Abstarct: Machine learning has gained special importance in the modern era and has found numerous applications. This branch of artificial intelligence, which is still in its early stages of development, plays a significant role in the advancement of modern technologies. Transport in disordered media, which is of high theoretical and practical importance in the field of organic electronic materials, is considered a novel area of application for machine learning. This research focuses on modeling charge and energy transport processes in disordered materials and presents a machine learning-baxsed algorithm that contributes to a better understanding of these processes. In this regard, transport characteristics have been precisely analyzed using a deep neural network. The effectiveness of this method is demonstrated by validating the concepts related to transport energy and the capability of dimensionality reduction. In this study, a deep neural network and a variational encoder-decoder architecture have been employed for a detailed analysis of transport characteristics. The main objective of this research is to develop a model for predicting transport behavior in disordered materials using deep learning, without relying on kinetic Monte Carlo simulations. To this end, data for training was first collected through Monte Carlo simulations and then used as input to the encoder-decoder network. With this method, key transport features were extracted and analyzed. The proposed architecture in this research is capable of automatically identifying essential data features and transforming them into a lower-dimensional space, enabling data dimensionality reduction and facilitating subsequent analyses. Additionally, the trained network can be considered as a substitute for Monte Carlo simulations, addressing issues related to the time-consuming nature and computational complexity of traditional simulations. Accordingly, it is hoped that the network and concepts presented in this study will provide effective tools for future research in deep learning and a better understanding of transport processes in disordered materials.