Every year, hundreds of fires occur in the forests and rangelands across the world and damage thousands hectare of trees, shrubs, and plants which cause environmental and economic damages. This study aims to establish a real time forest fire alert system for better forest management and monitoring in Golestan Province. In this study, in order to prepare fire hazard maps, the required layers were produced based on fire data in Golestan forests and MODIS sensor data. At first, the natural fire data was divided into two categories of training and test samples randomly. Then, the vegetation moisture stresses and greenness were considered using six indexes of NDVI, MSI, WDVI, OSAVI, GVMI and NDWI in natural fire area of training category on the day before fire occurrence and a long period of 15 years, and the risk threshold of the parameters was considered in addition to selecting the best spectral index of vegetation. Finally, the model output was validated for fire occurrences of the test category. The results showed the possibility of prediction of fire site before occurrence of fire with more than 80 percent accuracy.

Fire hazard is often mapped as a static conditional probability of fire characteristics’ occurrence. We developed a dynamic product for operational risk management to forecast the probability of occurrence of fire radiative power in the locally possible near-maximum fire intensity range. We applied standard machine learning techniques to remotely sensed data. We used a block maxima approach to sample the most extreme fire radiative power (FRP) MODIS retrievals in free-burning fuels for each fire season between 2001 and 2020 and associated weather, fuel, and topography features in northwestern south America. We used the random forest algorithm for both classification and regression, implementing the backward stepwise repression procedure. We solved the classification problem predicting the probability of occurrence of near-maximum wildfire intensity with 75% recall out-of-sample in ten annual test sets running time series cross validation, and 77% recall and 85% ROC-AUC out-of-sample in a twenty-fold cross-validation to gauge a realistic expectation of model performance in production. We solved the regression problem predicting FRP with 86% r² in-sample, but out-of-sample performance was unsatisfactory. Our model predicts well fatal and near-fatal incidents reported in Peru and Colombia out-of-sample in mountainous areas and unimodal fire regimes, the signal decays in bimodal fire regimes.

Fire accidents are one of the serious security threats facing the metro, and the accurate determination of the index system and weights for fire assessment in underground stations is the key to conducting fire hazard assessment. Among them, the type and quantity of baggage, which varies with the number of passengers, is an important factor affecting the fire hazard assessment. This study is based on the combination of subjective and objective AHP (Analytic Hierarchy Process) with the available Particle Swarm Optimisation algorithm PSO (Particle Swarm Optimization) and the perfect CRITIC (Criteria Importance Through Intercriteria Correlation) empowered fuzzy evaluation method on the metro station fire hazard toughness indicator system and its weights were determined, and a fuzzy comprehensive evaluation model of metro station safety toughness under the influence of baggage was constructed. The practical application proves that the method provides a new perspective for the fire risk assessment of underground stations, and also provides a theoretical basis for the prevention and control of mobile fire load hazards in underground stations.

Underground station passenger flow is large, the number of parcels carried by passengers is large and varied, and the parcels carried have an impact on the fire hazard and evacuation of the station. In order to determine the weights of the passenger luggage risk and environmental factor index system in the fire risk evaluation of underground stations in a more realistic way, an optimized and improved hierarchical analysis method for determining the judgement matrix is proposed, which improves the traditional nine-scaled method and adopts the three-scaled method for the four major categories of luggage, namely, handbags, rucksacks, portable power tools and trolley cases. The advantage of this method is that there is no need for consistency judgement in determining packages with a wide range of types and uncertain contents, thus simplifying the calculation. Meanwhile, the reasonableness and reliability of the method is verified by combining it with an actual metro station fire risk assessment system.