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 641–660 of 986 papers
Siddique AB
This paper proposes a thermodynamics-informed graph learning approach for predicting CO2 solubility in brines, crucial for dissolution trapping in CCUS. Tested on 3323 records, graph-based descriptors improved relative error but boosted tre…
Minh Phuoc Bui, Mien Thi Ngoc Nguyen
This study analyzes ESG disclosure patterns in sustainability reports of Vietnamese commercial banks using PhoBERT-based text mining of 25 reports. Findings show disclosure concentrated in governance, especially corporate governance, follow…
Salil Seth, Mohd Irfan Pathan, Lokesh Tomar
This paper applies the BERT model to analyze consumer reviews and social media posts for sentiments on decarbonization, sustainability, and waste management in retail. Offline shoppers are more critical of waste practices, while online shop…
Zhai G.
This paper applies machine learning and GARCH-MIDAS models to assess climate uncertainty in green bonds. It estimates the contribution of climate risk factors to green bond yield spreads. The findings indicate that climate uncertainty signi…
Taneja S.
This paper proposes an AI-driven green finance framework for the chemical industry to accelerate SDG-12 (responsible consumption and production) compliance. It uses AI to analyze sustainability data, automate financing decisions, and evalua…
Bashar A.
This study applies topic modeling to bibliometric data on sustainable finance, identifying emerging themes such as green bonds, ESG investing, and climate risk. It provides a structured overview of research trends for scholars.
Ayodele O.F.
This paper analyzes how the choice of activation function affects the accuracy and interpretability of neural network models that capture the nexus between carbon tax, CO2 emissions, and gas-fired power plant parameters. It contributes to A…
Gunasiri B.D.T.S.
This paper proposes an AI-assisted method for ESG disclosure analysis in beach hotels, using NLP and machine learning to extract and assess environmental, social, and governance information from reports. It contributes to automating ESG pra…
Das P.
This paper proposes a machine-learning model to predict solar power generation for a net zero energy building (NZEB). The model improves prediction accuracy, enabling efficient renewable energy use and optimized building energy management, …
Leong W.Y.
This paper proposes a generative AI approach for urban planning to achieve net-zero emissions. It optimizes land use, transportation, and energy systems, enabling efficient urban designs through simulation.
Chhatwal M.
This paper examines how generative AI and digital transformation can contribute to business sustainability, particularly achieving net-zero goals. It explores AI-driven optimization in energy management, supply chain, and emissions tracking…
Nikhil Jarunde
This paper proposes a unified framework using LLMs and generative modeling to construct transparent, regulation-ready trading strategies that integrate ESG information. It includes an LLM-powered ESG sentiment engine, automated scenario gen…
Vinuri Nilanika Goonetilleke, Muditha K. Heenkenda, K. Zaniewski
This review synthesizes how indoor mapping technologies (LiDAR, SLAM, deep learning-based floor plan extraction) contribute to reducing greenhouse gas emissions from buildings. Integration with Digital Twins, BIM, GIS, and IoT enables impro…
Abdullah Kursat Merter, Yavuz Selim Balcıoğlu
This study proposes a TabTransformer-based framework to predict environmental outcomes of energy sector M&A using ESG and financial data from 1000 transactions (2018-2023). ESG factors account for over one-third of predictive power, with po…
Bowei Zeng, J. Niu, Gefan Yang +4
This study develops a physics-guided deep learning framework for urban flood prediction, integrating U-Net, Bidirectional LSTM, and multi-head attention with physics-informed loss functions (gradient consistency, spatial smoothness). Using …
Ke Ren, Weiyu Zhang, Haoxiang Chang +3
This paper proposes a method for carbon price forecasting that models lead-lag relationships among market participants using dynamic graphs and provides uncertainty intervals, potentially improving prediction accuracy and interpretability.
Xin Cheng, Peisi Xu, Sylvie Van Damme
This study develops a framework integrating text mining (Jieba segmentation, dictionary matching) and image classification of social media data to evaluate cultural ecosystem services (CES) from nature-based solutions (NBS) in urban renewal…
ylm0216
This repository provides a reinforcement learning tool for learning optimal trading strategies in carbon credit markets. v1.0.0 is the initial release, including the foundational environment and agent models.
Arda Aktaş, Miguel Poblete-Cazenave
This study uses causal forests to estimate heterogeneous effects of residential energy technologies on health and economic outcomes in India. Combining climate policies with a full transition to clean fuels yields larger reductions in sickn…
Hoeser, Thorsten, Bachofer, Felix, Kuenzer, Claudia
DeepOWT is a globally accessible dataset of offshore wind turbine locations derived from Sentinel-1 SAR imagery using deep learning object detection. Version 4.25.1 enriches dense time series with deep learning event predictions (e.g., depl…
Browse by Topic