A Hybrid Intelligence System Based on Relevance Vector Machines and Imperialist Competitive Optimization for Modelling Forest Fire Danger Using GIS

摘要

This article proposes and verifies a novel intelligence approach for modelling forest fire danger developed based on a hybrid model of Imperialist Competitive Algorithm (ICA) and Relevance Vector Machine (RVM). The hybrid model is named as ICA-RVM. They are state-of-the-art machine learning techniques that have not been investigated for forest fire danger modeling. RVM is used to establish a prediction model that computes probability of fire danger, whereas ICA is adopted to optimize the predict ion model. The tropical forest at Gia Lai province, Central Highland (Vietnam), was used as a case study. A geographic information system (GIS) database featuring 12 fire ignition factors has been established to train and verify the hybrid intelligence model. Area under the curve (AUC) and statistical measures were used to assess the model performance. The result showed that the proposed model achieves high performances; AUC is 0.842 and 0.793 on the training dataset and the validation dataset, respectively. Compared to two benchmarks, Random Forests and Support Vector Machine, the proposed model performs better. Therefore, the propose ICA-RVM is a valid alternative system for forest fire danger modeling.