GX & Decarbonization Research

Amayrol Zakaria, Shamila Azman, Khairul Anuar Mat Saad +2

This paper systematically reviews AI-driven decarbonization strategies for maritime ports using PRISMA and bibliometric analysis. It identifies key research trends and highlights AI's role in enhancing operational efficiency and reducing em…

Hakpyeong Kim, Jun‐Ki Choi, Taehoon Hong

This study proposes a graph neural network-based input-output framework to estimate construction supply chain carbon footprints, enhancing the accuracy of Scope 3 emissions accounting with AI.

Abhishek N. Srivastava, Arun Krishna Vuppaladadiyam, Rakhi Punnadan Koroth +8

This review explores how AI-driven circular economy approaches can transform waste management, reduce GHG emissions, and recover resources. It proposes a three-level CE framework (micro, meso, macro) and discusses challenges in implementati…

Xuandong Zhang, Yankui Su, Jinjiang Li +1

This study proposes a method using digital trace data (mobile phone signals, POI check-ins, traffic data, etc.) to predict low-carbon urbanization. A hybrid model combining spatiotemporal graph convolutional network and LSTM identifies carb…

Subhodeep Mukherjee, Ruchi Sharma, Rashmiranjan Panigrahi +1

This systematic review examines how digital technologies (IoT, blockchain, AI, big data) enhance circular supply chain (CSC) performance. Four themes emerge: use of digital tech to optimize CSC processes, key industries (manufacturing, elec…

Jasmine Selvakumari Jeya Israel, Aldrin Joan Pandian William, Pradeep Kumar Mishra +1

This study proposes a Bi-LSTM-based approach to optimize emission forecasting, carbon offset allocation, and green fund utilization for steel, cement, and aluminum industries. Bi-LSTM demonstrates superior performance in long-term predictio…

Shamsun Nahar, Florina Rahman, Mahrima Akter Mim

This paper presents an AI-integrated platform combining renewable energy and data analytics for corporate ESG compliance. It uses AI/ML for energy demand forecasting, carbon emission estimation, and automated ESG reporting aligned with inte…

C. Rao, Praveen Kumar Naidu Rayanki, Polepalli Rajeev Meenon +2

This paper proposes a privacy-preserving cross-chain federated blockchain-IoT framework for carbon credit management, integrating RFID-based emission data collection, IBC interoperability, and DP-FL for fraud detection and price prediction.…

Shaena Ulissi, Andrew Dumit, P. James Joyce +4

This paper proposes evaluation criteria for AI-assisted product carbon footprinting (PCF) systems, using mapping and supply chain modeling as case studies. It offers a framework assessing accuracy, data quality, scalability, and other dimen…

Aria Dolatabadian, Khalil Kariman

This review compares classical and machine learning (ML) approaches for soil organic matter and carbon analysis. ML techniques like random forests and neural networks improve prediction accuracy and scalability, but the paper concludes that…

SangYoun Kim, T. Woo, Usama Ali +8

This systematic review of 906 publications (2016-2025) categorizes AI applications into flue gas treatment, air quality management, and CO2 capture. It identifies a shift from traditional monitoring to AI-driven surrogate modeling and gener…

Taedong Lee, Sinjae Kang, D. Utami +1

This study analyzes 634 sustainability reports (2014-2024) from the top 200 Korean firms using Structural Topic Modeling (STM). It identifies 13 topics and a phased shift: CSR and basic environmental management (2014-2018); workplace safety…

Manav Gangar, Nikhil D'Souza, Rishika Kapasi +2

This paper proposes a machine learning framework for detecting greenwashing by combining supervised classification and unsupervised anomaly detection. It introduces a Greenwashing Discrepancy Score (GDS) to quantify the mismatch between fir…

Ivan Savin (5189054), Mateo López Carel, Eva Schlindwein

Using computational linguistics on 1,477 ESG reports from STOXX Europe 600, this study identifies 34 main topics (six environmental). It finds that topics like sustainable value chains and renewable energy correlate with improved environmen…

Mengxi Xie

This dissertation combines machine learning (NLP) with econometrics to empirically analyze environmental policies. The first three studies examine the EU's Carbon Border Adjustment Mechanism (CBAM) via meta-analysis, US equity market reacti…

Ahmed G. Abo-Khalil

This paper proposes a unified framework integrating AI-driven renewable forecasting, grid economics, and lifecycle assessment. Using deep learning, it reduces prediction errors by 50% and operational costs by 18.7%. The study includes AI en…

Chris Meniw

This whitepaper analyzes the dual role of AI: optimizing power grids and integrating renewables while increasing energy and carbon footprint from compute infrastructure. It examines deployments in smart grids, industrial optimization, and r…

Kowalik R.

This paper reviews AI applications in photovoltaic-integrated buildings, covering energy forecasting, intelligent control, and net-zero performance. It demonstrates the effectiveness of machine learning and optimization methods. The study e…

Zhang H.

This paper proposes a machine learning-based method to assess the risk level and analyze the impact range of CO2 pipeline leakage in CCUS, contributing to the safety of decarbonization technologies.

Obaid Ullah, BenYan Tan, Ali Zeb +1

This paper applies machine learning to examine how artificial intelligence, carbon pricing, and green finance affect renewable energy affordability in advanced economies. It quantifies the impact of policy interventions and identifies drive…