GX & Decarbonization Research

Yuchen Du, Daniel Jacome, Jianghao Wang

This study optimizes fine-tuning of the Prithvi Earth Foundation Model using Multidimensional Latin Hypercube Sampling (LHS) for small-scale burn scar identification. LHS outperforms Simple Random Sampling, achieving 0.91 mIoU and retaining…

Murali Krishna Pasupuleti

This study positions AI as an environmental intelligence infrastructure for climate-risk assessment, emissions monitoring, and decision support. Using official data, it proposes a transparent prioritization model ranking major emitters by m…

Claudia Banciu, Adrian Florea

This review examines the convergence of AI and IoT (AIoT) for climate change management in smart cities. A bibliometric analysis of over 3700 articles reveals rapid growth, with waste management and air quality monitoring as leading applica…

Zhanyi Li, Zhanhong Liu, Chengping Zhou +2

This paper proposes an AI-driven framework for smart campus microgrids that integrates an enhanced multi-scale gated temporal attention network (MS-GTAN+) for meteorological hazard prediction, a multi-intelligence co-optimization algorithm …

Yuliang Hu, He Wang, Y. Duan +7

This review systematically analyzes all-solid-waste cementitious materials (ASWs) from industrial waste. It covers activation strategies for precursors like fly ash and slag, synergistic waste design, and machine learning for mix optimizati…

By Marjan Ilbeigi, Mohamed Alnejem, Mozhgan Karimi +4

This study proposes an integrated framework combining Lifecycle Assessment (LCA), Circular Economy (CE) evaluation, Multi-Criteria Decision Analysis (MCDA), and Artificial Neural Network (ANN) modeling to assess bio-based retrofitting strat…

Zeeshan Tariq, A. Bahadori‐Jahromi, Shah Room +1

This study develops multiple ensemble machine learning models with explainable AI (SHAP) to predict compressive and tensile strength of concrete incorporating fly ash and ground granulated blast furnace slag. The optimal hybrid mix (GF4) wi…

Suhib O. A. Amro, S. Naimi, A. Ibrahim

This paper proposes an AI-driven method to jointly optimize scheduling, risk, and sustainability in BIM-enabled construction project management. By explicitly including sustainability as an objective, it enables holistic decision-making tha…

Sachin Venu Jaya, V. Swarnakar, A. Acquaye +2

This study develops an integrated BIM-AI framework to enhance value engineering in construction, focusing on material optimization and resource management for circular economy. Using PRISMA-based literature review and Delft Ladder approach,…

M. S. Deore, D. P. D. Nemade

This study evaluates geopolymer concrete (GPC) using fly ash and GGBS, incorporating AI modeling to compare mechanical, durability, and environmental performance against conventional concrete. Findings show significant CO2 reduction and lif…

Arthur J. Sterling, Marcus P. Thorne, Julian T. Harrow

This paper integrates Lifecycle Assessment with a Multi-Objective Optimization model using a genetic algorithm to select sustainable construction materials. Applied to a mid-rise commercial building, it simultaneously minimizes lifecycle co…

M. Al-Jamal, Ayooub Alsarhan, Wafa' Q. Al-Jamal +4

This study presents a digital-twin-ready decision-support framework integrating BIM and AI-enhanced LCA. Machine learning surrogate models (Random Forest, Gradient Boosting, ANN) predict mechanical performance and lifecycle indicators (CO2,…

F. Pacheco-Torgal

This paper systematically reviews the role of AI in decarbonizing and enhancing resilience of the built environment. It maps AI applications across the building lifecycle—including generative design, predictive maintenance, digital twins, a…

Linda Cusumano, Mats Granath, N. Olsson +1

This study integrates set-based design with genetic algorithm (NSGA-II) optimization to simultaneously minimize cost and embodied carbon in early building design. Applied to a reference building, the genetic algorithm alone reduced carbon b…

Chanhyeok Kang, Bokyung Jung, Taekyu Lee +2

This study proposes a practical framework for estimating embodied carbon in buildings using automated IFC model generation and machine learning correction. With minimal inputs (gross floor area, floors, etc.), baseline emissions are compute…

A. Nawarathna, Zaid Alwan, Barry J. Gledson +1

This study develops a multiple linear regression model for early-stage embodied carbon (EC) estimation using data from 25 office buildings in Sri Lanka. Gross internal floor area (GIFA) and external wall area (EWA) are the most influential …

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. …

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.…

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…