GX & Decarbonization Research

Luo X.

This paper proposes a CF-EEMD-LSSVR machine learning model to evaluate and predict greenhouse gas emissions from lead smelting systems. The model captures complex emission patterns, achieving high prediction accuracy. It contributes to emis…

Teri Grimmer, Wookyoung Kim, Harim Jung +1

This study examines how AI-enabled analytics enhances ESG reporting in resource-constrained museums. Using resource-based view and dynamic capabilities theory, it conceptualizes AI-enabled ESG reporting as a strategic organizational capabil…

Joseph Agossa

This paper introduces KenyaESG, a sentence-level ESG disclosure classification dataset built from annual, integrated, and sustainability reports of firms listed on the Nairobi Securities Exchange (2010-2024). For each of the three pillars (…

Warit Attharat, Kritsada Puangsuwan, Supattra Puttinaovarat

This paper presents a web-based platform that uses deep learning (CNN) and GIS to detect lighting status in rooms, enabling real-time monitoring of electricity usage and carbon emissions. High classification accuracy is achieved, supporting…

Zhiyong Wu, Yun Qiao, Youren Ma

This paper proposes a standardized, AI-driven framework for assessing energy conservation in retrofitted and operational buildings across ASEAN. It integrates EUI, operational patterns, equipment loads, and local climate data to create adap…

Yu Xing, Siyuan Zou, Guohua Liu

This paper proposes a machine learning ensemble framework for carbon price prediction across China's seven regional pilot carbon markets. It integrates price, volume, inter-market, and macroeconomic variables using XGBoost, LightGBM, and Ra…

Zesen Wang, Lijuan Lan, Yonggang Li +1

This paper proposes TriHead-GAN, a Transformer-based GAN with a triple-head discriminator that jointly supervises distributional authenticity, cross-variable dependencies, and temporal smoothness for carbon emission time series generation. …

Xin-song Ma, Ren-wei Zhang

This study proposes a multi-scale adaptive graph convolution model for carbon price prediction, capturing complex price dynamics in carbon markets using deep learning.

Na Du, Baoyi Liu, Ao Gong +4

This paper proposes a deep reinforcement learning approach for optimal dispatch of regional integrated energy systems with carbon capture and trading. The method adapts to dynamic carbon prices, balancing economic and environmental objectiv…

Huan Liu, Shaojun Bai

This study applies multidimensional text analysis to corporate ESG reports to examine whether high ESG performers exhibit distinct linguistic patterns. By leveraging NLP methods, it sheds light on the relationship between disclosure quality…

Zhaoshuai Dang

This dataset comprises carbon price data from four Chinese regional markets (Hubei, Guangdong, Beijing, Shanghai). It is used for multivariate and univariate carbon price forecasting experiments with the AMST-Pyraformer model, an adaptive m…

Ahmed A. A. Abdel-Wareth, Ahmed A. Ahmed, Mohamed O. Taqi +2

A comprehensive review of AI applications (machine learning, sensors, data analytics) in livestock farming for climate resilience and sustainability. Covers GHG mitigation, feed efficiency, disease prevention, and animal welfare, highlighti…

K. Umer, Sajjad Ahmad, I. Raisani +5

This study examines the impact of transparency on the relationship between AI-driven finance and sustainable performance. Using a survey of 252 respondents from financial institutions and corporations, the findings indicate that transparenc…

Marina Nazir, Marina Nazir, Minhas Akbar +2

This paper explores how artificial intelligence and environmental digitalization contribute to mitigating climate risks and promoting sustainable development amid geopolitical uncertainty. It examines the potential of AI-driven climate risk…

Shukai Zhang, Chengzhi Yu, Shuang Liang

This study reframes street-level urban renewal as a coordination problem between vitality and low-carbon performance. Using multisource data and interpretable machine learning, it diagnoses vitality-carbon mismatches in Chengdu, China, find…

Abdul Rehman, Suyang Zhou, Sheeraz Iqbal +3

This paper proposes an Adaptive Quantum-DRL Multi-Objective Optimization (AQ-DRLMO) framework for low-carbon CCHP systems. It integrates quantum-inspired evolutionary algorithms with deep reinforcement learning, achieving 40.08% emission re…

Rency Dayne Duque, John Rein Vinuya, Kristenz Mingoy +2

This study presents Cravely, an AI-integrated digital platform for food waste reduction in the Philippines. It enables surplus food redistribution at discounted prices and uses an AI module to estimate avoided methane emissions. Evaluation …

Human Sciences Research Council

This chapter proposes a dynamic policy formulation system inspired by natural systems, using AI and big data to monitor climate indicators and automatically update policies via rapid feedback loops, avoiding delays of traditional policy pro…

NOUNANGNONHOU CT, DIDAVI KBA, AZA-GNANDJI MR

This paper proposes a hybrid deep learning model (B6) combining CEEMDAN-VMD dual decomposition with a GRU-attention backbone for wind power forecasting. Evaluated on seven wind farms, it reduces MAE and RMSE by 25-35% over baselines for 1h,…

Maataoui, Wijdane El, Abounada, Abdelouahed

This paper proposes replacing the classical virtual synchronous generator (VSG) control with a deep neural network (DNN) for wind power systems. The DNN is trained end-to-end using supervised learning to generate inverter control signals fr…