Work

Scalable Data Collection and Management for Agricultural Research: Foundations and Advancements in Data Mining Applications

Year: 2026
Type: book-chapter
Abstract: This chapter examines the convergence of participatory approaches and digital ecosystems in agricultural data collection, with a particular focus on Sub-Saharan Africa. While existing literature treats farmer-led models and digital technologies as separate trajectories, this synthesis demonstrates how participatory knowledge generation can be scaled and enriched through digital platforms and governance frameworks. It argues that scalable agricultural intelligence relies not only on technological innovation but also on governance, institutional integration, and farmer-centred design. The chapter demonstrates how hybrid models – which connect farmer-generated data with IoT sensors, cloud platforms, and AI analytics – can provide accuracy, inclusivity, and sustainability by referencing case studies including DigiFarm, PlantVillage Nuru, and TRICOT experiments. Comparative analysis of traditional, precision, participatory, and digital approaches reveals their distinct strengths while emphasising integration as the foundation for scalability and resilience. In order to tackle the enduring problems of data heterogeneity, connectivity, and trust, the chapter presents a hybrid paradigm that blends edge–cloud topologies, open APIs, and participatory governance. Moreover, ethical and policy dimensions, including data ownership, consent, liability, and equity, are critically examined. The chapter concludes by redefining digital agriculture as a socio-technical system in which farmer agency, institutional durability, and inclusive governance are central to building future-ready agricultural data ecosystems.
Language: English
Subfield: Plant Science
Open Access status: hybrid
OpenAlex ID: W7155196897
FWCI:
Cites: 78
Cited by: 1
Related to: 10