Key points are not available for this paper at this time.
Early and reliable detection of land degradation helps policymakers to take strict action in more vulnerable areas by making strong rules and regulations in order to achieve sustainable land management and conservation. The detection of land degradation is carried out to identify desertification processes using machine learning techniques in different geographical locations, which are always a challenging issue in the global field. Due to the significance of the detection of land degradation, this article provides an exhaustive review of the detection of land degradation using machine learning algorithms. Initially, the current status of land degradation in India is presented, along with a brief discussion on the overview of widely used factors, evaluation parameters, and algorithms used. Consequently, merits and demerits related to machine learning-based land degradation identification are presented. Additionally, solutions are prescribed in order to reduce existing problems in the detection of land degradation. Since one of the major objectives is to explore the future perspectives of machine learning-based land degradation detection, areas including the application of remote sensing, mapping, optimum features, and algorithms have been broadly discussed. Finally, based on a critical evaluation of existing related studies, the architecture of the machine learning-based desertification process has been proposed. This technology can fulfill the research challenges in the detection of land degradation and computation difficulties in the development of models for the detection of land degradation.
Hediyalad et al. (Mon,) studied this question.