Talks and presentations

How Remote Sensing Can Be of Value to the Energy Sector

March 24, 2021

Talk, Columbia Global Centers, Nairobi, Virtual

Abstract: Recent work has demonstrated how one can use daytime satellite imagery to assist the prediction of individual residential building consumption levels upon connection. Using six years of longitudinal data of electricity consumption for a large cross-section of grid customers from Kenya, we apply convolutional neural networks (CNNs) to daytime satellite images to predict expected levels of residential electricity consumption for individual customers throughout the country.

Opportunities and Challenges for Machine Learning in the African Electricity Sector

April 01, 2020

Panel Discussion, ICLR 2020 Workshop Tackling Climate Change with Machine Learning,

This session highlighted impactful work at the intersection of climate change, electricity, and machine learning in a variety of African contexts. Topics addressed will include energy access, load forecasting, and data mining for electricity system data. Watch session HERE

Decision Support Metrics for Electricity Planning

April 01, 2019

Talk, Interdisciplinary Ph.D. Workshop in Sustainable Development (IPWSD), Columbia University, NYC

This talk demonstrated a two-stage electricity planning approach. Building locations and merging algorithms were used to apporximate residential locations, used as demand nodes for network planning. Given residential nodes, electricity access metrics (low voltage wire length, medium voltage wire length, transformer density and the cost of electrification) are estimated for wards in Kenya. These metrics highlight opportunities for varying electricity technologies (solar, minigrid, full-scale grid).

Challenges and Gaps during Energy Disruptions

June 01, 2018

Panel Discussion, Human Geography Dimensions of Energy Access and Use, Georgetown University, Washington DC

This was a panel discussion on the challenges and gaps which may occur or arise with energy disruptions. Energy disruptions may include climate change or new technologies and or regulations.