Global Lake Monitoring using Group-specific Local Learning

Abstract

Global lake monitoring is crucial for the effective management of water resources as well as for conducting studies that link the impact of lake dynamics on climate change. Remote sensing datasets offer an opportunity for global lake monitoring by providing discriminatory features that can help distinguish land and water bodies at a global scale and in a timely fashion. A major challenge in global lake monitoring using remote sensing datasets is the presence of a rich variety in the land and water bodies at a global scale, motivating the need for local learning algorithms that can take into account the heterogeneity in the data. We propose a novel group-specific local learning scheme that uses information about the local neighborhood of a group of test instances for estimating the relevant context for classification. By comparing the performance of the proposed scheme with baseline approaches over 180 lakes from diverse regions of the world, we are able to demonstrate that the proposed scheme provides significant improvements in the classification performance.