Kindie Tesfaye-Fantaye of the International Maize and Wheat Improvement Center in Mexico will develop a computational model that incorporates the variable characteristics of households and farms to better predict the outcomes of agricultural interventions in Ethiopia in order to inform policy choices. Agriculture is central to the Ethiopian economy; it accounts for almost 50% of the gross domestic product and 80% of total employment, yet the industry struggles with limited infrastructure and environmental challenges. Prioritization of agricultural policies has generally relied on analysis of past observations, which are static and tend to ignore variability. They will build and validate an agent-based model that uses current data to model future outcomes, and input biophysical (e.g., soil, climate) and socioeconomic (e.g., household characteristics, land use, access to market and financing) data. They will test their model by comparing five candidate policy options under consideration by the government in terms of impact, effectiveness, efficiency, and inclusiveness. Once established, the model will be scaled up for policy intervention in other Sub-Saharan countries including Tanzania and Nigeria.

Amit Lal of Geegah LLC in the U.S. will develop battery-powered ultrasonic imagers to collect and wirelessly transmit high-resolution images of soil and airborne pests for the early detection of crop threats across large farming areas in rural Africa. Crop losses due to pest infestation negatively impact both food security and local economies. Damage caused by nematodes is particularly difficult to detect because the symptoms visible above ground are not unique and are often incorrectly attributed to deficiencies in soil nutrients or moisture. Currently the only way to test for nematodes is through root and soil samples taken after harvest, when it is too late to respond to an infestation. They will integrate complementary metal-oxide semiconductors (CMOS) with GHz ultrasonic imagers to detect nematodes and survey soil properties over large areas to detect infestations before crop damage occurs and transmit the data in real time. They will optimize the sensor technology in a controlled laboratory setting to maximize sensitivity and specificity and minimize power consumption and then transition to a farm setting for incorporating data transmission via the radio frequency wireless network.

Danya Arif, Subhash Chandir, and Qadeer Baig of IRD Global in Singapore will develop and implement a school-based initiative in Pakistan to train adolescent girls to provide practical immunization information to parents and caregivers and thereby increase vaccination coverage in peri-urban areas. Poor compliance with routine immunization schedules puts children at risk of vaccine-preventable disease; some of the most vulnerable are urban-slum communities where traditional methods to increase vaccination uptake have failed. As an alternative approach, they propose to create a strong community force of adolescent girls, trained in leadership and communication skills and educated on basic immunization facts, to counsel mothers in their community on the importance of timely vaccination and provide them with practical information on clinic locations and schedules. The girls will also be equipped to identify never- and under-vaccinated children. They will pilot test their approach in ten schools in two peri-urban slums in Karachi city with 500 female students in grades eight to ten. They predict that mothers will be more likely to accept and act on information delivered by these girls as accepted members of their community, and training the girls as adolescents will have a sustainable impact: as they themselves become mothers they will be lifelong advocates for childhood immunization.

Subhash Chandir, Danya Arif, and Ali Habib of IRD Global in Singapore will develop a text-based immunization chatbot that uses artificial intelligence (AI) and natural language processing to provide vaccine education and practical information to caregivers to improve vaccine coverage in Pakistan. Although free clinics exist, many children remain incompletely vaccinated because caregivers are unaware of the importance of immunization and uninformed about clinic locations and schedules. They will develop Bablibot – a chatbot to replicate interactive human conversations and able to understand caregiver queries and respond with automated text messages. The bot will provide information on immunization locations and schedules, address post-vaccination concerns, and prompt caregivers when vaccinations are due, easing the burden on overworked health workers. Chatbot conversations will be validated through human-in-the-loop (HITL) to enhance AI potential and, if needed, connect the caregiver with a human being. It will be widely accessible as it works via text. It will be pilot tested by integrating with the existing digital immunization registry of over one million children and recruiting 5,000 caregivers. The ability of Bablibot to provide accurate information, continuity of care, and convenient interaction with the healthcare system could increase immunization demand and coverage.