UROP Openings

Have a UROP opening you would like to submit?

Please fill out the form.

Submit your UROP opening

Machine Learning Systems for Food Security and Sustainability




MAS: Media Arts and Sciences

Faculty Supervisor:

Danielle Wood

Faculty email:


Apply by:



Neil Gaikwad <gaikwad@media.mit.edu>

Project Description

The mission of the Space Enabled research group is to advance justice in Earth's complex systems using designs enabled by space. Space technology contributes to the United Nations’ Sustainable Development Goals via communication, earth observation, positioning, microgravity research, spinoffs and inspiration. Space Enabled uses six research methods: design, art, social science, complex systems, satellite engineering and data science. We strive to enable a more just future in which every community and country can easily and affordably apply space-enabled technology to improve public services and solve local challenges. We are looking for a highly-motivated UROP with a strong interest at the intersection of design, computation, and society. As a UROP, you will assist in the ongoing development of the mobile computing and machine learning system to tackle food security challenges. The responsibilities include extending the capability of current mobile-based systems infrastructure by implementing analytics modules. You will assist in ongoing analytics software development and participate in deployment of machine learning models. At the end of the project, you will develop strong research skills and gain experience in designing human-centered systems and machine learning models for addressing societal challenges. The project is led by Neil Gaikwad and in the deployment phase; we aim to work with-and improve the livelihood of vulnerable communities affected by socio-economic impact of COVID-19. All the work for this UROP will be completed virtually.


Familiarity and experience with Javascript, Html/CSS, React, Python, Map Box, and SQL Good to have: interest in deep learning, machine learning fairness, and remote sensing