This page provides an English interface to the gxceed GX paper corpus. The corpus aggregates papers from 14 contributing scholarly metadata sources and uses AI-assisted classification to identify signals related to measurement, policy narratives, outcomes, implementation, industrial adoption, and verification.
The goal is not only to discover papers, but to observe how GX research is distributed across research substance, implementation narratives, external expectations, implementation substance, and judgment formation.
Summaries are AI-assisted. Always refer to the original paper for authoritative conclusions.
Showing 141–160 of 394 papers
A. Pournaghshband, F. Piadeh, Mohsen Ahmadi +1
This study develops an AI-driven decision-support framework integrating LCA, scenario-based material substitution, mixture-of-experts neural networks, and sustainability optimization. Using a UK office building case study with 1500 scenario…
Vlatka Bilas, Tomislav Radoš, Lana Frkovic
This study examines whether ESG ratings provide useful information for credit risk assessment in an emerging EU member state, using Croatian firm data from 2024-2025. Combining econometric models and random forest prediction, the findings s…
Shuangxiang Zeng, Lisha Dong, Jingtao Shao +2
This study optimizes carbon purification from spent cathode carbon (SCC), a hazardous waste from aluminum production, using machine learning. Six algorithms were compared, and LightGBM was tuned via RSM, orthogonal design, and local optimiz…
W. -J. Bai
This study develops an early warning system for green transportation financial risks using PCA for dimensionality reduction and an improved PSO-optimized SVM. Integrating financial, environmental, policy, and market indicators, it achieves …
K. K. Qin, Yu Zheng, Chao Zeng +1
This paper proposes a low-carbon scheduling and carbon emission prediction framework for power grid construction machinery by integrating an improved genetic algorithm (IGA), deep reinforcement learning (DRL), and a gated recurrent unit (GR…
Fu Jia, Yingjie Ju, Robert D. Klassen +2
This study examines how China's carbon emissions trading schemes (CETS) affect firms' environmental and social (E&S) disclosure using an institutional theory framework. Exploiting staggered CETS implementation (2013-2024) as a quasi-natural…
Mitch D
This paper proposes OptimTwin, an integrated framework combining AI-driven digital twins and power system asset management to support long-term grid investment planning. Using IRENA FlexTool and a deep neural network surrogate on the IEEE/N…
Wattana Viriyasitavat, Phoranee Rhuwadhana, Ra-Pee Pattanapanyasat +5
This study conceptualizes digital infrastructure (DI) as a socio-technical design space where sustainability is embedded by design rather than assessed post hoc via ESG reporting. Using PRISMA-based systematic review and realist synthesis, …
Mega Silvia, Deyan Zhao, Donghuan Bai +11
This study examines whether credible climate transition plans are associated with subsequent carbon performance among Fortune Global 500 non-financial firms. Using panel data from 239 firms (2018-2023), a Climate Transition Plan Credibility…
Abdul Kadar Muhammad Masum, Md. Abul Kalam Azad, Najmus Saadat +3
This study proposes a Deep-Tree Fusion (DTF) framework integrating tree-based logic with deep learning to improve ESG score prediction. Using 11,000 firm-years from 2015-2025, DTF achieves R²=0.97866, outperforming 10 baseline models. It of…
Rejaul Karim, Md. Mustaqim Roshid, Bablu Kumar Dhar +1
This study uses bibliometric methods to analyze 72 Scopus-indexed papers (2019-2024) on green fintech, focusing on climate finance, digital innovation, and environmental governance. It identifies key technological domains such as blockchain…
Inyangala¹ A, Waswa¹ AK, Angeyo² HK
This study develops an explainable stacked ensemble machine learning framework for rare earth element (REE) prospectivity mapping in the Ruri Carbonatite Complex, Kenya. Combining geological, geochemical, and radiometric data, the model ach…
A Joy and Yasmin Shaik F
This paper critically examines the environmental footprint of AI development and deployment, including energy, carbon, water, e-waste, and minerals. Data centre electricity hit 415 TWh in 2024, with AI workloads surging 50% in 2025, project…
Fiona Lippert, Andrew Gerald Barr, Marcos Herreras-Giralda +7
GHG retrievals rely on costly physics-based forward models, limiting real-time processing. This study develops neural network emulators for Sentinel-5, comparing end-to-end and hybrid approaches. The hybrid method achieves high accuracy (<1…
Suhib O. A. Amro, Sepanta Naimi, Changiz Ahbab
This paper proposes an AI-driven generative design framework integrating machine learning surrogates with NSGA-III and PSO to optimize building renovation for net-zero performance. Validated on 12 European case studies, it achieves 84.7% op…
Yanan Li, Dan Shi, Xiaojiao Qiao +1
Using data from Chinese A-share listed firms (2009-2023), this study shows that focal firms' digital transformation significantly reduces carbon emission intensity of upstream suppliers and downstream customers. Supply chain concentration a…
Francesco Sotti, Elettra Giulia Beatrice Bandi, Patrizia Tettamanzi
This study empirically analyzes how digitalization in sustainability reporting affects the textual quality (clarity, conciseness, tone) of non-financial disclosures among Italian listed companies. Against the backdrop of regulatory tighteni…
Ahlam El Ferrad, Aya Klaffa, Mohamed Oudgou +1
A systematic bibliometric review following PRISMA guidelines examines the link between digitalization, AI, and ESG disclosure using Scopus data. It finds 56% annual growth, concentration in China, and underrepresentation of Africa. Digitali…
Esther Curtin, Kerry A. Brown, Elizabeth McGill +3
This cross-sectional study quantified greenhouse gas emissions of 205 AI-generated recipes from a health app using LCA data. Plant-based recipes had lowest emissions, while red meat recipes were over fourfold higher than seafood/poultry. Mo…
Okon Udo Frank, Julius U. Akpabio, Aniefiok Livinus
This study develops AI models (ANN and SVR) to predict CO2 trapping efficiency with high accuracy, validated on 260 data points from a gas flare site in the Niger Delta. The ANN model achieved R2=0.9993, and CO2 mass fraction was the most i…
Browse by Topic