Water Quality Monitoring Using Remote Sensing and an Artificial Neural Network

Abstract

In remotely located watersheds or large waterbodies, monitoring water quality parameters is often not feasible because of high costs and site inaccessibility. A cost-effective remote sensing-based methodology was developed to predict water quality parameters over a large and logistically difficult area. Landsat spectral data were used as a proxy, and a neural network model was developed to quantify water quality parameters, namely chlorophyll-a, turbidity, and phosphorus before and after ecosystem restoration and during the wet and dry seasons. The results demonstrate that the developed neural network model provided an excellent relationship between the observed and simulated water quality parameters. These correlated for a specific region in the greater Florida Everglades at R2 > 0.95 in 1998–1999 and in 2009–2010 (dry and wet seasons). Moreover, the root mean square error values for phosphorus, turbidity, and chlorophyll-a were below 0.03 mg L−1, 0.5 NTU, and 0.17 mg m−3, respectively, at the neural network training and validation phases. Using the developed methodology, the trends for temporal and spatial dynamics of the selected water quality parameters were investigated. In addition, the amounts of phosphorus and chlorophyll-a stored in the water column were calculated demonstrating the usefulness of this methodology to predict water quality parameters in complex ecosystems.