among Rrs, optically active constituents (OACs), and non-OACs, and is progressively used in remote sensing retrieval of inland water quality. In this study, the enhanced multimodal deep learning (EMDL) models were proposed for Chlorophyll-a, total phosphorous, total nitrogen, Secchi disk depth, dissolved organic carbon, and dissolved oxygen retrieval in Lake Simcoe (80 km north of Toronto, Canada). The EMDL models were developed and validated using the Rrs data derived from the harmonized Landsat and Sentinel-2 images, synchronized water quality measurements, water surface temperature, and climate data (N = 1173). The performance of the EMDL models was compared to that of several other machine learning, deep learning, and empirical models. Using the developed EMDL models, the spatial distributions and long-term variations of the WQPs in Lake Simcoe from 2013 to 2019 were reconstructed. The impacts of 12 potential natural and anthropogenic factors on the water quality of the entire Lake Simcoe and its two most concerned estuaries were also quantitatively discussed. The results showed that the EMDL models produced satisfactory performance in estimation of the six WQPs, with the Slope being close to 1 (0.84–0.95), normalized mean absolute error ≤20.17%, and Bias ≤14.68%. The EMDL models had the potential to reconstruct the spatial patterns and time-series dynamics of water quality and effectively detect the gradients of spatial patterns. This study provides a novel approach to supporting the environmental management and identification of the affecting factors for the Lake Simcoe watershed.