GX & Decarbonization Research

Pablo Catret Ruber, David Garcia-Rodriguez, Domingo Jose Iglesias Fuente +3

This paper proposes machine learning models to predict greenhouse gas concentrations at ICOS sites, leveraging ecosystem-specific analyses to improve accuracy. It contributes to climate monitoring and carbon accounting applications.

Kozol E.

This paper discusses the application of artificial intelligence in sustainable finance, focusing on ESG-based financial instruments and decision-making. It examines how AI-driven ESG data analysis and scoring contribute to the development o…

Liu Q.

This paper presents an airport case study using AI-driven digital twin technology to optimize energy consumption and achieve net-zero goals. By combining AI and simulation, it demonstrates potential for operational efficiency and carbon red…

Bingwen Zhao, Luchan Xu, 郑振海 +2

This study employs an SSA-LSTM hybrid model to accurately predict heat and power loads of a district heating system, combined with carbon accounting and three policy scenarios to evaluate carbon peak timing and emission reduction potential.…

Dimitris Bakalbasis, Dimitris Karadimas, Anastasia Vassilakopoulou

This paper presents the design, implementation, and initial validation of an Industrial Metaverse Platform for CCS value chains, developed within the COREu project. It integrates digital twins, AI-driven analytics, IoT-based monitoring, and…

Abdul-Hussein Aziz A, Abbas IT

This study proposes a hybrid HMPCS algorithm combined with ML models (LSTM, LightGBM) to improve solar power forecasting accuracy. Experiments show the HMPCS-optimized LSTM achieves RMSE 0.139 and R² 0.93, reducing error by 23% over baselin…

Louzada RO, Silva RHd, Correia SAC +6

This study demonstrates that ignoring spatial autocorrelation in validation inflates apparent accuracy of UAV-LiDAR and machine-learning carbon stock models. Testing 98 scenario-response combinations in a Brazilian savanna, single-partition…

Suryawinata, Bonny, Darmadi, Herru, Mansuan, Melki

This systematic literature review (47 papers, 2019-2025) examines generative design (GD) for optimizing building energy, daylighting, and thermal comfort. Rhino/Grasshopper with multi-objective genetic algorithms dominate (87.2%), while gen…

Feiyu Cai, Jing Qiu, Yi Yang +4

This paper proposes a proactive spatial-temporal carbon response framework combining deep learning and LLM-based multi-agent systems to accurately forecast day-ahead nodal carbon intensity (NCI). It integrates geographically dispatchable lo…

Zheng Liang, Li Shenshen, Hu Xuefei +2

This dataset provides monthly carbon emission predictions at 0.01 degree resolution for Beijing and surrounding areas from 2019-2024, generated using a weakly supervised neural network (CCFI-Net) that integrates remote sensing, meteorologic…

(著者不明)

This paper proposes a bidirectional temporal convolutional network combined with exogenous variable enhancement for carbon market price forecasting, aiming to improve prediction accuracy. It uniquely merges machine learning techniques with …

Hu B.

This paper empirically investigates the relationships between attitudes toward emission trading schemes (ETS), acceptance of artificial intelligence (AI), climate entrepreneurship, and sustainable performance. Using AI-driven analysis, it r…

Mishra L.

This paper presents a document question-answering (DocQA) system that simplifies ESG accountability. Users can query ESG-related documents in natural language and receive accurate answers, enhancing reporting and compliance efficiency.

Ritu Gaur, Archana Jain, Deepak Kumar Gupta +3

This paper proposes a climate-aware valuation framework that integrates multimodal LLMs, geospatial APIs, and Neo4j knowledge graphs to inject physical climate risk signals into property valuation. It achieves 5-8% improvement in extraction…

Kateryna Chekriy, Rüdiger Kiesel

This paper uses state-of-the-art NLP to evaluate corporate net-zero transition plans. It integrates this data into a Bayesian net that combines past emissions reduction and future plans to compute an adjusted probability of staying within n…

Guowei Wu, Manxuan Mao, Jie Zhi +4

This study analyzed spatiotemporal patterns and drivers of county-level agricultural carbon emissions in Guangdong, China (2000-2022), using an interpretable machine learning framework (Random Forest + SHAP). Emissions decreased by 22.9%, w…

Damrongsak Naparat, Erboon Ekasingh

This paper proposes an agentic AI framework to assess the credibility of corporate SDG claims by analyzing sustainability reports. It automatically verifies alignment between claims and actual actions, contributing to greenwashing detection…

Rüdiger Otto, Juan José García‐Alvarado, Elena Rocafull +6

Presents the first high-resolution forest carbon map for the Canary Islands integrating field data, ALS, Sentinel-2, and climatic variables with machine learning. Estimates 10.26 Tg carbon; laurel forests have exceptional densities. Structu…

Yuanyi Niu, Liang Zheng, Yajuan Chang +7

This paper proposes an intelligent red-blue supplemental lighting control system for greenhouses that balances photosynthesis and carbon footprint. Using AI/machine learning, it optimizes the light environment to reduce energy consumption w…

Shi Zheng, Min Xu, Ziyu Fu +5

This study applies safety-constrained deep reinforcement learning to optimize the coordinated operation of green data centers, integrating renewables, grid, batteries, cooling, and computing loads. It formulates the problem as a constrained…