Artificial Intelligence Applications in Smart Feedlot and Livestock Management: A Comprehensive Review with Perspectives for Malaysia

Abstract

The global livestock industry faces mounting pressures from rising protein demand, environmental sustainability requirements, and labour shortages. Artificial Intelligence (AI) technologies offer transformative solutions by enabling intelligent, data-driven management of feedlot and livestock operations. This comprehensive review systematically examines the state of the art in AI applications across the livestock production cycle, covering Machine Learning, Deep Learning, Computer Vision, Internet of Things (IoT), Edge AI, Explainable AI (XAI), Digital Twin, and Multimodal AI. A dedicated section critically evaluates the Malaysian livestock and feedlot industry, encompassing beef, dairy, and poultry sectors, and assesses the current readiness for Precision Livestock Farming (PLF) adoption against the industry 4.0 agenda. Literature was sourced from Scopus, Web of Science, IEEE Xplore, ScienceDirect, Springer, and MDPI covering the period 2018–2026, with emphasis on 2020–2026. Following PRISMA methodology, 105 studies were included from an initial pool of 1,847 records. Findings reveal rapid advances in YOLO-based animal detection (mAP >90%), LSTM-driven disease prediction (AUC >0.87), and IoT sensor fusion platforms. However, significant gaps persist in explainability, real-time edge deployment, and domain-adapted models for tropical and developing-country livestock contexts. Based on the reviewed literature, this paper outlines an integrated Smart Feedlot Framework that combines IoT, Computer Vision, AI Analytics, Cloud/Edge Computing, and ESG monitoring within a unified Decision Support System (DSS). The review concludes with strategic research directions for foundation models, agentic AI, satellite-assisted monitoring, and carbon analytics in future livestock management.