GX & Decarbonization Research

Yuhao Gu, Han Lai

This paper explores how FinTech (blockchain, AI, big data) enhances green finance efficiency through environmental transparency, risk mitigation, and green innovation. Empirical results show blockchain improves disclosure authenticity, AI r…

K. Logožar

This paper proposes the VAF framework, arguing that smart ports can serve as governance infrastructures that make maritime flows visible and accountable. It integrates digital technologies like AI, digital twins, and blockchain with governa…

V. Vignesh, G. V. Narendran, R. Senthil Kumar +1

A hybrid framework integrating Fuzzy C-Means clustering with temporal deep learning (NARX, RNN, LSTM, GRU) is proposed for multi-parameter forecasting in blast furnaces. Evaluated on 43,396 industrial DCS samples, FCM-GRU achieved the best …

Andreas Poyias, Panayiotis Mourtopallas, Diamanto Platanou +3

This study develops a digital framework for optimizing green hydrogen integration in food industry steam production, which accounts for up to 57% of energy use. LightGBM models trained on PV and weather data achieve high forecasting accurac…

Firat Bolat, Hande Demi̇rel

This study integrates Sentinel-5P TROPOMI satellite observations with AIS data to monitor ship emissions in the Istanbul Strait, estimating annual CO2 of 213,678 t, NOx of 5,970 t, and SOx of 686 t. A correlation of 0.76 between AIS-derived…

Kejun Xie

This study examines the relationship between board environmental expertise and carbon disclosure quality (CDQ) using 28 ASX-listed firms. Analyzing 140 firm-year observations from 2019-2023 with Tobit regression, it finds a significant posi…

Kjartan Sigurðsson

This chapter analyzes AI's transformative role in sustainability reporting, particularly ESG, arguing it represents institutional change rather than mere technological improvement. It examines how blockchain, generative AI, and real-time mo…

Patrycja Hąbek, Kjartan Sigurðsson, Małgorzata Radomska

This paper examines the impact of AI on sustainability reporting. It discusses how AI can automate ESG data collection, analysis, and disclosure, enhancing efficiency and accuracy. It also addresses challenges and regulatory implications of…

Dajiang Liu, Tao Yu, Huiying Xu

This paper proposes a GAT-LSTM hybrid model for dynamic carbon footprint accounting in prefabricated steel structure buildings, integrating spatio-temporal data to estimate emissions across the construction process. It overcomes limitations…

Thing-Yuan Chang, Chien-Chih Chen, Chin-Hsien Hsu +2

The food supply chain emits 13.7 billion tons of CO2e annually, yet accurate Product Carbon Footprint (PCF) estimation is inaccessible to many manufacturers. This study proposes a machine learning framework combining Gaussian Mixture Model …

Tarak Barhoumi, Najoua Mezghani

This paper proposes CarbontoScope IA–SFAX, an augmented intelligence system to visualize urban carbon footprints, applied to Sfax, Tunisia. It identifies hidden emission sources, providing data for urban planning and policy. Integrating AI …

Paul Kron

This paper estimates the carbon cost of a large language model (LLM) query using life-cycle analysis and greenhouse gas emissions, calculating an ultimate cost of approximately $0.4 per query (about 10 gCO2eq/query) for future generations. …

Dara Ghahremani

This repository provides a machine-readable corpus of annual reports from European listed banks (2013-2023), along with scripts and an ESG dictionary for text analysis. It supports reproducible ESG disclosure research, including term-densit…

Małgorzata Radomska

This chapter analyzes the relationship between sustainability reporting and AI from a regulatory perspective. ESG disclosure and AI regulation have developed separately, leading to fragmentation and practical challenges. It maps key legisla…

P. Vibin Sri Balaji, Srinivasan R

This study proposes an AI-based framework integrating satellite data and machine learning to identify optimal solar plant sites and forecast 10-year energy output. Using NASA POWER data and Random Forest regression, it achieves high predict…

P. Vibin Sri Balaji, Srinivasan R

This study integrates satellite data and machine learning to identify optimal solar installation sites and forecast 10-year energy output. Using NASA POWER data and physical PV modeling, Random Forest achieves high predictive accuracy (R²≈0…

Jacopo Ghirri, Carlos Rodriguez-Pardo, Lara Aleluia Reis +1

Using deep learning on high-resolution socioeconomic and sectoral data, this study projects EU27 CO2 trajectories to 2030 under current trends. It finds emissions will exceed the 2030 target by 35% (620 Mt shortfall), with only a minority o…

Kaithari D.K.

This review surveys AI systems for real-time monitoring and optimization of ocean-based carbon capture, utilization, and storage (CCUS) networks. It synthesizes how AI enhances efficiency and risk management in carbon capture and storage, a…

Yihsu Chen, Abel Souza, Fargol Nematkhah +1

This paper models power markets where hyperscalers shift LLM inference workloads to modular datacenters co-located with renewables. It reveals that contract reshuffling can undermine emission reductions from cleaner procurement, and that fo…

J. Z. Lin

This study constructs a financial health rating system using Deep Belief Networks (DBN) to classify enterprises into seven tiers. Using 2,486 firm-year observations from 247 textile, apparel, and leather companies listed on Shanghai-Shenzhe…