<

Event Details

WiDS PSU Datathon 2026 – Predicting Wildfire Impact: From Infrastructure to Equity.

January 29 – March 8, 2026
Hybrid (In-Person + Virtual)
PSU, Building 101, Room E232 (B101-232) + Online

WiDS PSU Datathon 2026

Prince Sultan University is hosting the Women in Data Science (WiDS) Datathon 2026 as part of the global WiDS initiative. This year’s challenge theme is “Predicting Wildfire Impact: From Infrastructure to Equity”. Participants will work on data-driven and AI-based approaches to better understand wildfire impact, with attention to infrastructure-related effects and community-level equity considerations.

Why This Matters

  • Wildfires can disrupt infrastructure and essential services.
  • Data science can help forecast impact and support better preparedness.
  • Equity-focused analysis helps understand community-level vulnerability.
  • Hands-on learning with expert-led workshops and real-world datasets.

Workshops Schedule

Thu, Jan 29, 2026 • 12:00 pm – 2:00 pm

Datathon Orientation and Q&A

Presented by Prof. Tanzila Saba, Dr. Anees Ara, and Dr. Fatima Shannaq.

Thu, Feb 5, 2026 • 12:00 pm – 2:00 pm

Workshop 1: Geospatial DS + Data Wrangling

Presented by Dr. Sawsan Halawani.

Thu, Feb 12, 2026 • 12:00 pm – 2:00 pm

Workshop 2: ML for Wildfire Impact Prediction

Presented by Dr. Fatima Shannaq.

Sun, Mar 1, 2026 • 10:00 pm – 12:00 am

Workshop 3: Light MLOps + Deployment

Presented by Dr. Abrar Wafa.

Sun, Mar 8, 2026 • 10:00 pm – 12:00 am

Workshop 4: Success Stories

Presented by Ms. Reem Hejazi and Ms. Elham Al-Baroudi.

Competition Timeline

Registration Deadline

Jan 21, 2026

Workshops Period

Jan 29 – Mar 8, 2026

Winners & Recognition

Cash prizes and recognition at Stanford University Worldwide WiDS and PSU WiDS (details to be announced).

Technical Specifications

Platform

Kaggle (official WiDS Datathon competition platform)

Visit Kaggle

Tools

  • Python (primary language)
  • Pandas / NumPy
  • Scikit-learn / XGBoost (optional)
  • GeoPandas / GIS tools (for geospatial work, when applicable)
  • Matplotlib / Seaborn (visualization)

Dataset

WiDS Datathon 2026 dataset provided through the official Kaggle competition page, aligned with the theme “Predicting Wildfire Impact: From Infrastructure to Equity.”

Challenge

Build predictive models and insights to better understand wildfire impact, considering infrastructure outcomes and equity-related community effects.
Prediction / Modeling Task

Event Gallery