An autonomous decision support system for smart farming to increase crop productivity

Today, agriculture faces many challenges, most notably the significant and continuous increase in population, which requires more agricultural products to meet people’s food needs. Other challenges include global climate change, which has recently increased inefficiency due to drought, desertification, reduced irrigation water, increased soil pollution, plant diseases, and heat waves, causing many agricultural problems. Issues such as plant diseases, heat waves, floods, and water salinity all cause many agricultural problems. The farming industry needs to invest in new technologies and infrastructure to transform into an innovative industry capable of responding to these challenges through agile processes supported by industrial digital technologies, thereby maintaining efficiency and quality. The Industry 4.0 technology has been widely adopted by the manufacturing industry, enabling the sector to achieve the objectives of optimization, efficiency, responsiveness, and enhanced autonomy outlined by the digital transformation strategy. This study discusses the digitization of agriculture, leveraging IoT, machine learning, artificial intelligence, drones, and robotics to make a quantum leap in the future of the agricultural sector. By integrating advanced technologies into agricultural operations, this study seeks to enhance resource use and increase yields. Also, this study investigates an autonomous decision-support system for smart agriculture to increase crop productivity by implementing Industry 4.0 technologies in the agricultural sector. The study uses a quantitative technique. A comprehensive literature review establishes the theoretical framework, followed by the design and development of a decision support system prototype. This system integrates IoT sensors and artificial intelligence algorithms. Field trials are conducted on selected farms to test the system’s effectiveness, with data collected on soil moisture, weather conditions, nutrient levels, and crop health. IoT devices collect, analyze, process, and transmit data from devices and sensors to enable decision-making without human intervention. IoT also provides the basic communication infrastructure to connect smart devices, sensors, and drones to the Internet via mobile devices. These processes will enable many services, such as data collection and analysis, pattern recognition, and autonomous decision-making enabled by artificial intelligence, in addition to existing agricultural automation. The Researcher interviewed farmers to collect insights on the system’s usability and potential impact. The findings reveal that the autonomous decision support system significantly enhances crop productivity. Smart Farms using the system show an average yield increase of 15-20 per cent compared to conventional farming methods. The system optimizes irrigation schedules, reducing water use by 40% to 50% while preserving or enhancing crop health. Furthermore, the AI-driven pest prediction model achieves 90% accuracy in forecasting potential infestations, enabling timely, targeted interventions. In conclusion, this study highlights the potential of Industry 4.0 technologies to optimize processes and enhance efficiency. The autonomous decision support system provides a practical tool for farmers to make data-driven decisions, thereby increasing crop productivity and sustainable resource management. These findings have important implications for agricultural policy, technology adoption, and future research in smart farming. The study develops and deploys an ADSS in smart farming to increase crop productivity and highlights the need for further investigation into the environmental and economic impacts of the widespread adoption of smart agriculture. ADSS and the use of these technologies will revolutionize the farming sector, which is among the most inefficient today.

Citation

Ali, B.H. (2026) An autonomous decision support system for smart farming to increase crop productivity. University of Wolverhampton.

Publisher

University of Wolverhampton

URI

https://wlv.openrepository.com/handle/2436/626418

Type

Thesis or dissertation

Language

en

Description

A Thesis Submitted for the Degree of Doctor of Philosophy.

Collections

Theses and Dissertations