| Abstract: | In this communication, we evaluate the performance of the relevance vector machine (RVM) for the estimation of biophysical parameters from remote sensing data. For illustration purposes, we focus on the estimation of chlorophyll-a concentrations from remote sensing reflectance just above the ocean surface. A variety of bio-optical algorithms have been developed to relate measurements of ocean radiance to in situ concentrations of phytoplankton pigments, and ultimately most of these algorithms demonstrate the potential of quantifying chlorophyll-a concentrations accurately from multispectral satellite ocean color data. Both satellite-derived data and in situ measurements are subject to high levels of uncertainty. In this context, robust and stable non-linear regression methods that provide inverse models are desirable.Lately, the use of the support vector regression (SVR) has produced good results in inversion problems, improving state-of-the-art neural networks. However, the SVR has some deficiencies, which could be theoretically alleviated by the RVM. In this paper, performance of the RVM is evaluated in terms of accuracy and bias of the estimations, sparseness of the solutions, robustness to low number of training samples, and computational burden. In addition, some theoretical issues are discussed, such as the sensitivity to training parameters setting, kernel selection, and confidence intervals on the predictions.Results suggest that RVMs offer an excellent trade-off between accuracy and sparsity of the solution, and become less sensitive to the selection of the free parameters. A novel formulation of the RVM that incorporates prior knowledge of the problem is presented and successfully tested, providing better results than standard RVM formulations, SVRs, neural networks, and classical bio-optical models for SeaWIFS, such as Morel, CalCOFI and OC2/OC4 models. |
