An Integer Linear Programming Model to Select and Temporally Allocate Resources for Fighting Forest Fires

Rodríguez-Veiga, Jorge; Ginzo‐Villamayor, María José; Casas-Méndez, Balbina

doi:10.3390/f9100583

Cited by 19 publications

(10 citation statements)

References 12 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The necessity of the ARs is ignored in this model. Rodríguez-Veiga et al [13] proposed a MILP (Mix Integer Linear Programming) model that optimally selects resources (ARs, brigades, and engines) for extinguishing a fire in different time periods during the planning period. They carried out a simulation study to obtain the optimal solution.…”

Section: Literature Reviewmentioning

confidence: 99%

A greedy heuristic algorithm to solve a VRP-based model for planning and coordinating multiple resources in emergency response to bushfires

2022

View full text Add to dashboard Cite

Uncoordinated responses are problematic in various operations, especially in crucial circumstances such as bushfires, where they are associated with decreased efficiency, effectiveness, and safety. This paper presents a new VRP (Vehicle Routing Problem) model for routing, scheduling, and coordinating bushfire-related resources including Ground Resources (GR) and Aerial Resources (AR) in the suppression phase of a bushfire event. The coordination must be in a way that ARs' operations are allowed prior to GRs' operations, otherwise, aerial interference is unhelpful. The problem is NP-hard (Non-deterministic Polynomial-time) and cannot be solved in a Polynomial-time using exact methods, but due to the crucial circumstances of bushfires, it should be solved in a reasonable time. Therefore, we proposed a greedy heuristic algorithm to solve it. Dividing bushfires' area into a set of fire sites, we solved instances with different numbers of fire sites using both CPLEX and the greedy algorithm and compared the results. CPLEX fails to solve the instances having more than three fire sites, but the greedy algorithm solves the largest instance having 9 fire sites in less than 1 minute. The ignorable Relative Percent Difference (RPD) of the greedy algorithm in the first five instances indicates that our proposed algorithm is reliable.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A greedy heuristic algorithm to solve a VRP-based model for planning and coordinating multiple resources in emergency response to bushfires

2022

View full text Add to dashboard Cite

show abstract

“…Several studies on wildfires have applied simulation and optimisation approaches to determine how to allocate resources of various types. Their aim has been to support preparatory emergency response planning to facilitate firefighting operations that are as effective as possible in the event of a wildfire (Lan et al, 2011;Rodríguez-Veiga et al, 2018). Many studies have focused on preparatory emergency response in terms of, for instance, where to place airplanes for fire extinguishing in advance to reduce stand-by costs.…”

Section: Previous Researchmentioning

confidence: 99%

Choice of Airport in Extinguishing Wildfires: Model and Cases

Ekström

Grosse

2020

Proceedings of the 9th International Conference on Operations Research and Enterprise Systems

View full text Add to dashboard Cite

This paper develops a model to support the optimal choice of an airport as a base for the flying vehicles that are operated to extinguish wildfires and forest fires. Based on experiences from the two largest wildfires in Swedish history, this study models the optimisation as a balanced transportation problem. In both cases, the model selected the airport that is closest to the fire area. If the capacity of the chosen airport was insufficient to host all of the flying vehicles, then the model added a second airport which is also nearby the wildfire area. The cases demonstrate that the total cost of the operation is lower when the extinguishing work is concentrated in an area that has a short distance between the airport and the fire, the fuel depots and the pilots' accommodation. Improved access to relevant data in the context of crisis management by air could allow for the inclusion of additional parameters and correct data in the optimisation model, which could in turn provide more comprehensive decision-making support.

show abstract

“…The traditional method for rating wildfire scale is based on the size of the burned area [39]. However, we propose a more meaningful definition of scale that encompasses not only the size of the burned area but also the fire's duration [40]. The basic statistical descriptions of the dataset variables are given in Table 4.…”

Section: B Multi-collinearity Test and Data Feature Normalizationmentioning

confidence: 99%

A Neural Network Model for Wildfire Scale Prediction Using Meteorological Factors

2019

View full text Add to dashboard Cite

A forest fire is a natural disaster that destroys forest resources, thus having a severe impact on humans and on the animals and plants that depend on the forest environment. This paper presents a model for predicting the scale of forest wildfires of Alberta, Canada. A fire's scale is determined by the combination of the fire's duration and the size of the area it burns. Our prediction model enables fire rescuers to take appropriate measures to minimize damage caused by a wildfire based on its predicted scale in the fire's early stages. The modeling data were collected from the Canada National Fire Database (CNFDB) published by Natural Resources Canada, which includes wildfire and meteorological data for Alberta, Canada. The size of the burned area and the fire's duration were used to estimate the scale of a wildfire. After multicollinearity testing and feature normalization, the data were divided into training and testing sets. Taking the meteorological factors as input values, a backpropagation neural network (BPNN), a recurrent neural network (RNN), and long short-term memory (LSTM) were implemented to establish prediction models. Of these classification methods, LSTM exhibited the highest accuracy, 90.9%. The results indicate that it is feasible to predict the scale of a forest wildfire at the beginning of its occurrence using meteorological information.

show abstract

An Integer Linear Programming Model to Select and Temporally Allocate Resources for Fighting Forest Fires

Cited by 19 publications

References 12 publications

A greedy heuristic algorithm to solve a VRP-based model for planning and coordinating multiple resources in emergency response to bushfires

A greedy heuristic algorithm to solve a VRP-based model for planning and coordinating multiple resources in emergency response to bushfires

Choice of Airport in Extinguishing Wildfires: Model and Cases

A Neural Network Model for Wildfire Scale Prediction Using Meteorological Factors

Contact Info

Product

Resources

About