Negin Sobhani
Data Scientist / Computational atmospheric scientist
National Center for Atmospheric Research (NCAR)
About “Negin”
As an atmospheric scientist, I use environmental data to help people. I am an atmospheric scientist and a software engineer who is passionate about adopting emerging computational technologies for improving the performance of weather and climate forecasting models. I am particularly interested in improving weather and climate forecasts using artificial intelligence and deep learning algorithms.
I am currently working at the Climate and Global Dynamics Laboratory at the National Center for Atmospheric Research. I have a Ph.D. in Chemical Engineering from the University of Iowa and my thesis was focused on optimization of weather and air quality models for different applications.
- Machine Learning to Improve Weather and Climate Forecasting Models
- Artificial Intelligence
- Interactive Visualizations
- Numerical Weather Prediction Models (NWPs)
- Earth System Modeling
-
Ph.D. in Chemical and Environmental Engineering, 2017
University of Iowa
-
BSc in Chemical Engineering, 2011
University of Tehran
Experience
Responsibilities include:
- Designed and developed a Python-based dashboard for online interactive visualizations, statisticalanalysis, and evaluation of climate simulations against tower observations.
- Developed a user-friendly framework for Docker-based climate simulations and analysis of climate simulations.
- Created user guides for the developed tool to the community of technical and non-technical users.
Responsibilities include:
- Implemented and evaluated various machine learning and deep learning algorithms for seasonal and sub-seasonal forecast of extreme weather events such as heatwaves.
- Designed and trained deep neural networks for emulating complex cloud microphysical processes.
- Supervised two interns to optimize different neural network architectures for seasonal forecasts of extreme weather events.
- Created several tutorial Jupyter notebooks to teach summer interns about data handling, visualization, and statistical analysis of climate data.