1. Our Team

Fellow
Stephen Lee
Researcher, MIT
Focus
Big Data & The Grid
Areas of Expertise
Electrification Planning, Data for Infrastructure Planning

Stephen is a Hub Fellow and a researcher in the MIT Universal Energy Access Lab and the MIT Computer Science and Artificial Intelligence Laboratory. His current work involves remote sensing for large scale infrastructure planning using a variety of machine learning and statistical methods. Ongoing projects include automatically mapping infrastructure in large areas using satellite image data and performing data fusion for electrification status and demand estimation using Bayesian spatial models. Stephen has experience in India and sub-Saharan Africa working on projects related to data-driven electrification master planning. He previously worked as a management consultant with NERA Economic Consulting and Deloitte Consulting. Stephen is currently pursuing a PhD in Electrical Engineering & Computer Science at MIT. He holds Master’s degrees in Electrical Engineering & Computer Science and in Technology & Policy from MIT and Bachelor’s degrees in Materials Science & Engineering and Economics from Johns Hopkins University.

Social Share:

Related Content

Memo

Long-tailed distributions and electrification planning: why we need to model the ‘long tail’ of large consumers

By Stephen Lee, Jay Taneja
What do earthquake magnitudes, viral YouTube videos, and consumer-level electricity demand have in common? If you guessed: “they all exhibit long-tailed distributions,” you’re correct! ‘Long-tailed’ distributions refer to those in which a small number of occurrences take extreme values, far from the central part of the distribution.
Continue Reading

Memo

Imagining the ‘Google’ of electrification: how digital twins and computational systems for continuous planning can reinvent century-old practices

By Stephen Lee, Ignacio J. Perez-Arriaga
Some of today’s largest companies – Google, Facebook, and Amazon – disrupted their respective markets and earned trillion-dollar company valuations by using computational systems to provide information, collect data, and continuously optimize their processes.
Continue Reading

Memo

Lighting the Way: Nighttime Lights for Electrification Planning

By Stephen Lee, Brian Min, Jay Taneja, Zeal Shah
Data is often scarce when it relates to the development of electricity infrastructure in emerging economies. Using geographic information system (GIS) databases has become standard practice,1 but information digitization, data collection, and aggregation at scale can be costly and take years.
Continue Reading

Memo

A planner’s guide to acquiring building locations data

By Stephen Lee
Planning efficient, least-cost electricity infrastructure can benefit from using modern tools to gather improved information describing areas of interest. Building location data in the form of latitude and longitude coordinates are important when outlining the most efficient ways to electrify an area with limited resources.
Continue Reading

Memo

Why Energy Demand Demands More Attention

By Stephen Lee, Jay Taneja
If you were planning to open a coffee shop in your neighborhood, you would want to know how many cups your potential customers might consume each day.
Continue Reading

Memo

The Virtuous Cycle of Clean Cooking and Electricity Costs

By Stephen Lee
Access to electricity and clean cooking solutions are separate objectives of Sustainable Development Goal 7 (SDG7). Programs tackling these aims have been largely disconnected, however new research identifies virtuous cycles from their joint consideration: increasing electric cookstove penetrations increases electricity consumption, lowers electricity unit-costs through the realization of economies of scale, and improves the viability of electric cookstoves, continuing the cycle.
Continue Reading

Memo

Empowered Planning with Models, Satellites, & Machine Learning

By Stephen Lee
Geographic Information System (GIS) technologies have the capability to revolutionize large-scale electrification planning. Advances in computer-based electrification planning models, satellite imaging, and machine learning are able to optimize infrastructure planning, lowering the costs of electricity provision and expediting progress.
Continue Reading