Emerging machine learning expert leads Kenya AI workshop
ASU research team uses satellite data to combat food insecurity and climate change
What if we already gather all the data we need to help us prepare for disasters, better plan our urban environments and protect our food supply? What if we lack the tools to effectively analyze all the data we already collect?
A doctoral student at Arizona State University is on the front lines of artificial intelligence, or AI, research designed to help us act on what we know.
This June, top data science researchers and graduate students convened on the campus of Dedan Kimathi University of Technology in Nyeri, Kenya to tackle some of the planet’s most pressing problems — food insecurity, environmental conservation and climate change.
Data Science Africa, or DSA, hosted its annual Summer School, attracting hundreds of students, industry professionals and academics from all over the world to collaborate on the event’s theme of “Data Science for Social Good in the Age of Generative AI.”
Gedeon Muhawenayo, a doctoral student in the School of Computing and Augmented Intelligence, part of the Ira A. Fulton Schools of Engineering at ASU, attended the event on behalf of the Kerner Lab, discussing the team’s work as part of the NASA Harvest program. NASA Harvest is a consortium of leading scientists and agricultural stakeholders who combine their expertise to ensure food security.
Hannah Kerner, an assistant professor of computer science and engineering in the Fulton Schools, is developing tools to analyze huge sets of Earth observational data to inform actionable plans. In her laboratory, her team is using a type of AI called machine learning to process massive sets of information.
One aspect of the group’s work involves supplying satellite imagery to banks of computers and tasking AI systems with learning to recognize what type of crop is being grown in the images. Once the AI can identify the crops, it can build meaningful maps when it receives new images. This process enables experts to know how much food is being produced in a region and whether it will be enough to feed the population.
From satellites to social impact
Kerner recruited Muhawenayo to join her team following his work in the Rwanda Space Agency, where he created machine learning systems for use by sustainable farming programs.
“Gedeon is an invaluable addition to the lab,” Kerner says. “He has the motivation, dedication and technical skills to advance AI methods that result in meaningful results — not only for publications, but for real people. I am certain he will go on to do innovative and socially impactful work in machine learning and beyond.”
Muhawenayo is an emerging expert in the field of machine learning for remote sensing. He studies data — such as electromagnetic radiation, visible light, infrared and microwave signals — that is gathered by satellites and drones and then creates AI tools to process it.
“I started exploring ways to extract useful features from satellite imagery and soon realized that machine learning algorithms were the key to achieving this,” Muhawenayo says.
Hailing from Kigali, Rwanda, the mission to ensure food security has a special significance for Muhawenayo.
“Many African countries are prone to a wide range of natural hazards that strain the most vulnerable communities, particularly smallholder farmers,” he says. “Furthermore, agriculture is a major economic sector. Advancements in machine learning can support ways to increase harvests for these communities, especially in the face of challenges posed by climate change.”
After receiving his master’s degree in machine intelligence from the African Institute for Mathematical Sciences in Accra, Ghana, Muhawenayo joined the Kerner Lab
“I was particularly inspired by their emphasis on user-driven research and the practical application of cutting-edge research,” he adds. “I want to be part of a research agenda that leverages technology for social good.”
Going global and getting engaged
At the DSA Summer School event, Muhawenayo led a machine learning for remote sensing workshop, training fellow graduate students on how to deal with large sets of Earth observation data. In his talk, he introduced students to sources of satellite data, discussed how to develop budgets for research projects and showcased programming tools to process the images. He also conducted a hands-on session, helping attendees create their own cropland maps.
Muhawenayo’s work is part of efforts underway in the Fulton Schools to create world-class graduate programs and attract top students from around the globe.
Ross Maciejewski, director of the School of Computing and Augmented Intelligence, says this outreach is a key area of focus for the school’s faculty members.
“Hannah Kerner’s collaboration with Gedeon is a great intersection of technical acumen and specialized, regional knowledge that will produce real, practical results,” Maciejewski says. “Creating a home for excellent doctoral students is an important part of our research and academic missions.”
Meanwhile, Muhawenayo says he found the DSA 2024 Nyeri Summer School event inspiring and believes that today’s students are serious about solving the world’s tough problems.
“The engagement from younger generations in the global community gives me hope that we can drive meaningful change,” Muhawenayo says. “I believe we can create a sustainable future and effectively combat the adverse effects of climate change.”