Welcome! I am the Chief Data Scientist at Radiant Earth Foundation, a non-profit organization aiming to use the power of Earth Observations data to enable global development community tackle environmental and development challenges. I lead Radiant Earth Foundation's machine learning efforts on developing open source tools, models and training dataset for a wide range of applications in agriculture, urban planning, health and environmental monitoring. You can read more about our initiative MLHub.Earth in my blog post here. I am also leading a new technical working group at Radiant Earth Foundation on "Machine Learning for Global Development". You can read about our first meeting of the working group here

Before joining Radiant Earth Foundation in Sep 2017, I was a Postdoctoral Research Scientist at Columbia University’s Earth and Environmental Engineering Department working with Prof. Pierre Gentine. My research was focused on improving our understanding of the heterogeneous processes linking the water, carbon and energy cycles. In particular, I developed new retrieval algorithms from remote sensing observations for different variables of the Water and Carbon cycles and using the remote sensing estimates to characterize the dynamic feedback between terrestrial ecosystem and atmosphere.

Before joining Columbia University, I was a Postdoctoral Research Associate in the Department of Civil and Environmental Engineering at MIT working with Prof. Dara Entekhabi in Parsons Laboratory for Environmental Science and Engineering. At MIT, I developed a new polarimetric retrieval algorithm for the NASA’s Airborne Microwave Observatory of Subcanopy and Subsurface (AirMOSS) mission to estimate soil and vegetation parameters from P-band Synthetic Aperture Radar (SAR) observations. In contrast to the current global measurements of surface soil moisture using Soil Moisture Active Passive (SMAP) mission which has an L-band instrument, measurements in P-band frequencies have a higher penetration depth and can be used to retrieve soil moisture profiles up to several tens of centimeters.

I received my Ph.D. in Civil and Environmental Engineering from MIT in 2014 (supervisors: Prof. Dara Entekhabi, Prof. Dennis McLaughlin). My PhD dissertation was focused on quantification of uncertainty in remotely-sensed precipitation estimates. I developed an ensemble-based framework to characterize the uncertainty in precipitation estimates using historical errors. This framework generates realistic spatial (2D) replicates of rainfall that can be used to propagate the uncertainty into ecohydrological and meteorological models, especially those used in Data Assimilation.


Favorite Quotes:

- The quality of life depends upon the ability of society to teach its members how to live in harmony with their environment-defined first as family, then the community, then the world and its resources. (Ellen Swallow Richards, "Mother of Ecology")

- The purpose of models is not to fit the data but to sharpen the questions. (Samuel Karlin)

- Imagination is more important than knowledge. (Albert Einstein)