Vol.15, No.2, May 2026.                                                                                                                                                                          ISSN: 2217-8309

                                                                                                                                                                                                                        eISSN: 2217-8333

 

TEM Journal

 

TECHNOLOGY, EDUCATION, MANAGEMENT, INFORMATICS

Association for Information Communication Technology Education and Science

 

A Sustainability-Oriented Platform for Monitoring Electricity Usage and Carbon Footprint in Educational Institutions Using Deep Learning and GIS

 

Warit Attharat, Kritsada Puangsuwan, Supattra Puttinaovarat

 

© 2026 Supattra Puttinaovarat, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)

 

Citation Information: TEM Journal. Volume 15, Issue 2, Pages 1056-1068, ISSN 2217-8309, DOI: 10.18421/TEM152-10, May 2026.

 

Received: 22 May 2025.
Revised: 04 November 2025.
Accepted: 05 December 2025.
Published: 27 May 2026.

 

Abstract:

 

Amid growing global efforts to mitigate climate change, significant attention has been placed on reducing greenhouse gas emissions, with many organizations striving to achieve Carbon Net Zero in accordance with the Sustainable Development Goals (SDGs). Among the primary contributors to institutional carbon footprints is electricity consumption. However, energy monitoring practices in most institutions remain limited to aggregated monthly readings from electricity meters, offering little insight for short-term or room-level energy management and policy planning. To bridge this gap, this study introduces a web-based application that detects and classifies the on/off status of lighting in individual rooms. The system enables real-time monitoring and verification of electricity usage and the resulting carbon emissions. To address this limitation, this study introduces a web-based application designed to detect and classify the on/off status of lighting in individual rooms, enabling real-time monitoring and verification of electricity usage and the corresponding carbon emissions. The application integrates image processing, machine learning, and geographic information systems (GIS) technologies. Experimental results confirm the high accuracy and robustness of the proposed Convolutional Neural Network (CNN)-based model for image-based classification. Furthermore, the platform offers interactive visualization of carbon footprints through a dynamic dashboard integrated with spatial mapping, supporting data-driven and real-time decision-making for institutional sustainability management.

 

Keywords – Deep Learning, IoT, carbon footprint, SDGs, GIS.

 

-----------------------------------------------------------------------------------------------------------

Full text PDF >  

-----------------------------------------------------------------------------------------------------------

 


Copyright © 2026 UIKTEN
Copyright licence: All articles are licenced via Creative Commons CC BY-NC-ND 4.0 licence