GX & Decarbonization Research

Xiaobing Yu, Haitao Zhang

This paper proposes a UCB–Q-value assisted differential evolution algorithm for low-carbon microgrid scheduling with flexible loads. It optimizes operational plans to reduce carbon emissions while accommodating demand flexibility. Experimen…

(著者不明)

Using double machine learning on 266 Chinese cities (2010-2020), this study finds that the Low-carbon City Pilot and Innovative City Pilot both significantly enhance urban carbon neutrality performance, with notable synergistic effects. Mec…

Run Liu

This dataset provides multivariate time series data from three pilot carbon markets (Beijing, Hubei, Shenzhen) including a unified dataset with imputed missing values. Accompanying code includes cross-market correlation, nonlinear causality…

Mustafa Çağrı Peker

This study applies machine learning (Perceptron and Decision Tree) and the Multi-Level Perspective framework to model the energy transition in Türkiye's road transport sector. It identifies entrenched fossil fuel infrastructure, taxation, a…

Assunta Di Vaio, Elisa Van Engelenhoven, Anum Zaffar +1

This study analyzes sustainability disclosures of two European ports (Rotterdam and Hamburg) that have implemented digital twin (DT) technology. Using automated thematic extraction via Leximancer and manual coding of 36 documents (sustainab…

Aversa D.

This study empirically analyzes the relationship between banks' sustainability disclosures, climate change, and central banks using NLP on unstructured data. It evaluates disclosure quality and climate risk management, offering insights for…

Leong W.Y.

This study leverages AI to optimize renewable energy deployment and operation, proposing pathways for emission reduction. Machine learning models predict energy supply-demand and formulate cost-effective decarbonization strategies.

Si Zheng, Yifan Duan, Chao Xue +1

This paper proposes Scope3Trace, a framework that extracts Scope 3 GHG emissions from sustainability reports using LLMs with evidence grounding. It integrates PDF parsing, OCR, table reconstruction, and hybrid rule-LLM extraction to obtain …

Xinyu Tang, Mingzhu Tang, Na Li +1

This paper proposes ConvTimeXer, a hybrid model combining bidirectional temporal convolution and TimeXer for carbon price forecasting. Experiments on China's carbon market data over three years demonstrate high accuracy and robustness, effe…

Yue Wang, Waya Zhao, Wenli Ye +2

This study uses spatial DID and double machine learning on 30 Chinese provinces to examine how digital government development and regional e-commerce ecosystem competitiveness drive the low-carbon energy transition. Digital government has l…

Thi Huong Dinh, Nhung Hong Nguyen, Ngoc Quang Nguyen +1

This paper examines how AI and green transformational leadership affect low-carbon practices in the Vietnamese hospitality industry using PLS-SEM. It finds that AI positively influences green innovation culture and low-carbon behavior, medi…

Ángeles Montserrat Govea Franco, Saúl Domínguez Casasola, Heriberto Salazar-Soto

This study uses machine learning (k-prototypes clustering and ANN) to analyze the effectiveness of emissions trading systems (ETSs) across 53 countries. It classifies 58 ETSs into four archetypes and identifies renewable energy consumption …

Artem SHAPOSHNIKOV, Svetlana RATNER, Inna Choban de Sousa Paiva +1

This paper conducts a meta-analysis of 76 empirical studies (2009-2025) on the effect of AI and digital technologies (DT) adoption on corporate greenwashing (ESG disclosure-performance gap). AI/DT implementation is associated with a statist…

Sala D, Polyanska A, Psyuk V

This paper examines the evolution of energy transition research through a bibliometric co-occurrence analysis of keywords from 146 publications. Recent research (2022-2024) focuses on renewable energy, sustainable development, and intellige…

Xinyi Mu, Dujuan Yang, Qi Han

This study proposes a Bayesian learning agent-based model to analyze heating system decarbonization decisions in homeowner associations. It models the learning process of members and evaluates how policy and economic factors affect the adop…

Rai A.

This study combines techno-economic assessment with deep learning methods to evaluate wind-driven green hydrogen fuel production in Scandinavia. It uses deep learning models to predict wind output and hydrogen production costs, assessing fe…

Leng J.

This study applies data analytics and machine learning to site screening for CO2 geological storage in depleted oil and gas reservoirs in the Gulf of Mexico. It proposes a method to improve the accuracy and speed of storage site evaluation,…

Kumar R.

This paper reviews recent trends and future prospects of AI and sustainable finance using Natural Language Processing (NLP) models. It focuses on applications in ESG assessment and greenwashing detection, discussing how AI can enhance decis…

Zhipeng Han, Liguo Wang, Yongling Wang

Using an interpretable machine learning framework (LASSO, random forest, SHAP) on 7,791 firm-year observations of Chinese A-share industrial firms (2016-2022), this study reveals a threshold-dependent ESG-carbon total factor productivity (C…

Mira Kopp

This study develops a typology of European cities for climate mitigation and adaptation using automated text extraction and clustering. It integrates a systematic review to link city types with tailored strategies, supporting evidence-based…