Mobile-Enabled Pest Prediction in Sub-Saharan Africa: An Empirical Review of SMS and Mobile Platforms Bridging Traditional Farming Knowledge and Digital Early Warning Systems

Abstract

Food security in Sub-Saharan Africa is threatened by a number of agricultural pests including the fall armyworm, desert locusts and stem borers. Typical pest monitoring, mostly conducted by manual scouting and late reporting, can inhibit prompt early warning and response. This paper presents a systematic review of the empirical evidence on SMS platforms, mobile applications and mobile based pest prediction systems with a focus on incorporating indigenous ecological knowledge. Using the thematic synthesis approach and supported by the Technology Acceptance Model, Diffusion of Innovation Theory and Information Systems Success Model, 54 peer-reviewed articles, institutional reports and conference papers were reviewed between 2018 and 2026. The results show that mobile platforms increase the timeliness and geographical scope of pest data collection and dissemination. By combining climatic, vegetation and historical pest information, machine-learning models can help improve accuracy over local conditions. Incorporating indigenous indicators into digital systems brings context, farmer confidence and adoption. However, the key challenges remain are network infrastructure issues, digital literacy, data quality and interoperability issues, and institutional coordination. The study suggests a Hybrid Mobile Pest Early Warning (HM-PEW) approach of combining indigenous knowledge, mobile reporting, locally calibrated machine learning analytics and tiered SMS, USSD and application-based dissemination.