The rapid development of machine learning and data analysis techniques observed in recent years can affect numerous aspects of environmental management decision-making. With the advent of remote sensing and continuous monitoring techniques, big data is already contributing to areas such as weather forecasting, environmental sustainability assessment, and disaster management. The main goal of this study is to elucidate the basic concepts of applying machine learning methods to decision support tasks in conservation management, and to discuss methods for improving the efficiency of processing and extracting knowledge from environmental monitoring data. In particular, the capabilities of Cascade ARTMAP, a self-organizing neural network system for rule production and discovery, are analyzed in this vein.

Keywords: environmental monitoring, neural network, machine learning, adaptive resonance theory, ARTMAP, rule extraction