Can multispectral information improve remotely sensed estimates of total suspended solids? A statistical study in Chesapeake Bay

Abstract

Total suspended solids (TSS) is an important environmental parameter to monitor in the Chesapeake Bay due to its effects on submerged aquatic vegetation, pathogen abundance, and habitat damage for other aquatic life. Chesapeake Bay is home to an extensive and continuous network of in situ water quality monitoring stations that include TSS measurements. Satellite remote sensing can address the limited spatial and temporal extent of in situ sampling and has proven to be a valuable tool for monitoring water quality in estuarine systems. Most algorithms that derive TSS concentration in estuarine environments from satellite ocean color sensors utilize only the red and near-infrared bands due to the observed correlation with TSS concentration. In this study, we investigate whether utilizing additional wavelengths from the Moderate Resolution Imaging Spectroradiometer (MODIS) as inputs to various statistical and machine learning models can improve satellite-derived TSS estimates in the Chesapeake Bay. After optimizing the best performing multispectral model, a Random Forest regression, we compare its results to those from a widely used single-band algorithm for the Chesapeake Bay. We find that the Random Forest model modestly outperforms the single-band algorithm on a holdout cross-validation dataset and offers particular advantages under high TSS conditions. We also find that both methods are similarly generalizable throughout various partitions of space and time. The multispectral Random Forest model is, however, more data intensive than the single band algorithm, so the objectives of the application will ultimately determine which method is more appropriate.