Driver Analysis and Integrated Prediction of Carbon Emissions in China Using Machine Learning Models and Empirical Mode Decomposition DOI Creative Commons

Ruixia Suo,

Qi Wang,

Qiutong Han

et al.

Mathematics, Journal Year: 2024, Volume and Issue: 12(14), P. 2169 - 2169

Published: July 11, 2024

Accurately predicting the trajectory of carbon emissions is vital for achieving a sustainable shift toward green and low-carbon future. Hence, this paper created novel model to examine driver analysis integrated prediction Chinese emission, large carbon-emitting country. The logarithmic mean divisia index (LMDI) approach initially served decompose drivers emissions, analyzing annual staged contributions these factors. Given non-stationarity non-linear characteristics in data sequence decomposition–integration was proposed. employed empirical mode decomposition (EMD) each set into series components. various emission components were anticipated using long short-term memory (LSTM) based on deconstructed impacting aggregate predicted constituted overall forecast emissions. result indicates that EMD-LSTM greatly decreased errors over other comparable models. This makes up gap existing research by providing further LMDI method. Additionally, it innovatively incorporates EMD method study, proposed effectively addresses volatility demonstrates excellent predictive performance prediction.

Language: Английский

Exploration of ecological compensation standard: Based on ecosystem service flow path DOI
Zhongwei An, Caizhi Sun, Shuai Hao

et al.

Applied Geography, Journal Year: 2025, Volume and Issue: 178, P. 103588 - 103588

Published: March 12, 2025

Language: Английский

Citations

1
Digital Pathways to Sustainable Agriculture: Examining the Role of Agricultural Digitalization in Green Development in China DOI Open Access
Ying Meng, Dong Li

Sustainability, Journal Year: 2025, Volume and Issue: 17(8), P. 3652 - 3652

Published: April 17, 2025

Amid the urgent need to align agricultural practices with United Nations Sustainable Development Goals (SDGs), this study examines role of digitalization in promoting sustainable and green development China. Specifically, it explores demand-side factors that drive improvements categorizes models into three types: market-oriented, policy-driven, innovation-driven. Utilizing provincial-level data from 2011 2021, employs semiparametric spatial Durbin empirically assess effects, underlying mechanisms, regional disparities advancing development. The main findings are as follows: (1) Overall, both level have gradually increased during period, significantly contributing (2) impact on shows an upward trend eastern, coastal, non-grain-producing regions, well southeastern areas “Hu Huanyong Line”. In contrast, inland regions northwestern Line” exhibit a U-shaped relationship, grain-producing experience clear inhibitory effect. Additionally, effect is more pronounced higher levels (3) Agricultural generates positive spillover benefiting not only local region but also surrounding areas, stronger radiative neighboring regions. (4) Mechanism analysis suggests under all models, can effectively enhance by improving alignment supply demand for products, accelerating establishment promotion brands, strengthening environmental regulation, fostering new business entities, mechanization, efficiency facility agriculture.

Language: Английский

Citations

0
Adoption of Lean Construction and AI/IoT Technologies in Iran’s Public Construction Sector: A Mixed-Methods Approach Using Fuzzy Logic DOI Creative Commons
Mehmet Nurettin Uğural, Seyedarash Aghili, Halil İbrahim Burgan

et al.

Buildings, Journal Year: 2024, Volume and Issue: 14(10), P. 3317 - 3317

Published: Oct. 21, 2024

The construction sector in Iran faces substantial inefficiencies, including high material wastage, posing environmental and economic risks. This study investigated the adoption of Lean Construction (LC) practices AI/IoT technologies Iran’s public using a mixed-methods approach. research examined organizational, technical, infrastructural factors across four key provinces—Tehran, Isfahan, Khorasan Razavi, Fars—and employed fuzzy logic to address uncertainties decisions. Data from 28 stakeholder interviews were analyzed Python 3.9, with libraries such as Pandas 1.3.3, NumPy 1.21.2, skfuzzy 0.4.2 for statistical analysis NVivo 12 thematic coding. revealed that organizational readiness leadership support critical drivers adoption, particularly Isfahan which exhibited highest likelihood scores (0.5000). Tehran Fars showed slightly lower due regulatory barriers financial limitations. findings highlight need targeted training, reforms, infrastructure investments accelerate these technologies. aligned Sustainable Development Goals (SDG 9: Industry, Innovation, Infrastructure SDG 11: Cities Communities) by offering practical recommendations advancing sustainable sector. insights provided have broader implications other developing economies facing similar challenges, contributing global efforts toward development.

Language: Английский

Citations

2
Driver Analysis and Integrated Prediction of Carbon Emissions in China Using Machine Learning Models and Empirical Mode Decomposition DOI Creative Commons

Ruixia Suo,

Qi Wang,

Qiutong Han

et al.

Mathematics, Journal Year: 2024, Volume and Issue: 12(14), P. 2169 - 2169

Published: July 11, 2024

Accurately predicting the trajectory of carbon emissions is vital for achieving a sustainable shift toward green and low-carbon future. Hence, this paper created novel model to examine driver analysis integrated prediction Chinese emission, large carbon-emitting country. The logarithmic mean divisia index (LMDI) approach initially served decompose drivers emissions, analyzing annual staged contributions these factors. Given non-stationarity non-linear characteristics in data sequence decomposition–integration was proposed. employed empirical mode decomposition (EMD) each set into series components. various emission components were anticipated using long short-term memory (LSTM) based on deconstructed impacting aggregate predicted constituted overall forecast emissions. result indicates that EMD-LSTM greatly decreased errors over other comparable models. This makes up gap existing research by providing further LMDI method. Additionally, it innovatively incorporates EMD method study, proposed effectively addresses volatility demonstrates excellent predictive performance prediction.

Language: Английский

Citations

1