An IoT-Enabled Framework for Real-Time Monitoring and Prediction of Methane Emissions in Sustainable Ruminant Farming
Onwuchekwa Nnamta Peter1, Ezeofor Chukwunazo Joseph2
1Onwuchekwa Nnamta Peter, Center for Information and Telecommunication Engineering, University of Port Harcourt, Rivers State, Nigeria.
2Dr. Ezeofor Chukwunazo Joseph, Department of Electrical and Electronic Engineering, University of Port Harcourt, Rivers State, Nigeria.
Manuscript received on 30 November 2025 | First Revised Manuscript received on 02 February 2026 | Second Revised Manuscript received on 03 March 2026 | Manuscript Accepted on 15 April 2026 | Manuscript published on 30 April 2026 | PP: 11-16 | Volume-13 Issue-4, April 2026 | Retrieval Number: 100.1/ijies.B105505020226 | DOI: 10.35940/ijies.B1055.13040426
Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper presents the development of an Artificial Intelligence (AI) enabled Internet of Things (IoT) framework for methane emission monitoring and prediction in sustainable ruminant farming. Methane emissions from ruminant livestock are a significant contributor to greenhouse gas emissions and a major environmental concern in sustainable agriculture. Conventional methods for measuring and controlling these emissions are manual, time-consuming, and lack predictive intelligence, thereby limiting farmers’ ability to make timely, data-driven decisions. This paper addresses these challenges by integrating IoT-based sensing and AI-driven predictive analytics to enable real-time data acquisition, intelligent forecasting, and emission control for livestock management. The IoT subsystem, designed and simulated in Proteus, comprises a methane gas sensor, an ATmega328P microcontroller, an ESP8266 Wi-Fi module, and a cloud-based Blynk dashboard. Simulation results confirmed stable data transmission, accurate methane detection across varying concentrations, and real-time visualization on a mobile interface. The AI component utilized a comprehensive dataset of feed composition, animal weight, and environmental variables collected from ruminant farms across South–South Nigeria. Three supervised learning algorithms, Random Forest, XGBoost, and Artificial Neural Network (ANN), were retrained and evaluated using performance metrics such as Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The Random Forest model outperformed the others with MAE = 1.52, RMSE = 2.21, and predictive accuracy of 93%. The integrated AI–IoT system demonstrates the ability to monitor methane emissions continuously, predict future trends, and generate actionable insights to optimise feed strategies and livestock mitigation, precision livestock management, and environmental sustainability in modern agriculture.
Keywords: Artificial Intelligence, Internet of Things, Methane Emission, Sustainable Ruminant Farming, Machine Learning
Scope of the Article: Electrical Engineering