Spandan Das: Self-Taught Machine Learning Intern,
NCCS User, College Student, and Published Author



Hometown: I was born in Milwaukee, Wisconsin, but I have lived most of my life in Fairfax, Virginia.

What was your career path to NASA? I had studied computer science in high school at the Thomas Jefferson High School for Science and Technology (TJHSST) in Alexandria, Virginia, including a course in machine learning. I also led the high school computer team and studied computer science on my own through online courses and in programming contests. A few months prior to the start of my summer 2020 internship, during COVID-19 quarantine restrictions, I decided to study machine learning on my own, primarily through self-study using books and courses offered online. That preparation and knowledge of computer science served me well for my application for a NASA internship. I eventually completed two valuable internships in summer 2020 and 2021 at the NASA Goddard Space Flight Center.

An architectural rendering of the main entrance of the Thomas Jefferson High School for Science and Technology by the Architect of Record for the campus-wide renovation, Ballou Justice Upton Architects. Rendering courtesy of BJU Architects.

During my first internship in summer 2020, I was a rising high school senior. I was matched with my internship mentor, Dr. Jie Gong, a research atmospheric scientist in the Climate and Radiation Lab at NASA Goddard, based on my background in computer science and machine learning. Initially, Dr. Gong and I met remotely and discussed what I would be working on that first summer. An important requirement for one of her own major projects was the ability to predict the type of classification of an atmospheric phenomena (precipitation, in this case), based on metadata provided by NASA’s Global Precipitation Measurement mission (GPM) satellites. I started working on that project in summer 2020 and made good progress on using machine learning and testing precipitation models. I compared results using data from two instruments, one with an active sensor, which is more expensive to build and maintain, and one with a passive sensor, which is less expensive. I presented my results to Dr. Gong’s team and to the Climate and Radiation Lab at the end of my first summer internship -- remotely of course, because of COVID lockdown. My mentor liked my work, and I liked the project.

After graduating high school, I had a second summer internship with Dr. Gong at NASA Goddard in 2021, also working remotely. I continued working on the results from the research begun the previous summer, testing more complex machine learning models and expanding on and interpreting those earlier findings. The combined results of those two summers of work culminated in a coauthored paper published in July of 2022 in the professional journal, Remote Sensing.

Dr. Jie Gong, atmospheric scientist in the Climate and Radiation Branch at NASA Goddard.

How did having to work remotely as an intern and the experience of working with Dr. Gong impact you, in terms of your future research interests? The research was, of course extremely rewarding in itself. Before my internships, I had never worked with or attended meetings with scientists. During my internship, I met with my mentor daily. I was also able to attend regular meetings with a group of 6-7 researchers. At first, I was very intimidated, but I was able to eventually be comfortable with asking questions. Having the opportunity to interact with these NASA scientists regularly and ask questions was one of the coolest parts of my internship experience. I was initially deeply focused on tackling this project from a computer science and machine learning perspective. But at these meetings with NASA experts in their fields, I was able to learn more about what the data and results meant, and they were able to point me in the right direction. They suggested other features to add that might help the model and shared their ideas on which models might work better because certain data is distributed a certain way, which was eye-opening. I got feedback from the head of the lab after my department-wide presentation was also helpful. That all made for a great experience.

How will this research help improve or impact future models? The impact of this project is that we are able to use data from a passive sensor, plug that data into a machine learning model, and get precipitation results similar data to that from an active sensor. Using data from the less expensive passive sensor with machine learning means fewer sensors, ultimately saving NASA costs for the next generation of satellites and remote sensing instruments used for precipitation observations.

One major challenge for the Global Climate Model (GCM),” explained Dr. Gong, “is to correctly partition convective and stratiform precipitation processes, which directly impacts the model’s representation of the energy balance and hydrological cycle. With the help of machine learning models and the computational power provided by NCCS, we can use multiple spaceborne passive sensors (e.g., GPM-GMI) trained by one spaceborne active sensor (GPM-DPR in this case) to track the spatial and temporal evolutions of precipitation systems and their structures. This can not only further our knowledge of understanding how precipitation forms in different stage and weather system regimes, but can also help evaluate and improve GCMs.

How did the NASA Center for Climate Simulation (NCCS) support this research? NCCS provided me with sufficient compute power to build, train, and test various learning models which were crucial to my project as an intern as well as the research that ensued. I simply could not have run and test any of these simulations on desktops or laptops without the GPUs and supercomputing resources of the NCCS. “The NCCS support team is superb,” emphasized Dr. Gong. “They are extremely supportive and professional.”

What did you do after your summer internships ended? After graduating high school in spring 2021 and completing my second NASA summer internship, I moved to Pittsburgh, Pennsylvania in fall 2021 and started working on an undergraduate degree at Carnegie Mellon University (CMU). I am now in my second year at CMU, studying computer science with a concentration in machine learning. My primary research interests include exploring the applications of machine learning to robotics, vision, and finance.

What or who especially inspires you? My teachers and mentors always inspire me and push me to do more. Two in particular have been extremely influential in developing my interest in using technology to solve challenging and meaningful problems.

In high school, Mr. Malcolm Eckel used the Socratic method to teach members of his artificial intelligence course how to set up a problem using the tools that we had. He helped us understand the relative utility of existing algorithms and how to develop new ones. This all helped us fully understand the ground-up approach to problems and understand and focus on why we were doing what we were doing.

Malcolm Eckel, math teacher at Thomas Jefferson High School for Science and Technology.

Dr. Jie Gong, my NASA internship mentor for two summers, inspired and encouraged me. I had never worked one-to-one with a scientist like that, and she spent a lot of time with me. I was fortunate in many ways to have Dr. Gong’s mentoring. She met with me daily, despite the pandemic and the demands of conducting her own research, collaborating virtually. She was focused on ensuring that I learned new things over the summer and encouraged me to publish my results so that I could learn about the scientific research process from start to finish. Dr. Gong also made sure that I had plenty of networking opportunities, despite the quarantine limitations. She invited me to virtually attend weekly Climate and Radiation department meetings, where I was able to get valuable, first-hand feedback on my project from a number of NASA researchers. In addition, she gave me the opportunity to go to NASA Goddard for an in-person networking opportunity, where I met other interns and NASA Administrator Bill Nelson.

Spandan Das, at left, with NASA Administrator Bill Nelson at center, other interns and NASA staff at a networking meeting for interns in summer 2021 at NASA Goddard.

Are there any people in your field who have influenced you? One person who always inspires me is my father, who worked for many years during my childhood to complete his Ph.D. in computer science at the University of Wisconsin Milwaukee while also raising our family. Seeing my father study complex topics and develop new algorithms, even after long hours at work, has inspired me to push through difficult times, both inside and outside of research.

What challenges have you had to overcome? One recent challenge that I have had to overcome was balancing my school’s course load with research. While this combination has led to long hours, it has been extremely rewarding in my development as a student and research scientist.

In terms of scientific research and your education, where are you heading next? I’m still figuring that out, but I think that a graduate degree is likely.

Related Link


Sean Keefe, NASA Goddard Space Flight Center
November 30, 2022