🌍 Climate Scientist & AI Expert | PhD in Interdisciplinary Engineering | Postdoctoral Research Fellow at Northeastern University
This is my personal portfolio website showcasing my work in climate science, artificial intelligence, and extreme weather modeling. The site highlights my research projects, publications, professional experience, and educational content.
Live Site: https://pujadasneu.github.io
- Extreme Weather Modeling - AI-driven solutions for precipitation forecasting
- Flood Risk Assessment - Hybrid physics-ML methodologies for disaster preparedness
- Remote Sensing - SAR imagery analysis for flood depth estimation
- Climate Modeling - CMIP6 Earth System Models evaluation and improvement
- Hydrological Engineering - Urbanization impacts on precipitation extremes
- PhD in Interdisciplinary Engineering (4.0/4.0 GPA) - Northeastern University
- NASA-funded Project Lead - RAIN (Remote sensing data driven AI for precipitation Nowcasting)
- Multi-institutional Collaborations - NASA, ORNL, TVA, Zeus AI, RTI
- 15+ Publications - Including npj Climate and Atmospheric Science
- Research Internships - NASA Ames Research Center, Capella Space Corp
- Languages: Python, MATLAB, R, Shell Scripting
- ML/AI: Supervised Learning, Time Series Analysis, Computer Vision, Generative AI
- Climate Data: CMIP6 analysis, NetCDF/HDF/GRIB processing
- GIS Tools: ArcGIS Pro, QGIS, Google Earth Engine, GDAL
- Climate Modeling: Hydrologic modeling, atmospheric data processing
- Watershed Modeling: HEC-RAS, HEC-HMS, SWMM, VIC
- Cloud Computing: High-Performance Computing (HPC) resources
- Statistical Analysis: Extreme value analysis, probabilistic modeling
- Network Analysis: Gephi, complex networks
Developing hybrid physics-ML methodologies for intense orographic precipitation prediction in the Appalachian region. Leading multi-institutional collaboration for enhanced flood and river management.
Analyzing precipitation extreme statistics across urban vs non-urban regions in CONUS, contributing to infrastructure design and climate adaptation strategies.
Utilizing Synthetic Aperture Radar imagery for flood depth estimation and damage assessment during major flood events.
- "Hybrid Physics-AI Outperforms Numerical Weather Prediction for Extreme Precipitation Nowcasting" - npj Climate and Atmospheric Science (2024)
- "Finer Resolutions and Targeted Process Representations in Earth Systems Models Improve Hydrologic Projections" - arXiv preprint (2024)
- "Floods, Facts, and Fictions: Numbers and Narratives Behind Bangladesh's 2024 Regional Floods" - Earth arXiv (2025)
Check out my YouTube tutorials on climate data analysis and machine learning applications in weather prediction:
My research has been featured in:
- Flood Prediction with Artificial Intelligence - Northeastern University News
- Reducing Climate Change Disasters - Northeastern University News
- Responsive Design - Optimized for all devices
- Modern UI/UX - Clean, professional design with smooth animations
- Interactive Elements - Hover effects, scroll animations, and dynamic content
- SEO Optimized - Proper meta tags and semantic HTML
- Fast Loading - Optimized CSS, JavaScript, and images
This portfolio is built using:
- HTML5 - Semantic markup and accessibility features
- CSS3 - Modern styling with Flexbox/Grid, animations, and responsive design
- Vanilla JavaScript - Interactive features and smooth user experience
- Font Awesome - Professional icons throughout the site
- GitHub Pages - Free hosting and automatic deployment
The website is fully responsive and optimized for:
- 📱 Mobile phones (portrait & landscape)
- 📱 Tablets (portrait & landscape)
- 💻 Laptops and desktops
- 🖥️ Large screens and ultrawide monitors
- Fast Loading - Optimized assets and efficient code
- Smooth Animations - Hardware-accelerated CSS transitions
- Cross-browser Compatible - Works on all modern browsers
- Accessibility - WCAG guidelines compliance
- Email: pujadas251@gmail.com
- Phone: +1 (857) 340-8425
- Location: Malden, MA
- LinkedIn: Connect with me
This project is open source and available under the MIT License.
Special thanks to:
- Northeastern University - For providing the research environment and support
- NASA - For funding the RAIN project
- Collaborating Institutions - ORNL, TVA, Zeus AI, RTI
- Open Source Community - For the tools and libraries that made this possible
Last updated: June 2025
⭐ If you found this portfolio helpful, please consider giving it a star!