GX & Decarbonization Research

Iqra Mubeen, Samina Rauf

This paper investigates whether ESG sentiment generated by LLMs can predict portfolio risk. It finds that positive ESG sentiment correlates with lower volatility and downside risk, while negative sentiment increases risk exposure. LLMs outp…

Shuai Li, Pei Yu, Z J Yang +1

This supplement accompanies research applying machine learning (XGBoost, Bayesian optimization) to low-carbon concrete mix design. It includes material-stage emission factors, optimized hyperparameters, minimum-embodied-carbon candidate mix…

Ummesara ., Chaitanya Kumar Sahu, R Ranjith +5

This review integrates trends in AI-enabled regenerative agriculture (RA) to promote climate resilience. AI tools (ML, remote sensing, IoT) enable dynamic monitoring of soil/crop health, carbon accounting, and adaptive farm management, acce…

D. R, Santhosh Kumar A G

This secondary data analysis (2020-2025 sources including Bloomberg, MSCI, World Bank) examines AI's role in ESG integration and sustainable finance. It finds that NLP and ML improve ESG data coverage by up to 40% and enhance climate risk p…

Murali Krishna Pasupuleti

This paper proposes the Generative Climate-Aware Deep Hedging (G-CADH) framework, which combines deep hedging with generative market models to manage portfolio risk and financial resilience under climate change. It integrates a conditional …

Anuj Pal

This study evaluates the ability of large language models (LLMs) to distinguish between symbolic and substantive sustainability communication in ESG disclosures. It constructs a dataset from annual and sustainability reports of publicly lis…

Krasteva-Hristova R

This exploratory study analyzes the 2024 UK transparency reports of Deloitte, EY, KPMG, and PwC to assess governance disclosures for AI-assisted professional judgment in audit and sustainability assurance. It develops a seven-dimension AI-J…

Kodela, Kalyan Chakravarthy, Roy, Stabak, Ghorbanzadeh, Shaghayegh +2

This paper proposes the Spatio-Temporal Graph Multi-Agent Carbon Flux Model (STG-MACFM), a learning-driven framework within a GeoAI-enabled digital twin. It uses hierarchical agents, reinforcement learning, and graph attention networks to d…

Poorvika N.

This paper proposes a framework integrating AI-powered digital twins and zero-trust security for predictive maintenance of net-zero assets, aiming to enhance grid reliability and optimize renewable energy asset operations.

Yifan Duan, Si Zheng, Lihuan Li +2

GHGbench provides an open dataset and benchmark for company- and building-level greenhouse-gas prediction. The company track covers 12,000+ firms with Scope 1+2 and Scope 3 disclosures; the building track harmonizes 491,591 records from 13 …

Yanming Guo, Charles Guan, Jin Ma

ExioML is an open-source dataset of environmentally extended multi-regional input-output tables for emission factors, covering 49 regions and 28 years (1995-2022). It includes GPU-accelerated computational tools and two aggregation schemes …

Triana Arias Abelaira, María Jesús Guillén Palomino, Lázaro Rodríguez Ariza +1

This study uses a bibliometric approach to analyze 221 articles on climate risk in finance, focusing on the integration of AI techniques. It finds that NLP and digital transformation are key themes, linking AI innovation policies to greenwa…

Anuj Pal

This paper uses Large Language Models (LLMs) to evaluate corporate ESG disclosure quality by distinguishing symbolic from substantive sustainability communication. It introduces the Operational ESG Disclosure Coding Framework (OEDCF) and co…

Radosveta Krasteva-Hristova, Vanya Georgieva

This conceptual article examines how AI can support sustainability assurance under CSRD, ESRS, ISSA 5000, and the EU AI Act. It explores applications such as disclosure identification, ESRS mapping, anomaly detection, greenwashing risk scre…

Weixiang Xu, Yi-Fan Shi, Jinhui Zheng

This study uses panel data from cities in the Yangtze River Economic Belt (2011-2021) to empirically analyze AI's impact on urban green and low-carbon development. Applying dual machine learning and spatial Durbin models, it finds that AI p…

Lin K.

This review comprehensively examines the application of machine learning (ML) to CO2 geological storage. It covers predictive modeling, site selection, monitoring, and risk assessment, highlighting how ML enhances storage efficiency and saf…

Šribar, Jernej, Mohorcic, Mihael, Čampa, Andrej

This paper proposes CoMAD V2G, a multi-agent deep reinforcement learning framework for coordinated management of V2G-enabled EVs and shared energy storage in Positive Energy Districts. Validated with real-world datasets, it reduces grid rel…

Sayyed Sadaqat Hussain Shah, Arshad Javed, Muhammad Mahboob Khan +2

This study examines how AI adoption influences green bond issuance and corporate ESG scores using panel data from 54 economies (2019-2024) and multiple models (fixed-effects, quantile regression, TVP-VAR-SV). It finds that a one-standard-de…

Meng-Sian Chen, Jing Wang, Mengfei Peng

This paper proposes a bi-objective optimization model for virtual power plants (VPPs) integrating wind, PV, storage, and gas units, using the NSGA-II algorithm to minimize total cost and carbon emissions. A case study reveals a trade-off be…

Yun-Kae Kiang, King H. Lam

This paper proposes ReGMS, a retrieval-grounded multi-agent architecture for climate scenario analysis to support IFRS S2/TCFD reporting. Specialized LLM agents coordinate to build and verify transition and physical-risk scenarios. Using NG…