GX & Decarbonization Research

Suliman Khan, Safat Al-Deen, Chi King Lee

This paper provides an experimental dataset of ultra low-carbon concrete for performance prediction and machine learning applications. The dataset supports decarbonization in the construction sector, enabling performance evaluation and opti…

Shuangyang Zhai, Zishan Zhang, Haoyu Hou +2

This study examines whether China's carbon emissions trading (CET) pilot policy affects auditor industry specialization using a staggered difference-in-differences design on A-share firms from 2010 to 2022. Results show that CET exposure in…

Tamara Menichini, Stefania Roberta Miccoli, Nicoletta Maria Strollo

This paper systematically reviews AI's role in ESG reporting from a knowledge management perspective, identifying nine positive impact categories on SAR. Using the SECI model, it conceptualizes AI as an enabling infrastructure that enhances…

Yelmen B.

This study models energy use and GHG emissions in orange production in Turkey using artificial neural networks (ANN). It demonstrates AI application in agriculture for emission prediction and energy efficiency improvement, offering insights…

Wang H.

This paper proposes an AI-forecasting-based approach to manage cloud computing resources in a carbon-neutral manner, optimizing energy efficiency and reducing carbon emissions to support net-zero targets. It exemplifies the application of A…

Imad Ud Din Durrani, Hassan Raza

This study integrates disclosure tone (positivity, negativity, uncertainty) into machine learning models to enhance financial performance prediction for non-financial firms in Pakistan. Textual data from annual reports were analyzed using a…

Ritwick Boyra, Rajesh Bose, A. Khan +5

This paper proposes CrossChain-VaxTrace, an integrated architecture combining cross-chain blockchain, federated graph neural networks, and edge AI to address vaccine supply chain challenges. It achieves 67% energy savings via PoA consensus …

Marisol Coba-Martínez, Jarniel García-Morales, G. Guerrero-Ramírez +4

Proposes an intelligent control strategy for alkaline water electrolysis to produce green hydrogen on-demand, matching the stoichiometric requirements of methanol synthesis. ANN models with classical and conformable activation functions are…

Nicolas van der Nest

AI-assisted analysis of 30 Singapore Exchange-listed firms' reports reveals a gap between disclosure and implementation in supplier sustainability governance. While Scope 3 disclosure is universal, enforceable supplier controls remain limit…

Shunhao Mai, Zenglu Zhang, Jie Zhu +2

This paper introduces the Disclosure-Emission Gap (DEG) Index, a novel metric to detect corporate carbon washing by quantifying the divergence between disclosed environmental commitments and verified emission performance. Using CarbonBERT-C…

Jinpeng Dai, Fanghui Lu, Riccardo Maddalena +2

This study uses CPO-XGBoost machine learning to predict compressive strength of limestone calcined clay cement (LC3) and optimize low-carbon mix designs. LC3 reduces CO2 emissions in cement production, contributing to construction decarboni…

Zeqi Zhang, Yingjie Li, Danhui Lai +2

This paper proposes a low-carbon operational decision-making method for computing-energy parks using large language models (LLMs) and multi-agent collaboration. A dynamic carbon emission factor (DCEF) captures time-varying carbon signals, a…

Tong Qian, Yang Liu, Yunlin Huang +2

This review examines how AI enables electricity–computing synergy to address data center energy demands and renewable energy variability. It highlights deep learning for renewable forecasting and deep reinforcement learning for flexible wor…

Chandrani Ray Chowdhury

This chapter reviews generative models for probabilistic forecasting of renewable energy production, addressing the limitations of traditional ML/DL in handling stochastic, nonlinear data. It demonstrates how probabilistic forecasts support…

Jinliang Wang, Xiang Ma, Z. Ding

This paper proposes a method using large language models (LLMs) to automatically extract and analyze ESG disclosure information from corporate sustainability reports. Compared to traditional manual analysis, it enables efficient and compreh…

Leyi Yan, Shuangning Li, Sihang Liu

This paper characterizes carbon emissions of AI agent workloads and proposes carbon-aware execution scheduling that exploits deadline flexibility. AgentDecarbonizer, running alongside OpenClaw, estimates task duration and schedules executio…

Wiem Dridi, Saliha Theiri

Using French SBF120 firms from 2018-2024, this study finds that higher carbon emissions are associated with higher audit fees, with effects amplified in concentrated audit markets and regions with high environmental carbon exposure. Carbon …

Jicheng Du

This study develops a machine learning benchmark and life-cycle screening database for low-carbon alkali-activated materials from coal gangue and steel slag. It compiles 237 mixture records, benchmarks Random Forest and XGBoost under variou…

Nhat‐Luong Nhieu, Hoang‐Kha Nguyen

This study develops a T-Spherical Fuzzy-Valued Neutrosophic MEREC-EDAS framework to evaluate low-carbon cooling and energy management technologies for data centers. Based on assessments from 30 experts, nine technologies are ranked against …

Zhengjiao Qi, Yukuan Wang, Jingxian Liu +1

This study applies a wind-constrained Pareto multi-objective reinforcement learning (Pareto MO-PPO) to vessel traffic organization in port approach channels, incorporating wind as both an emission driver and scheduling constraint. In a Caof…