ADAPTIVE PREDICTION OF WILDFIRE BEHAVIOR ON THE BASIS OF AEROSPACE MONITORING
Author(s): Nezhevenko Evgeny Semenovich, Kozik Viktor Ivanovich, Feoktistov Artem Sergeevich
Rubric: Methodological research
Release: 2014-1 (4)
Keywords: computer simulation, wildfire, recurrent neural network, data assimilation, Kalman filter
Annotation: A method of modeling a dynamic process on the Earth surface, for instance, a forest fire, with the use of a recurrent neural network is proposed. The learning process of the neural network, similar to the process of data assimilation in GIS technologies is described. A method of acceleration of neural network learning by using the Kalman filtration is proposed. The efficiency of its application is analyzed. The software implementation of the model based on fire recurrent neural network which simulate the process in real time is presented.
Bibliography: Nezhevenko EV.SE., Kozik VI.IV., Feoktistov AR.SE. ADAPTIVE PREDICTION OF WILDFIRE BEHAVIOR ON THE BASIS OF AEROSPACE MONITORING // Education Resources and Technologies. – 2014. – № 1 (4). – С. 377-384. doi: