Abstract

With the increase in the number of forest fires worldwide, especially in the West of the United States, there is an urgent need to develop a reliable fire propagation model to aid fire fighting as well as save lives and resources. Wildfire spread simulation is used to predict possible fire behavior, which is essential in assisting fire management and training purposes. This paper proposed an agent-based model that simulates wildfire using a cellular automata approach. The proposed model incorporated a machine learning technique to automatically calculate the igniting probability without the need to manually adjust the input data for a specific location.

Software architecture diagram

The program includes three large components: the input service, the simulation model, and the output service.

The input service processes users inputs. The input includes diffusion coefficient, ambient temperature, ignition temperature, burn temperature, matrix size, and a wood density data set. All of the inputs can be set to default values if users choose not to provide data. The wood density data set can also be auto-generated if a real-world data set is not provided.

The simulation model is the most important component of the program. This part consists of two main parts, fire temperature simulation service and the wood density simulation service. As the names suggest, the fire temperature simulation service is responsible for processing how fire temperature changes throughout the simulation process. The wood density simulation service is in charge of processing the changes in wood density of the locations described in the input when fire passes through.

The final component, the output service, creates a graph at each time step, and puts together the graphs into a gif file. By using the gif file, users can visualize how fire spreads given the initial inputs.

Design Overview

Simulation Model

Link to the final version of the paper

https://drive.google.com/file/d/1d4UQhkRWoYSxDWYb5SY-lca6QLaZFJMZ/view?usp=sharing

Link to the final version of the software demonstration video (hosted on YouTube)

https://youtu.be/u7L3QIGLRFg

This past week, I spent time working on the presentation. I also met with Charlie to discuss the presentation slides. Charlie told me to replace a table in the Motivation section with graphs to show how wildfires have increased overtime. He also told me to cut down some texts in the Related Work sections. For the Proposed solution, he told me to redesign my graph. I also had to add more details in the Timeline and Budget sections. I also worked on the final paper during the break by adding the new requested sections. 

For this week I looked into many different datasets, including gis fire map data https://frap.fire.ca.gov/mapping/gis-data/ and Kaggle dataset https://www.kaggle.com/elikplim/forest-fires-data-set but couldn’t find what I was looking for.

I picked The Ranch Fire in California but couldn’t find good datasets for it. I was trying to find I’m trying to find elevation, wind direction, humidity, and vegetation. 
All of them have to contain coordinates so I can layer them together. Also, I need each set at different time stamps for the simulation. I will discuss this during the next weekly meeting.

For this week I have done the following tasks:

Learned to view shapefile contents with Netlogo and Python library pyshp. A shapefile is an Esri vector data storage format for storing the location, shape, and attributes of geographic features. This type of file is quite complicated so it took me sometimes to understand the format and its contents.

I had trouble finding the right dataset for my project. Charlie suggested that I look into https://www.frames.gov/afsc/partners/fmac/guides-products. I downloaded the data for Alaska but it does not have the contents that I was looking for. Finding the right data is currently a big challenge.

I am also getting more familiar with Netlogo. Using Netlogo, I could view the content of the data for Alaska and also extract the metadata using the command line provided with NetLogo.

This week I met with Charlie to discuss my project design. We also talked about GIS extension, which is a library to handle GIS data for NetLogo. Charlie talked about how to layer different types of data on a base map. The most important tasks for the upcoming weeks are to figure out how to find different types of data for a fire location and how to process the data.

For this week, I started working on NetLogo, the software that I plan to use to create the simulation model for my project. I looked into the tutorials and the sample models library. NetLogo has its own programming language and development environment, so I spent quite some time to study its ecosystem. I also created a simple simulation model that read a file containing elevation information, display the elevation in different shades of green, built some fire sources and let them spread to places where elevation was smaller than 500. All of my notes for NetLogo can be found in Box.

Charlie and I also discussed my design for the project. For now I will focus on four types of input: Wind, Elevation, Temperature, and Humidity. First I will explore them individually to see how each affects my model. Then I will combine them, two at a time, to explore their combined effect on the model.

I met with Charlie for the weekly meeting. We discussed different designs for my simulation model. I will first create some input data, which includes creating dummy values for the base map instead of using a real map. The main program will contain simple transition functions. This is to make sure that I can produce a simple version of a simulation model. I will also have to look more into NetLogo, especially into its fire model libraries.

I’ve finished writing the Literature Review for my idea “Fire Spread Simulation Using Cellular Automata.” After reading the papers for my research, I found a recent paper on this topic which used Machine Learning to solve the drawbacks of previous research. However, I could only find one paper using this technique so I will have to dig deeper to find more related materials. Charlie has suggested that I should categorize the papers based on the input data (terrain, weather condition, etc).

I’ve chosen “Fire Simulation Using Cellular Automata” as my final idea. I have also met with Charlie and decided to meet every week on Monday. I will also meet with Xunfei regularly for my research. Xunfei has suggested that I should look into ArcGIS for the simulation part of the research and also suggested me to talk to Jose as ArcGIS would require funding.

Here are my comments for the papers I read this week.

[1] Forest fires spread modeling using cellular automata approach.

They described a method using cellular automata to simulate how fire spread over an area of island Brac in Croatia. The paper had a great overview of Classification of forest fire models, explanation of cellular automata, well-known Neighborhood Templates, and how Landscapes can be represented as cellular automata. They mentioned that only vegetation characteristics and wind conditions were taken into account as input parameters. I might include more input data if I use this model.

[2] Computer vision system for fire detection and report using UAVs Special Issue for Submission.

The main concerns of the paper was how to detect fire using computer vision techniques as well as hardware systems. The paper serves as an explanation to their system rather than how their system is compared to other fire detection models. I might use this pa- per for my research if I want to establish a communication system later on.

[3] Using cellular automata to simulate wildfire propagation and to assist in fire management.

Unlike the cellular automaton mentioned in the other two papers, this one did not take into consideration the state of stress of vegetation and the meteorological condition. If it possible, I would like to develop a system that can output different simulations based on different cellular automata models based the ones in this paper and in the other two mentioned above.

[4]  An FPGA processor for modeling wildfire spreading.

The model was designed to not require too much computational resources and computational power so that it could describe fire behavior in real time. I might use this model if I want to design my simulation model in real time.

[5]  A Cellular Automata model for fire spreading prediction.

The result was a model of cells that evolve with given transition rules. This model forms the basic foundation my research. I can implement a similar model with these transition rules.

[6] Forest fire spread simulating model using cellular automaton with extreme learning machine Extracting Traffic Events and Human Mobility Patterns in Geosocial Media Data for Assessing Real-time Road Traffic View project Understanding human activity pattern.

They mentioned that the accuracy of this model was between 58.45 and 82.08%. I do not think a simulation accuracy of 58.45% is a reliable. This research also used cellular automaton to pre- dict fire propagation, which is similar to the paper ”Forest fire spread simulation algorithm based on cellular automata.”

Below are the papers I read for each idea this week. I also read more papers for my third idea, “Fire Spread Simulation” and found the cellular automata algorithm mentioned in one of the papers quite interesting. The basic idea behind the model is to break down the images of the forest fire into different cells and apply the same algorithms onto each cell, similar to divide and conquer. The authors have also developed an improved algorithm based on this model to not only predict how fire spreads but also trace the source of fire.

Improve Fire Identification Mapping and Monitoring Algorithm (FIMMA) 
[1]  Z. Li, W. Jiang, F. Wang, Q. Meng, X. Zheng, and B. Liu, “GIS based dynamic modeling of fire spread with heterogeneous cellular automation model and standardized emergency management protocol,” Proceedings of the 3rd ACM SIGSPATIAL International Workshop on the Use of GIS in Emergency Management, EM-GIS 2017, 2017.
[2]  X. Xie, J. Wang, H. Qin, and X. Cheng, “The simulation and research of fire spread situation based on osg,” ACM International Conference Proceeding Series, pp. 156–159, 2019.

Fire Detection Using A Combination of Different Image Analysis Techniques

[1]  L. Giglio, W. Schroeder, and C. O. Justice, “The collection 6 MODIS active fire detection algorithm and fire products,” Remote Sensing of Environment, vol. 178, pp. 31–41, jun 2016.
[2]  Y. Long and X. Hu, “Spatial partition-based particle filtering for data assimilation inwildfire spread simulation,” ACM Transactions on Spatial Algorithms and Systems, vol. 3, no. 2, aug 2017.

Fire Spread Simulation 
[1]  X. Rui, S. Hui, X. Yu, B. Wu, and G. Zhang, “Forest fire spread simulation algorithm based on cellular automata,” Natural Hazards, vol. 91, no. 1, pp. 309–319, 2018. 
[2]  S. K. Singh and S. Kanga, “Forest Fire Simulation Modeling using Remote Sensing & GIS,” International Journal of Advanced Research in Computer Science, vol. 8, no. 5. [Online]. Available: https://www.researchgate.net/publication/325848449 

For this week, I read the papers on Moodle, met with Charlie to discuss my ideas, and read papers related to them. Below are some updates for each topic.

Idea 1 Title: Improve Fire Identification Mapping and Monitoring Algorithm (FIMMA)

Description: Enhance FIMMA to reduce the number of false-positive results and apply the algorithm to detect fire in urban areas.

Update: This algorithm has been developed for the past 20 years by NASA. It has gone through many modifications and enhancements, and is currently producing quite accurate results. The main reason why it cannot detect fire instantly is because of the time the satellites take to circle the Earth.

Idea 2 Title: Fire Detection Using A Combination of Different Image Analysis Techniques.

Description: The research aims to detect fire by analyzing different attributes (heat, temperature of the surrounding area, temperature and color of the smoke) at different ranges of the electromagnetic spectrum (UV, visible, and infrared).

Update: There have been numerous unmanned vehicles being developed to take images of a fire scene at different electromagnetic spectrum. A drawback of detecting fire using image analysis might potentially lie with the hardware rather than the analysis techniques. For example, the resolution of the images and the hardware of the camera are usually affected when the vehicles try to take photos too close to the fire source.

Idea 3 Title: Real-time Fire Tracking System.

Description: The research aims to create a system that can provide current data for active fire as well as calculate the direction it is moving. The system can combine the data from Google Earth and NASA’s Fire Map to provide the current condition of the fire. It will also need real-time data of a given location, particularly weather (wind, humidity) and local condition (population, buildings) in order to make predictions. 

Update: Since last week, I have been focusing on this idea more than the other two. What I am planning to do is to build a system that can produce a simulation of how an active fire spreads in a specific fire situation, particularly in forest fire. Many factors will have to be considered to build this simulation, especially data about the surrounding environment, weather, and terrain, etc. I plan to use archived data so that I can compare my predictive result to the actual fire spread direction.

1 ) Name of Your Project: Improve Fire Identification Mapping and Monitoring Algorithm (FIMMA).

Enhance FIMMA to reduce the number of false-positive results and apply the algorithm to detect fire in urban areas.

2 ) Name of Your Project: Fire Detection Using A Combination of Different Image Analysis Techniques.

The traditional methods to detect forest fires such as using mechanical devices or humans are not effective on a global scale. With the advancement of technology, detecting forest fire using image analysis has proven to be promising due to its low cost and effectiveness on a global scale. However, these analyses generally focus on only one technique, either analyzing the images in one range of the electromagnetic spectrum or study the heat signature of the fire. The research aims to detect fire by analyzing different attributes (heat, temperature of the surrounding area, temperature and color of the smoke) at different ranges of the electromagnetic spectrum (UV, visible, and infrared).

3) Name of Your Project: Real-time Fire Tracking System.

A wildfire usually spreads rapidly within hours from the start, which means responding quickly to the fire can lead to fewer damages and casualties. The research aims to create a system that can provide current data for active fire as well as calculate the direction it is moving. The system can combine the data from Google Earth and NASA’s Fire Map to provide the current condition of the fire. It will also need real-time data of a given location, particularly weather (wind, humidity) and local condition (population, buildings) in order to make predictions.

• Name of My Project

Managing Fire From Space

Improve Fire Identification Mapping and Monitoring Algorithm (FIMMA).

• What research topic/question is my project going to address?

Space technology has been used to improve life on Earth through many applications. One of them is to use Earth observation satellites to detect forest fires and alert local authorities in real time.

NASA has been developing FIMMA algorithm that analyzes data taken from Earth observation satellites to detect possible forest fires.

The FIMMA algorithm has several limitations, which often leads to false-positive results. The research aims to address and find possible solutions to the current limitations and produce a better algorithm.

• What technology will be used in your project?

Fire Information for Resource Management System (FIRMS).

• What software and hardware will be needed for your project?

Data manipulation and graphing tools.

• How are you planning to implement?

Compare the current implementation of FIMMA algorithm with other fire detection algorithms and fire products.

• How is your project different from others? What’s new in your project? 

The algorithm is currently only accurate over forested regions. The algorithm may miss real fires over urban areas, as well as many agricultural burns. A focus of the research is to improve the fire detection accuracy of these regions.

• What’s the difficulties of your project? What problems you might encounter during your project?

The research requires a deep understanding of the algorithm, geology, satellite technology, and data science.

It can be challenging to obtain the most updated progress of the algorithm.