Water clarity in Brazilian water assessed using Sentinel-2 and machine learning methods

Secchi Disk Depth (Z(sd)) is one of the widely used water quality measurements. Controlled by variations in Optically Active Constituents, it is a key index of overall water quality. In-situ measurements of Z(sd) lacks spatiotemporal coverage which could be solved using remote sensing data, such as from the Sentinel-2/MSI. However, inland waters have highly variable optical properties, and that is still a challenge for the state-of-art algorithms of Z(sd) retrieval. One of the most promising approaches for dealing with this challenge is the use of Machine Learning methods. Moreover, predicting Z(sd) for large areas using high-resolution remote sensing imagery requires a high computational effort, which could be solved using Cloud-Computing platforms. Therefore, this study evaluates the use of Machine Learning (Random Forest, Extreme Gradient Boosting, and Support Vector Machines) and Semi-Analytical algorithms (SAA) for Z(sd) retrieval focused on Sentinel-2 imageries available in the Google Earth Engine platform to assess the clarity of the Brazilian inland waters. Machine Learning methods were calibrated and validated using a comprehensive dataset (N = 1492) collected in the last 20 years in Brazil. The results were compared with semi-analytical approaches. After evaluation with in-situ data, the best algorithm was implemented in the Google Earth Engine platform to generate Z(sd) maps. The calibration with in-situ data demonstrated that the Machine Learning methods outperform the SAA, with the Random Forest presenting the best results (errors lower than 22%). The results showed that when SAA were applied to the environment in which they were calibrated, the results were closer to that of machine learning methods, indicating that SAA could also be used for Z(sd) retrieval. The application of Random Forest to the Sentinel-2 atmospherically corrected imagery had errors of 28%, demonstrating the feasibility of the algorithm and atmospheric correction methods for predicting Z(sd). (AU)