I am a machine learning and deep learning scientist with geospatial background and experience in developing machine learning and deep learning solutions for a wide range of spatial and temporal problems, from COVID-19 predictive modeling to image segmentation in satellite imagery.

I have a B.Sc. in Geomatics Engineering and a M.Sc. in GIS Engineering from K.N.Toosi University of Tech., a M.A. in Geography from University of California Santa Barbara and am working on my PhD in Geography at University of Colorado Boulder. At CU Boulder, I’m a member of GeoHAI Lab directed by Dr. Morteza Karimzadeh.

Research Interests

My main researh interests lie at the intersection of deep learning and spatial science, or GeoAI as known formally.

SKILLS:

• General: Machine learning, Deep learning, Geospatial data science, Object-oriented design and programming, working with location data
• Programming: Python (proficient), C++ and JAVA (intermediate)
• Data Science: Tensorflow, Scikit-Learn, PyTorch, JAX (intermediate)
• Geospatial: ArcGIS, QGIS, ENVI, Google Earth Engine, GeoPandas, RasterIO

News

• I received the Outstanding Student Presentation Award from AGU for my presentation titled “A Comparison Of Classic Deep Learning Architectures For Sea Ice Classification From SAR” at Fall Meeting 2021. Read more here

• My manuscript on “Partial Label Learning with Focal Loss for Sea Ice Classification” is currently under revision.

Publication Highlights

Here are some of my most recent publications. To see a full list, please visit the Publications page.

• Spatiotemporal prediction of COVID-19 cases using inter-and intra-county proxies of human interactions. Nature Communications, (2021). B Vahedi, M Karimzadeh, H Zoraghein

• A spatiotemporal machine learning approach to forecasting COVID-19 incidence at the county level in the USA. International Journal of Data Science and Analytics, (2022). B Lucas, B Vahedi, M Karimzadeh.

• GIS-based spatial modeling of COVID-19 incidence rate in the continental United States. Science of the total environment, (2020). A Mollalo, B Vahedi, KM Rivera

Presentation Highlights

Here are some of my most recent talks. To see a full list, please visit the Presentations page.

• (Invited) Sea Ice Type Classification using Deep Convolutional Networks and Partial Label Learning. AGU Fall Meeting 2022, Chicago, IL.

• Semantic Segmentation of Sea Ice Using Multi-scale Spatial Context. AGU Fall Meeting 2022, Chicago, IL.

• A Comparison Of Classic Deep Learning Architectures For Sea Ice Classification From SAR. AGU Fall Meeting 2021, New Orleans, LA.

• Sea Ice Type Classification from Sentinel-1 SAR Imagery Using Deep Neural Networks. AGU Fall Meeting 2021, New Orleans, LA.