Fecha de publicación: 01/09/2024 Fuente: Journal of Applied Research in Technology & Engineering (JARTE) Abstract
Agricultural production systems play a crucial role in global societal sustenance as they provide the world's food, fuel, and fiber supplies. However, these systems face numerous challenges including climate change and resource depletion. Modern technologies powered by artificial intelligence (AI) can help address these challenges by contributing to revolutionizing agricultural production and building resilience. While there has been a growing body of research on AI-based technologies in agricultural production systems, comprehensive literature reviews on the potential of AI-based technologies in enhancing resilience, and sustainability in agricultural production systems is lacking to the extent of the authors’ knowledge. Additionally, some studies have focused on specific AI-based technologies such as internet of things, creating a gap in ascertaining the impact of the cumulative application of these techniques. This review aims to fill these gaps by exploring the trends in the emergence of AI technologies and applications in agricultural production systems. It also investigates the integration of these technologies into traditional farming operations and driving climate-smart agriculture (CSA). Data on automation systems, AI applications, and CSA were gathered from peer-reviewed publications, reports, and public databases. Two Natural Language Processing (NLP) tools were utilized: the Iris.ai application and an in-house NLP tool developed with Fast.ai-NLP (the Fast.ai deep learning library). The Iris.ai-NLP tool extracted a thousand papers between 1940 and 2021, while the Fast.ai-NLP extracted forty thousand papers from early 1900s to 2023. These extracted papers were finally revised to a concise reading list of a hundred and thirty four papers. Results showed that greater attention has been given to AI-based technologies and models that enhanced production systems. The collective application of AI-based techniques can improve food security and environmental sustainability by optimizing processes to increase yield and aiding in effective monitoring to decrease environmental emissions such as greenhouse gases. The analyzed studies using NLP tools showed how AI technologies could address limitations in the agricultural sector and contribute to improving productivity, resilience to climate change, and food security. Rapid implementation of these technologies in agricultural production systems worldwide has the potential to address challenges such as, resource degradation and depletion, skilled labor shortages, and high input costs.