<![CDATA[Methane (CH₄) emissions from ruminant livestock farming are one of the major sources of greenhouse gases and simultaneously cause feed energy losses of approximately 2–12%, thereby reducing livestock production efficiency. In addition, conventional emission monitoring systems are costly and difficult to implement widely in smallholder farming systems. This study aims to review the development of Internet of Things (IoT) and Machine Learning (ML) technologies for monitoring and predicting methane emissions in ruminant livestock production, while also identifying opportunities for the development of data-driven decision support systems. The study employed a Systematic Literature Review (SLR) approach following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Relevant articles were retrieved from the Scopus database using the keywords “methane emission” and “machine learning.” Of the 89 articles initially identified, five studies met the inclusion criteria and were selected for further analysis. Data were analyzed using a descriptive-comparative approach by examining the technologies, sensor types, system architectures, data communication methods, and machine learning algorithms employed in each study. The results indicate a technological shift from conventional measurement methods toward intelligent systems integrating IoT, wireless sensor networks, cloud computing, and artificial intelligence. Among the machine learning approaches, Long Short-Term Memory (LSTM) demonstrated the best performance for time-series methane emission prediction, while statistical methods remained widely used for sensor calibration and data normalization. The integration of IoT and ML has significant potential to support precision livestock farming through real-time monitoring, emission forecasting, and automated decision-making, thereby improving feed efficiency and reducing greenhouse gas emissions.]]>
