On the estimation of tree mortality and liana infestation using a deep self-encoding network

Abstract Global environmental change leads to the variation in the relative coverage of dead trees, liana-infested and non-liana-infested trees in many tropical forests. Increase in the coverage of lianas had adverse effects on forested ecosystems such as decreasing tree growth rates and increasing tree mortality. This paper proposes a classification framework that integrates unmanned aerial vehicle systems (UAVs)-derived multi-spectral images and a Deep self-encoding network (DSEN) with the goal of monitoring and quantifying the relative coverage of dead trees, liana-infested, and non-liana-infested trees at high spatial scales. Today's UAVs-derived multi-spectral images provide the much necessary high resolution/quality data to monitor ecosystem-level processes at low cost and on demand. On the other hand, DSEN, a state-of-the-art classification approach that uses multiple layers to exploit abstract, invariant features from input data, has been proved to have the ability to acquire excellent results. This new classification framework, implemented at a tropical Dry Forest site in Costa Rica, provided accurate estimations of the relative coverage of dead trees, liana-infested trees, non-liana-infested trees, and non-forests. The approach opens the door to start exploring linkages between a booming UAVS industry and machine learning/Deep learning classifiers.