The Application of Artificial Intelligence in Transforming Agriculture in Ghana: A Systematic Review of Empirical Evidence, Impacts, and Scaling Constraints
Antwi Edmond Owusu
*
Department of Agrobiotechnology, Agricultural-Technological Institute, RUDN University, 117198, Moscow, Russia and Department of Agricultural Extension, University of Ghana, Legon, Ghana.
Buabeng Victoria Fosua
Department of Agrobiotechnology, Agricultural-Technological Institute, RUDN University, 117198, Moscow, Russia and Department of Agriculture Engineering, University of Cape Coast, Ghana.
Abdul Wasiw Abubakar
Department of Crop Science, University of Ghana, Legon, Ghana.
Solomon Kojo Hagan
Center for Climate and Sustainability Studies University of Ghana, Ghana.
Anderson Matthew
Department of Agrobiotechnology, Agricultural-Technological Institute, RUDN University, 117198, Moscow, Russia and Department of Agribusiness Management and Consumer Studies, University of Energy and Natural Resources, Sunyani, Ghana.
*Author to whom correspondence should be addressed.
Abstract
Background: Artificial intelligence (AI) is increasingly promoted as a transformative tool for addressing persistent challenges in agricultural productivity, climate resilience, and market efficiency, particularly in smallholder-dominated systems such as Ghana. However, empirical evidence on its effectiveness and scalability remains fragmented.
Methods: This study conducted a PRISMA 2020–compliant systematic review of peer-reviewed and grey literature published between 2015 and 2025. Searches across five major databases yielded 78 eligible studies, which were synthesized using a narrative quantitative approach to assess AI application types, reported impacts, and adoption constraints in Ghanaian agriculture.
Results: The review identified 11 empirically evaluated AI pilot initiatives spanning precision agriculture, climate and weather forecasting, pest and disease diagnostics, market linkages, and financial services. Reported outcomes include crop yield increases ranging from 10% to 92%, farmer income gains of 10–15%, reductions in post-harvest losses of 25–30%, and input efficiency improvements of up to 25%. AI-enabled climate advisory tools improved harvest outcomes for approximately 84% of participating farmers, while digital financial platforms increased formal financial inclusion by about 15%.
Conclusion: AI applications in Ghanaian agriculture demonstrate strong technical potential but remain largely constrained to pilot scale due to infrastructural, data, institutional, and capacity limitations. Scaling their impact will require coordinated policy frameworks, investments in rural digital infrastructure and data ecosystems, and targeted capacity-building initiatives to support inclusive and sustainable adoption.
Keywords: Artificial intelligence, precision agriculture, smallholder farming, digital agriculture, climate resilience, Ghana