Forecasting Post-Wildfire Vegetation Recovery in California using a Convolutional Long Short-Term Memory Tensor Regression Network
JSHS · 2024
Overview
The increasing wildfire frequency and size have posed growing challenges for re -establishing plants after wildfires, making the study of post -wildfire plant regrowth essential for creating effective plans to recover ecosystems. Previous research has predominantly focused on unraveling and analyzing the key ecological and biogeographical factors that influence post-fire succession. This research proposes a novel approach for predicting and analyzing post -fire plant recovery. Using the Normalized Difference Vegetation Index (NDVI) to quantify vegetation levels, a Convolutional Long Short -Term Memory Tensor Regression (ConvLSTMTR) network is created to predict future NDVI based on short -term plant growth data after fire containment. The model is trained and tes ted on 104 major wildfires in California from 2013 to 2020 with burn areas larger than 3000 acres. The integration of ConvLSTM with tensor regression enables the calculation of an overall logistic growth rate k using my model’s predicted NDVI time series. Overall, my k- value predictions demonstrate impressive performance, with 50% of predictions exhibiting an absolute error of 0.12 or less, and 75% having an error of 0.24 or less. Finally, I employ Uniform Manifold Approximation and Projection (UMAP) and K-nearest neighbor (KNN) clustering to determine trends in similar post-wildfire recovery, providing valuable insight into areas of high and low recovery rate. My study pioneers the combined use of tensor regression and the ConvLSTM and introduces the applic ation of UMAP for clustering similar wildfires. Taken together, this study contributes to the advancement of predictive ecological modeling and holds the potential to inform future post-fire vegetation management strategies.
Competition history
- JSHS 2024
Resources
Related projects
ISEF · 2024
Forecasting Post-Wildfire Vegetation Recovery in California Using a Convolutional Long Short-Term Memory Tensor Regression Network
ISEF · 2024
Developing a Novel Wildfire Spread Prediction Model Using Spatio-Temporal Analysis and Time-series Forecasting
ISEF · 2018
Satellite Modeling of Wildfire Susceptibility in California by Using Artificial Neural Networking
JSHS · 2024
Predicting Next-Day Wildfire Spread with Environmental Data and Machine Learning
ISEF · 2021
An Accessible, Low Cost Tool for Citizen Scientists: Using Remote Sensing Techniques to Predict Fire Damage Propensity
ISEF · 2023
Developing a Deep Learning Model to Approximate the Convolutional Geometry of Wildfires
ISEF · 2022
It's Flaming Out: Using Artificial Intelligence To Emulate Critical Aspects of Wildfire Growth
ISEF · 2021
Assessing and Predicting Wildfire Severity in California Based on Relationships Between Wildfires and Drought Using Machine Learning
Closest projects by meaning, across every fair and year in the corpus.