Thomas, Ann Mary, Dey, Maitreyee and Rana, Soumya Prakash ORCID: https://orcid.org/0000-0002-8014-8122 (2026) TAL-Net: a temporal attention LSTM framework for urban electricity and emissions forecasting in the U.S. npj Urban Sustainability. ISSN 2661-8001 (Online) (In Press) (doi:10.1038/s42949-026-00424-y)

PDF (Author's Accepted Manuscript (restricted)) 53913 RANA_TAL-Net_A_Temporal_Attention_LSTM_Framework_(AAM)_2026.pdf - Accepted Version Restricted to Repository staff only Download (6MB) | Request a copy

Abstract

Urban sustainability depends critically on accurate forecasting of electricity demand and associated CO2 emissions, particularly as cities strive to meet climate targets while ensuring energy resilience. However, existing approaches often model these two aspects in isolation, missing key interdependencies that influence urban energy dynamics. This study presents TAL-Net, a novel Temporal Attention LSTM Network designed for the joint forecasting of electricity demand and CO2 emissions in complex urban energy systems. Leveraging deep learning and domain-informed feature engineering, we evaluate TAL-Net alongside four other state-of-the-art models using high-resolution data from two contrasting U.S. regions - California and Texas - characterized by differing climates, energy portfolios, and urban infrastructure. TAL-Net consistently achieves superior forecasting accuracy, demonstrating lower MAPE, MAE, and RMSE across both regions. Our findings highlight the value of attention mechanisms in capturing temporal patterns and cross-variable dependencies, offering AI-driven insights to guide urban energy planning, carbon mitigation strategies, and grid management in fast-evolving metropolitan contexts.

Item Type:	Article
Additional Information:	Data availability. The dataset is a publicly available dataset, published by the U.S. Energy Information Administration (EIA) between 1st July 2018, and 30th June 2023 [33]. Available doi: https://doi.org/10.7910/DVN/OKEATQ Code availability. The code developed for this study, is publicly available on GitHub at: https://github.com/Ann-Mary-Thom.
Uncontrolled Keywords:	urban sustainability, electricity demand forecasting, CO₂ emissions forecasting, temporal attention LSTM, deep learning, smart energy systems, sustainable urban planning, artificial intelligence.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > T Technology (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty / School / Research Centre / Research Group:	Faculty of Engineering & Science Faculty of Engineering & Science > School of Engineering (ENG)
Last Modified:	06 Jul 2026 07:43
URI:	https://gala.gre.ac.uk/id/eprint/53913

Actions (login required)

View Item

Downloads