Machine-Learning Methods Applied to Water-Cycle Processes
Special Issue Information
Dear colleagues,
Machine-learning methods have rapidly gained popularity as a tool for solving complex problems in a variety of fields, such as the ones related to forest processes. The development of deep-learning models and computational resources has spurred studies in multispectral imagery from satellites, Unmanned Aerial Vehicles, and other remote sensing sources. Machine-learning, which is a sub-category of the field of Stochastics, can be applied to process simulations, pattern recognition, classification tasks, and prognosis methods. This versatility leads to interdisciplinary research in various areas of forest research, such as hydrometeorological modeling, as well as water, food, and energy cycle assessments (i.e., known as the water-food-energy nexus), but also species distribution simulation, wildfire and pest hazard assessments. This Special Issue focuses on all processes related to the water-cycle, sustainable forestry, and stochastic methods, with focus on the machine-learning algorithms.
Dr. Panayiotis Dimitriadis
Guest Editor