Remote-sensing based adaptive path planning for an aquatic platform to monitor water quality

This paper addresses issues inherent to the design of navigation planning and control systems required for adaptive monitoring of pollutants in inland waters. It proposes a new system for estimating water quality, in particular the chlorophyll-A concentration, by using satellite remote sensing data. The aim is to develop an intelligent model based on supervised learning, with the goal of improving the precision of the evaluation of chlorophyll-A concentration. To achieve this, we use an intelligent system based on statistical learning to classify the waters a priori, before estimating the chlorophyll-A concentration with neural network models. We therefore develop several models for the same surface of water, based on the spectral signature of the samples acquired in-situ. A control architecture is proposed to guide the trajectory of an aquatic platform to collect in-situ measurements It uses a multi-model classification/regression system to determine and forecast the spatial distribution of chlorophyll-A. At the same time, the proposed architecture features a cost optimizing path planner. Experimental results are presented to validate our approach using data collected on Lake Winnipeg in Canada.