Sharif Digital Repository

Wildfires are complex phenomena with many indeterminate and highly unpredictable driving factors that have remained unresolved. During the last decade, machine learning methods have successfully excelled in wildfire prediction as an alternative to traditional field research methods by elucidating the relationship between historical wildfire events and various important variables. The main purpose of this research is to evaluate the random forest machine learning approach and the logistic regression statistical approach to prepare a wildfire susceptibility map using data related to historical wildfires and effective variables in the Okanogan region in Washington province of the United States... 

The simultaneous outbreak of multiple diseases within complex human societies, especially under synergistic interactions, poses significant challenges in statistical physics and dynamic system modeling. This thesis investigates self-organized criticality in models of two cooperating diseases integrated with the forest fire model. The primary objective is to identify and analyze critical features in complex systems influenced by the concurrent spread of multiple diseases with distinct transmission mechanisms. The proposed model extends existing frameworks by incorporating primary disease transmission probabilities p and cooperative transmission probabilities q, as well as the probability of... 

Fire behavior analysis and fire dynamics simulations, especially Wildfire, is of great importance due to all the necessities. The development and application of fire dynamics models, especially in complex geometric spaces, has become one of the priorities of the firefighting and environmental organizations of countries and international unions at the international level today. Analytical methods are not suitable for complex geometries due to the complexity of fire dynamics equations. Experimental methods are a desirable method for investigating complex geometries, but the fire phenomenon requires a high experimental study cost; Because fire causes severe damage or even destruction of a... 

Considerable damage is caused by wildfires to properties, wildlife, and human lives in Iran, as in other parts of the world. The northern regions face heightened risks due to high fuel loads exacerbated by global warming and drought. To evaluate the capability of the WRF-FIRE model, which integrates atmospheric and fire models, on regions where available data is limited, simulations were conducted for the wildfire that occurred in the Malekroud Forest in 2010. The fire domain utilized the Large Eddy Simulation (LES) mode, enhancing simulation accuracy and reliability. Various scenarios were designed to assess the model’s sensitivity to uncertainties such as fuel types, moisture content, and... 

This study focuses on path planning for a team of Unmanned Aerial Vehicles (UAVs) involved in efficiently searching a region for early wildfire detection. The primary goal of the path planning algorithm is to identify optimized search paths that maximize the likelihood of detecting wildfires. This optimization considers various factors, including UAV flight time constraints and the locations of the final bases. To improve the algorithm's performance, an initial phase incorporates the utilization of density-based clustering to eliminate noise within the probability map. Furthermore, centroid-based clustering is applied to mitigate the complexity of the optimization problem. Subsequently, an...