This project aims for students to recreate and enhance an algorithm from a published paper that calculates the risk index of a property from wildfires. The objective is to accurately predict and assess the wildfire risk to properties using advanced machine learning techniques and to incorporate additional data points that may increase the precision of the risk index. By the end of the project, students will have learned how to interpret academic research, implement machine learning models, and integrate environmental risk factors into predictive algorithms, showcasing their ability to apply theoretical knowledge in practical, real-world applications aimed at mitigating climate-related risks.

Literature Review and Algorithm Understanding

• Objective: Familiarize with the existing algorithm and its theoretical foundation as laid out in the academic paper.
• Deliverable: A summary report outlining the algorithm's methodology, strengths, and limitations.
• Filename for Deliverable: Wildfire_Risk_Algorithm_Review.pdf

Data Collection and Preprocessing

• Objective: Gather the required datasets and prepare them for use in the machine learning model.
• Deliverable: A cleaned and preprocessed dataset ready for model training.
• Filename for Deliverable: Preprocessed_Dataset_Description.pdf

Model Implementation and Testing

• Objective: Recreate the algorithm using a machine learning framework and test its accuracy against a portion of the data.
• Deliverable: The source code of the implemented model and a report on its performance metrics.
• Filename for Deliverable: Model_Performance_Report.pdf

Model Enhancement and Validation

• Objective: Improve the algorithm by integrating additional relevant data and testing different machine learning techniques.
• Deliverable: The enhanced model's source code and a comprehensive report comparing the performance of the original and enhanced models.
• Filename for Deliverable: Model_Enhancement_Report.pdf

Students will be supported through access to cloud computing resources for model training and testing, and participation in workshops on machine learning techniques, data preprocessing, and project management tools relevant to the project.