Modeling of Ground Vehicle Infrared Radiation with ML Methods According to Seasonal Effects

This study compares Machine Learning (ML) models that represent the effect of seasonal changes on the infrared (IR) radiation of an operationally active ground vehicle. The temperature distribution on the vehicle surface is a critical parameter for detection and tracking and varies with seasonal effects. In this study, tank surface temperatures are calculated by Finite Element Method (FEM) analysis. The behavior of obtained dataset is modeled using various ML methods. In the modeling process, air temperature, surface temperature and solar load variables were used as inputs. Within the scope of the study, different ML methods were compared, the model with the best performance was determined, and the IR radiance was calculated using the temperature values predicted by this model.