Electricity access is critical to tackling global poverty, scientists say

Access to electricity may play a much more significant role in improving economic livelihoods than previously assumed, a new study has found.

Stanford University scientists harnessed the power of satellite imagery and artificial intelligence to quantify the impacts such a shift can make — publishing their findings on Wednesday in Nature.

Homing in on the country of Uganda and its expanding electricity grid, the researchers saw that financial conditions for populations that gained access to electricity roughly doubled in comparison to those that lacked power.

“We provide first-of-its-kind causal evidence of how electricity access impacts economic well-being at scale across an entire country in Africa,” lead author Nathan Ratledge, a PhD candidate at Stanford’s Doerr School of Sustainability, said in a statement.

The findings come amid the second and final week of the United Nations climate change conference COP27 in Egypt, where countries are negotiating how to increase support for developing countries on the front lines of the climate crisis.

If approved by all nations attending COP27, a draft agreement released on Monday would establish funds for “loss and damages,” to pay reparations to such nations. 

In Uganda, the country assessed by the Stanford researchers, the electricity grid covered 41 percent of the nation’s land mass as of 2019 — up from 12 percent in 2010, according to the study.

But the scientists found that communities granted electricity access witnessed significant changes, evident in the appearance of home construction, appliances and other tangible assets.

Drawing these conclusions wasn’t an easy task at first. Ratledge said that when he first began probing electrification in Africa five years ago, he couldn’t find electrical grid maps anywhere on the continent.

“It’s hard in many low-income countries to get any reliable data, and especially repeated data over time,” he said. “In many cases, it just doesn’t exist.”

But three Stanford professors — Marshall Burke, David Lobell and Stefano Ermon — were working on a new tool that aimed to bridge this data gap, according to the team.

Their “deep learning” technique, highlighted in a 2020 article in Nature Communications, harnesses artificial intelligence to detect patterns and extract information from imagery — allowing scientists to apply that insight to freely accessible satellite data going back over time.

Using this tool, Ratledge and his co-authors zoomed in on the rapid expansion of Uganda’s electricity grid in 2011 and 2012.

They combined newly developed digitized maps of the country’s grid from 2005 through 2016 with satellite-based estimates of wealth from a deep learning model, according to the study.

The model uncovered data from almost 642,000 household in 27,000 villages across sub-Saharan Africa, the authors noted.

Ultimately, the researchers found that Ugandan communities given access to electricity boosted their wealth at about twice the rate of those where power was not available.

“This insight would not have been possible just a few years ago,” Burke, an associate professor at the Doerr School of Sustainability, said in a statement.

Burke predicted that ongoing advances in ultra-powerful, cheap computing will help improve information access to researchers studying policies and programs aimed at reducing poverty in any country.

“This technique opens up a whole new and dramatically different frontier for assessing economic growth among emerging countries,” Ratledge added.