GX & Decarbonization Research

N. Albelwi

This paper introduces FedCarbon, a federated learning-based building stock modeling system that enables collaborative embodied carbon benchmarking without central data aggregation. Using hierarchical federated aggregation with attention-bas…

N. Albelwi

This paper proposes DT-LCAF, a digital twin-enabled LCA framework for real-time embodied carbon optimization in construction. It integrates BIM, IoT, and ML (graph attention networks and reinforcement learning), validated on proxy data from…

S. Ren, Min Chen

This study proposes a data-driven scheduling strategy for the Ship Integrated Energy System (SIES). Using LSTM for fuel consumption prediction and NSGA-II for multi-objective optimization, it simultaneously reduces CO2 emissions and costs. …

Zhihan Qiu

This paper examines the application of digital technologies (IoT, big data, AI) in ship energy efficiency management to comply with IMO regulations like CII. It analyzes practices in fuel monitoring, route optimization, and power control, i…

Raoua NACEIRI MRABTI

This paper applies AI-based optimization to green hydrogen export corridors from Morocco to Europe. Using machine learning on simulated data for road, pipeline, and sea transport, it finds that trans-Mediterranean pipelines are the most cos…

Bin Xu, Luyang Wang, Tingting Xiang +1

This study proposes a machine learning-enhanced tri-objective optimization framework for stowage planning of finished steel maritime logistics. It simultaneously maximizes deadweight utilization and minimizes carbon emissions, achieving 99.…

Shiwei Zhou, Xinglong Liu, Feng Zhang +1

This paper proposes a genetic algorithm (GA)-based ship path optimization framework that uses AIS data to incorporate wind speed and ocean currents, aiming to minimize fuel consumption and carbon emissions. Evaluated on real AIS datasets, i…

Aniruddha Bora, J. Chalfant, C. Chryssostomidis

International shipping accounts for ~3% of global GHG emissions, but routing remains heuristic. This paper presents PIER, an offline reinforcement learning framework integrating physics-informed state construction, that reduces mean CO2 emi…

Doru Coșofreț, Florin Postolache, Adrian Popa +2

This paper proposes a hybrid digital CO2 emission-control technology for maritime transport using physics-informed adaptive speed optimization. It integrates exact optimization (Backtracking, Dynamic Programming) with reinforcement learning…

Juei-Cheng Jao, Muhammad Hanzla Alvi

This paper examines legal frameworks for Maritime Autonomous Surface Ships (MASS) in the context of maritime decarbonization. It argues that existing conventions designed for crewed vessels create gaps in safety, cybersecurity, and liabilit…

M. Spalding

This paper comprehensively examines AI's role in maritime decarbonization and ocean conservation. It analyzes applications in voyage optimization, wind-assisted propulsion, vessel automation, port coordination, predictive maintenance, ship …

Dimitra Palantza, Konstantinos Karyotis, Judit Torres Fernández del Campo +2

This study develops a hybrid machine learning and remote sensing framework for high-resolution soil organic carbon (SOC) mapping in Mediterranean agroforestry systems. Using Sentinel-2 data and environmental covariates, the model achieves R…

Md. Fardous Hasan Bappy

This paper compares meta-heuristic optimization algorithms with commercial solvers for designing resilient hybrid microgrids aimed at industrial decarbonization. It analyzes how AI-driven optimization can enhance energy efficiency and cost …

Simin Huang, Lin Yang, Jing Meng +4

This study develops a machine-learning optimization framework to quantify how five enabling technologies (hydrogen, storage, grids, electrified transport, CCUS) shape decarbonization, equity, and resilience goals. It finds investment distri…

Adekola Priscilla

This study analyzes the spatial spillover effects and dynamic evolution of agricultural carbon sinks in China under the dual-carbon goals. Using panel data from 30 provinces (2000-2022), it employs spatial econometric models (Spatial Durbin…

Jesús Pérez Expolio

This paper proposes a combination of machine learning and quantum variational sampling to optimize carbon capture systems under uncertainty. It applies AI/ML techniques to enhance CCUS process efficiency and cost reduction, promising indust…

Deepti Singh, Rakesh Kumar, Pooja

This study applies AI (ANN, RF, and GA) to optimize self-compacting concrete (SCC) mix designs, achieving 21–29% carbon emission reductions across grades M20–M60 while maintaining strength and workability. Using a dataset of 120 mixes, ANN …

Mohaddeseh Azimi, Zhengfu Bian, Narges Salehi Shahrabi

This study uses machine learning to analyze the associations between carbon intensity, labor productivity, and income inequality in China's energy sector. It provides quantitative insights into how the decarbonization transition may affect …

Alessandro Sura, EMANUELE DI VENTURA

This study compares stakeholder engagement in EFRAG and ISSB sustainability standard-setting using NLP. Sentiment and topic analysis of comment letters reveals that EFRAG shows balanced sentiment and broader thematic focus, while ISSB empha…

Murali Krishna Pasupuleti

This book proposes a framework for 'Green Intelligence Digital Twins' - computational models that integrate uncertainty quantification, causal inference, trustworthy machine learning, and lifecycle engineering to support climate-resilient, …