NASA Earth Exchange (NEX): Big Data Challenges, High-Performance Computing, and Machine Learning Innovations



Sangram Ganguly

Senior Research Scientist, NASA

I am a research scientist at the Biosphere Science Branch at NASA Ames Research Center, Moffett Field, California, and at the Bay Area Environmental Research Institute. 

My work leverages expertise across a range of disciplines, including cloud computing solutions for big data science and analytics, machine learning, advanced satellite remote sensing and image analytics, and climate sciences. 

I did my PhD at Boston University (USA). Prior to that, I graduated with an integrated masters (BS and MS) degree in geosciences from the Indian Institute of Technology (IIT), Kharagpur, India, in 2004. I am an active panelist for the NSF and NASA carbon and ecosystem programs and a science team member for the NASA Carbon Monitoring System Program. My research has been highlighted in mainstream news media, and I am the recipient of five NASA achievement awards that were recognized in the fields of ecosystem forecasting, climate science, and remote sensing. I am also a cofounding member of the NASA Earth Exchange Collaborative and Supercomputing Facility at NASA Ames and a founding member and developer of the OpenNEX Platform


Advanced remote sensing techniques and physical algorithms: radiative transfer theory, MODIS & MISR, Landsat-derived biophysical variables (e.g., LAI), Lidar and Radar remote sensing for biomass estimation, multi-sensor fusion for carbon flux estimation 

Image analytics: pattern recognition/image classification, big data architectures for large image manipulation and query, soft computing techniques (fuzzy, neuro-fuzzy, genetic algos.)

Climate modeling and dynamics

Advanced signal processing techniques for multi-dimensional and multi-temporal analysis of satellite imagery

Machine learning: deep learning algorithms for large image classification (e.g.,from Worldview, NAIP, landsat, etc.), biophysical parameter prediction, and climate gridding