Engineering Intelligent Decision-Support Systems for Sustainable Crop Productivity in Emerging Economies

Abstract

Developing economies face major challenges in achieving sustainable agricultural productivity, including poor infrastructure, climate change and poor resource use. Intelligent decision-support systems (IDSS) provide a data-driven approach to enhancing agricultural management practices, resulting in enhanced crop production, resource efficiency, and resilience to environmental issues. This paper discusses the engineering principles of IDSS in agriculture with a focus on the application of Internet of Things (IoT) sensor networks, cloud computing, machine learning methods, and geospatial analysis. The research looks in detail at models for forecasting crop production, controlling diseases and pests, scheduling irrigation and optimising nutrients. We study architectural issues in depth, including modularity, scalability, interoperability and energy-efficient design. The paper discusses challenges faced by the developing economies like limited connectivity, diversity of data sources and cyber security threats and suggests strategies to overcome them. In this paper we propose a reference framework for the combination of edge intelligence, predictive analytics and user-centric decision dashboards that facilitate smallholder farmers and agribusiness actors to make informed, timely and sustainable decisions. Results suggest that well-designed IDSS can increase efficiency of water and fertiliser use by up to 40%, decrease crop losses due to biotic and abiotic stresses, and increase total productivity. This review further contributes to the literature by providing a systematic engineering perspective on the design, implementation, and improvement of IDSS for agricultural systems in resource-limited settings.