GX & Decarbonization Research

Mohd Nadeem, Ankit Singh, Shreya Yadav +1

This paper proposes a framework using AI for carbon footprint assessment and green AI lifecycle management, aiming to achieve sustainable AI through methodological contributions.

Yuliana Susilowati, Ayubella Anggraini Leksono, Elsa Rakhmi Dewi +5

This study integrates remote sensing and AI to analyze mangrove dynamics and blue carbon potential in Semarang, Indonesia. By applying machine learning to satellite imagery, it maps mangrove changes and estimates carbon storage, providing a…

Ding Q, Anandarajah G, McDowall W

This study integrates AI-enabled social sensing with energy system modeling to identify least-regret VRE pathways, using China as a case. Unlike cost-optimal baselines, the least-regret strategy requires spatially distributed deployment for…

Venios, Stefanos, Velmachos, Thodoris, Georgiadis, Panagiotis +2

This report presents the development of the HarvRESt cloud platform and dashboard for farm energy management. AI models (LightGBM, XGBoost) provide forecasts for PV, wind, demand, biogas, and battery flexibility. A Self-Consumption Maximisa…

Alshahmy S.

This paper explores how artificial intelligence (AI) can enhance the issuance and monitoring of sustainable finance instruments such as green bonds and sustainability-linked loans. AI can streamline issuance processes, improve tracking and …

Onur Sevli

This paper presents a benchmark dataset (1,000 records, 12 features, 3 balanced classes) for classifying carbon footprint of ML model training, grounded in the Green AI emission formula. It adds log-space Gaussian noise (sigma=0.20) to mimi…

Talemwa Byomutonzi Johansen, Mwema Felix Mwema, Silas Mirau +1

This study proposes a hybrid framework integrating regression, time-series, and machine learning models for land-use carbon accounting, demonstrated via a Tanzanian case study. Random Forest and XGBoost showed lower prediction errors, but r…

Shadfar Davoodi, Mohammad Moosazadeh, Geovanny Branchiny Imasuly +3

This review comprehensively overviews the application of explainable AI (XAI) to subsurface carbon capture, utilization, and storage (CCUS) systems. XAI improves interpretability of complex subsurface processes, enhancing safety and efficie…

G Li, Hongxin Guo, Jian Kang +5

This corrigendum refers to a framework that uses machine learning to optimize multi-scale spatial forms within urban blocks for low-carbon performance. It analyzes the relationship between building morphology and energy consumption, aiding …

Sejal Jain, Pranav Singh, Sachin kushwaha +1

This paper presents CarbonLens, an AI-powered carbon footprint tracking and sustainability analytics platform for personal emissions. It uses React.js, Node.js, Express.js, MongoDB, and Ollama-based LLMs to automatically estimate emissions …

Jiapeng Dai

This study examines how forward integration into global value chains affects energy poverty, moderated by governance. Using panel data from 57 economies (2005-2022) and estimators including double machine learning, it finds that forward int…

Hasitha Priyashantha, Imasha S. Jayathissa, Janak K. Vidanarachchi +3

This policy paper synthesizes evidence on climate adaptation and mitigation for livestock systems in South Asia, emphasizing climate-smart interventions including precision livestock farming with AI and sensors, traditional knowledge, and r…

Petteri Siitonen, Samuli Honkapuro, Salla Annala +1

This study uses BERT-based sentiment analysis on 50,000 Finnish social media posts to examine changes in consumer attitudes towards energy technologies and behaviors before, during, and after the 2022 European energy crisis. Results show in…

Erokhin, D.

This study analyzes 553 YouTube videos and 5060 comments on ESG reporting. Videos mostly endorse ESG, but comments show skepticism and concerns about greenwashing and politicization. Low correlation between video and viewer sentiment highli…

Je Hyun BAE, JaeHo Lee, Eun-Chong Kim +1

This study uses Gemini 3 Flash to measure disclosure quality in Korean voluntary sustainability reports. It finds that voluntary reporters have higher ESG ratings, and textual quality and reporting continuity are associated with subsequent …

Yanbing Zhang, Changzheng Zhang, Chengyu Li

This paper investigates the emergence and dissolution of green innovation bubbles among Chinese power industry chain enterprises from 2016 to 2023. Using the AMO framework and double machine learning (DDML), it identifies causal drivers, an…

Bartholomew Paudyn

This paper critically examines ESMA's Strategy 2023-28, focusing on how AI and machine learning in ESG ratings may hinder sustainable finance and technological innovation. It argues that algorithmic decision-making exacerbates greenwashing …

(著者不明)

This book provides a comprehensive exploration of how finance, technology, governance, and social behavior are being transformed to address climate change. It focuses on how AI, blockchain, and IoT are redefining climate accountability and …

Shikder S.H.

This paper proposes an AI-driven framework for green finance and environmental monitoring in Bangladesh, addressing data deficits. It conceptualizes how AI can integrate financial and environmental data to support green investments, though …

Li Y.

This study empirically tests whether LLMs can replace human reading in analyzing sustainability reports. It provides evidence on the accuracy and efficiency of LLMs for information extraction and evaluation, highlighting the potential for A…