Assessment of the climate trace global powerplant CO2 emissions DOI Creative Commons
K. R. Gurney, Bilal Aslam, P. Dass

et al.

Environmental Research Letters, Journal Year: 2024, Volume and Issue: 19(11), P. 114062 - 114062

Published: Oct. 4, 2024

Abstract Accurate estimation of planetary greenhouse gas (GHG) emissions at the scale individual emitting activities is a critical need for both scientific and policy applications. Powerplants represent single largest most concentrated form global GHG emissions. Climate Trace, co-founded promoted by former U.S. Vice President Al Gore, new effort using, in part, artificial intelligence (AI) approaches to estimate asset-scale Trace recently released database powerplant CO 2 facility-scale that uses AI non-AI approaches. However, no independent peer-reviewed assessment has been made this important database. Here, we compare an atmospherically calibrated, multi-constraint United States. The 3.7% (65) compared facilities used AI-based approach show mean relative difference (MRD) −1.1% (SD: 46.4%) year 2019. 96.3% (1726) non-AI-based MRD −50.0% 117.7%). Of estimated facilities, 151 (8.7%) agree within ±20%. large differences between Vulcan-power emission estimates these primarily caused Trace’ use national-mean power plant capacity factor (CF) which poor representation reported CFs US leads very errors those same 1726 facilities.

Language: Английский

DRRP-Net: Dense-Res- Recurrent Prototypical Networks for Carbon Emission Prediction using Satellite Image Time Series DOI
Choudari Lakshmi,

S. Konda

Neurocomputing, Journal Year: 2025, Volume and Issue: unknown, P. 130216 - 130216

Published: April 1, 2025

Language: Английский

Citations

0
Methane Monitoring: A Systematic Review of Multi-Source Data Integration Challenges and Solutions DOI
Yang Xu, Abbas Yazdinejad, Hao Wang

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
A real-time correction model for carbon emission measurement data and carbon emission factors in coal-fired power plants based on data fusion DOI Open Access

Yizhuo Fan,

Jiaqiang Wang, Shu Gao

et al.

Journal of Physics Conference Series, Journal Year: 2025, Volume and Issue: 3001(1), P. 012033 - 012033

Published: April 1, 2025

Abstract Carbon emissions from coal-fired power plants contribute to approximately half of the total national carbon emissions, making accurate measurement these essential for achieving “double carbon”. Currently, most widely used methods measuring are material balance method, flue gas and emission factor method. However, fluctuations in coal quality inaccuracies equipment result significant variability granularity accuracy measurements. Thus, this paper proposed a real-time correction model based on data fusion, order achieve low-carbon transition plants. The differences between calculation results two different were quantified reasons analyzed by using on-site measured data. Then, combining advantages method Kalman filter was corrected real time as benchmark. show that fusion can significantly improve reduce random errors. difference fused values under similar working conditions be reduced 41.35%, standard deviation is 47.02%, which verifies effectiveness

Language: Английский

Citations

0
Assessment of the climate trace global powerplant CO2 emissions DOI Creative Commons
K. R. Gurney, Bilal Aslam, P. Dass

et al.

Environmental Research Letters, Journal Year: 2024, Volume and Issue: 19(11), P. 114062 - 114062

Published: Oct. 4, 2024

Abstract Accurate estimation of planetary greenhouse gas (GHG) emissions at the scale individual emitting activities is a critical need for both scientific and policy applications. Powerplants represent single largest most concentrated form global GHG emissions. Climate Trace, co-founded promoted by former U.S. Vice President Al Gore, new effort using, in part, artificial intelligence (AI) approaches to estimate asset-scale Trace recently released database powerplant CO 2 facility-scale that uses AI non-AI approaches. However, no independent peer-reviewed assessment has been made this important database. Here, we compare an atmospherically calibrated, multi-constraint United States. The 3.7% (65) compared facilities used AI-based approach show mean relative difference (MRD) −1.1% (SD: 46.4%) year 2019. 96.3% (1726) non-AI-based MRD −50.0% 117.7%). Of estimated facilities, 151 (8.7%) agree within ±20%. large differences between Vulcan-power emission estimates these primarily caused Trace’ use national-mean power plant capacity factor (CF) which poor representation reported CFs US leads very errors those same 1726 facilities.

Language: Английский

Citations

0