This project is focused on building decision-making tools for stakeholders (e.g. Energy Utilities) particularly in challenging situations of extreme weather events such as compound events of a heat waves and fire-weather danger. While the heat stress exposure urges the Utilities management to provide extra energy supply to assure AC usage and keep people cool, the wildfire risk points them to induce planned power outages, so fire ignition due to energy grid failure is prevented. This tool will help Energy Utilities to decide how to distribute the energy, and where to apply planned power outages according to vulnerabilities of the communities. We are seeking to build a trans-disciplinary team from Civil Engineering, Data Science, Applied Math and Computer Sciences who can work together on building this innovative tool which will include analytical and ML models for energy grid distribution, power outages, heat stress and fire-weather forecasting.
PROJECT TIMELINE: We will start with literature search and overview of ML methods for decision making (week 1-2), we will collect and clean the input data sets and prepare the training data sets (week, 3-4), Building and training ML models for decision-making for energy distribution (week5-6), Visualization of the data and building a Dashboard with variety of key analytics (week 7-8), Final presentation (DS Discovery Symposium) and report (week9-10)
PROJECT WORKFLOW: We will split the interns in two groups - backend and frontend depending on the students skills and experience. We will meet on regular basis once weekly with the entire team and another meeting with each of the groups.
DELIVERABLES: 1) ML model for energy distribution decision making; 2) Dashboard Analytics
PREFERRED APPLICANT SKILLSET:
- Python - Beginner/Intermediate/Advanced
- SQL - Beginner/Intermediate/Advanced
- EDA - Beginner/Intermediate/Advanced
- Data Visualization - Beginner/Intermediate/Advanced
- Geospatial Data Analysis - Beginner/Intermediate/Advanced
- NLP - Beginner/Intermediate/Advanced
- Machine/Deep Learning - Beginner/Intermediate/Advanced
- Computer Vision - Beginner/Intermediate/Advanced
- Cloud Computing - Beginner/Intermediate/Advanced
PREFERRED ADDITIONAL SKILLSET: geopandas, geojson, api
ABOUT THE DISCOVERY PROGRAM:
The Discovery Research Program aims to empower undergraduate researchers by connecting them to data science-driven research projects. Discovery encourages applicants from all majors and backgrounds. The majority of our available projects leverage tools and methodologies in Data Science for research inquiry in a broad range of topic areas.
Depending on the project, students can expect to spend anywhere between 6-15 hours per week. While backgrounds in STEM are all useful, we believe that diverse perspectives and experiences are the most essential qualities for successful research.
For additional information about the Discovery Research Program, visit: