Prediction and management system for forest fires based on hybrid flower pollination optimization algorithm and adaptive neuro-fuzzy inference system

Natural disasters are the most dangerous events that always threaten our planet that may lead to destroying the human civilization and wildlife, so the early detection will help in avoiding, reducing and managing the wild effects on people, places, and animals. Forest fires are natural disasters which happen cause of the climate changes. This paper presents a prediction and management system for forest fires based on hybrid flower pollination optimization algorithm (FPO) and Adaptive Neuro-Fuzzy Inference System (ANFIS). FPO is applied to optimize the training parameters of ANFIS to get better prediction results. The proposed system is compared with three well-known algorithms (i.e. Genetic algorithm with ANFIS (GA-ANFIS), Particle Swarm Optimization with ANFIS (PSO-ANFIS) and basic ANFIS) using six data sets to evaluate the accuracy of the proposed system then it is evaluated over forest fires data set. The experiments results proved that the FPO-ANFIS achieved better forecasting results than other approaches.