Novel Model Created That Can Predict Wildfire Burn Area Based on the Drought Factor
AJAS · 2022 Environmental Science
Overview
In recent years, many severe and destructive wildfires have plagued the state of California. Extreme fire conditions, such as drought, that occur especially during autumn months in California, have been taking place at the same time as many of these wildfires. In this study, the relationship was quantified between the self-calibrated Palmer Drought Severity Index (sc- PDSI) and wildfire severity in California during the time period 1984-2018, and a model was created that can work to predict the severity of future wildfires. The methods of wavelet transform coherence (WTC), cross wavelet transform (XWT), and continuous wavelet transform (CWT) were used in conjunction with machine learning algorithms to analyze and establish the relationship between sc-PDSI and wildfire severity. This study concludes that there was a significant relation between wildfire AE (areal extent) and sc-PDSI in 6-8, 5-6, and 2-3 year periods during the study period. The relationship was statistically significant (associated with 95% significance) and indicates that sc-PDSI is one of the main drivers for the wildfire AE in these periods. In addition, machine learning was utilized in conjunction with the Quantile Regression Model (QRM) in order to develop the prediction model and further analyze the relationship. The QRM results indicate that the sc-PDSI impact on wildfire AE is more pronounced for more severe wildfires compared to smaller wildfires. A prediction model of wildfire AE based on the QRM relation between AE and sc-PDSI was also developed to predict future wildfire AE in California. My findings are extremely significant as the prediction model can be used in the aid of damage control of wildfires in California, leading to fewer burned acres, less economic damage, and fewer casualties.
Video
This video could not be played here. Watch it on the original project page.
My Story
Environmental science has been a topic that I’ve been passionate about my entire life, and my love for it brought me to research, which fortunately has brought to me the AJAS opportunity.
In 2nd grade, my mother brought me to the Environmental Protection Agency on Bring Your Kids to Work Day. Although the memory of staring at butterflies and learning about tree leaves around campus still occasionally dances around my mind, the real magic of the day happened in my mom’s office room. Within those cramped four walls, my mother’s finger traced rivers on maps and her mouth told stories of the impact she had on our earth, and I fell in love with learning about the environment too. I learned how she developed models to monitor and predict air quality, which is being used in communities around the globe to protect human health.
As I grew older, every summer, I began to go back to Beijing, the heart of China. Though I returned to reunite with family and explore the crevices of my culture, slowly I began to realize the change in my surroundings. During a time when I was old enough to understand but too young to know how to fix it, I watched as the skies became lined with black fog, and as the masses of people piled high and higher in apartment buildings that couldn’t hold them. I watched as lakes in the Olympic Forest Park, where I would row boats and feed fish with my family, dried up and turned grey. And when the Huai River, which flowed right behind my grandmother’s house in the Jiangsu province, was found to contain cancer-forming chemicals, I watched as my desperation grew higher. I was growing up witnessing a place I loved and called home crumble, and I had no idea what I could do about it.
At around the same time, in 7th grade, a close family to mine almost lost their lives in a wildfire in California. When I read the articles stating that the fires were only going to get worse, I remember going to sleep with the promise that I would do something etched behind closed eyelids.
So when I discovered the science research shortly after, the puzzle pieces all clicked into place. It was a chance for me to learn more about a topic I’ve always been curious about, poke and prod my head for both the questions and the answers, and finally be able to do something. Thus began my research career.
Since then, research has been an integral part of my life. Ever since I discovered it, research has shaped much more than my science abilities, has taught me lessons I will remember for a lifetime, and has become an activity that I truly love. What started as a childhood vision has now turned into something I want to do for the rest of my life.
As my research career continued, I realized that I wanted to share my discoveries with as many other people as possible to create a large impact. Therefore, I began to participate in competitions and conferences as well as contacted scientists and professors to share my findings with them. One opportunity I was fortunate enough to have to experience was run by the North Carolina Academy of Science, and winning an honor at this opportunity resulted in becoming an American Junior Academy of Science Delegate.
Additional Items
Research Paper
Images (14)
Awards (1)
- AJAS Fellows Badge
Competition history
- AJAS 2022
Resources
Related projects
ISEF · 2021
Assessing and Predicting Wildfire Severity in California Based on Relationships Between Wildfires and Drought Using Machine Learning
ISEF · 2022
Developing a Machine Model to Predict Wildfire Risk and Identify Key Wildfire Drivers in California
ISEF · 2018
Satellite Modeling of Wildfire Susceptibility in California by Using Artificial Neural Networking
ISEF · 2021
An Accessible, Low Cost Tool for Citizen Scientists: Using Remote Sensing Techniques to Predict Fire Damage Propensity
CSEF · 2019
Predicting Wildfires with Neural Networks: An Approach to Preventing California Wildfires
ISEF · 2024
Developing a Novel Wildfire Spread Prediction Model Using Spatio-Temporal Analysis and Time-series Forecasting
CSEF · 2018
A Data Analysis Approach to Wildfire Prediction
JSHS · 2024
Predicting Next-Day Wildfire Spread with Environmental Data and Machine Learning
Closest projects by meaning, across every fair and year in the corpus.