Oak is a common species in Iran and the most important one in Zagros forests. Zagros forests play a crucial and influential role in Iran's water supply, soil conservation, and climate modification. Unfortunately, a significant part of those forests suffer from oak decline. Oak decline (or oak mortality) is a widespread phenomenon in oak forests worldwide, which has gained the attention of many researchers in forestry over the past decade. In Iran, this phenomenon was first observed in Zagros forests in 2013. Factors affecting oak decline and their mutual interactions are not identified, making understanding and modeling these processes challenging. Only a few studies have been performed about this phenomenon in Iran. Thus, we chose to determine the most influential parameters and find the best modeling method for oak decline in Iran, especially in Lorestan province. To find influential environmental variables, a related literature review was thoroughly investigated. Environmental parameters, including temperature, precipitation, elevation, slope, direction, soil type, and aerosol amount, were selected as basic influencing parameters. All parameters were then interpolated to produce raster data with 30-meter cell resolution. Four operators, multiplication, logarithm, hyperbolic transformations, and principal component analysis (PCA), were used to find the optimal combination of the parameters. A total of 385 different varieties of influencing parameters were produced using the operators mentioned above. The relation and weight of each parameter are unknown. Thus, Artificial Neural Networks were used to model the oak decline process. Three feed-forward artificial neural networks, including Back-propagation Neural Network (BP), Probabilistic neural network (PNN), and Support Vector Neural Network (SVNN), were selected as modeling methods. Then, 385 combinations of the influencing parameters were used in the models mentioned above. Ten thousand samples were randomly selected from the study area to train and evaluate each neural network. Seventy percent of these random samples were used to train, 15 percent to evaluate, and 15 percent to validate the models. Also, the cross-validation method was used to avoid overfitting of neural networks. Finally, 1155 created NN models were compared using the R parameter to find the best configuration for modeling oak decline and identifying the most influential environmental parameters in oak decline. Evaluating 1155 different networks indicated that the Probabilistic neural network (R=0.87) with six inputs, including 1) elevation, 2) slope, 3) direction, 4) aerosols, 5) soil type, and 6) principal component of temperature and precipitation, performed better than SVNN and BP in modeling oak decline. Moreover, using different combinations of influencing factors improved the results and increased the correlation coefficient (R) of optimal inputs by 0.05 compared to initial inputs. Thus, it can be concluded that an increased number of inputs does not necessarily guarantee a better performance. Furthermore, two principle parameters of temperature and perception are more significant in modeling drought stress than other parameters. Oak decline is a complicated phenomenon, and different factors contribute to its occurrence. The present study investigates all environmental parameters affecting oak decline through a comprehensive literature review. Results indicate the appropriate performance of probabilistic neural networks in modeling oak decline. Moreover, principal component analysis is considered a useful tool for modeling drought stress in oak trees. Due to these neural networks' different accuracy and precision, it is necessary to evaluate different configurations. For further research, it is suggested to use other parameters, such as distance from population centers, water table, age of oak trees, height, and characteristics of other nearby trees.