Dataset Information

Machine learning approaches reveal highly heterogeneous air quality co-benefits of the energy transition.

ABSTRACT: Estimating health benefits of reducing fossil fuel use from improved air quality provides important rationales for carbon emissions abatement. Simulating pollution concentration is a crucial step of the estimation, but traditional approaches often rely on complicated chemical transport models that require extensive expertise and computational resources. In this study, we develop a machine learning framework that is able to provide precise and robust annual average fine particle (PM_2.5) concentration estimations directly from a high-resolution fossil energy use dataset. Applications of the framework with Chinese data reveal highly heterogeneous health benefits of avoiding premature mortality by reducing fossil fuel use in different sectors and regions in China with a mean of $19/tCO₂ and a standard deviation of $38/tCO₂. Reducing rural and residential coal use offers the highest co-benefits with a mean of $151/tCO₂. Our findings prompt careful policy designs to maximize cost-effectiveness in the transition toward a carbon-neutral energy system.

SUBMITTER: Zhang D

PROVIDER: S-EPMC10480617 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning approaches reveal highly heterogeneous air quality co-benefits of the energy transition.

Zhang Da D Wang Qingyi Q Song Shaojie S Chen Simiao S Li Mingwei M Shen Lu L Zheng Siqi S Cai Bofeng B Wang Shenhao S Zheng Haotian H

iScience 20230818 9

Estimating health benefits of reducing fossil fuel use from improved air quality provides important rationales for carbon emissions abatement. Simulating pollution concentration is a crucial step of the estimation, but traditional approaches often rely on complicated chemical transport models that require extensive expertise and computational resources. In this study, we develop a machine learning framework that is able to provide precise and robust annual average fine particle (PM<sub>2.5</sub> ...[more]

PMID: 37680462

Similar Datasets

Project description:In order to mitigate global warming and improve air quality, the transformation of regional energy structures is the most important development pathway. China, as a major global consumer of fossil fuels, will face great pressure in this regard. Aiming toward achieving the global 2 °C warming target in China, this study takes one of the most developed regions of China, Guangdong Province, as the research area in order to explore a future development pathway and potential air quality attainment until 2050, by developing two energy structure scenarios (BAU_Energy and 2Deg_Energy) and three end-of-pipe scenarios (NFC, CLE, and MTFR), and simulating future air quality and related health impacts for the different scenarios using the WRF-Chem model. The results show that under the energy transformation scenario, total energy consumption in Guangdong rises from 296 Mtce (million tons of coal equivalent) in 2015 to 329 Mtce in 2050, with electricity and clean energy accounting for 45% and 35%. In 2050, the transformation of the energy structure leads to 64%, 75%, and 46% reductions in the emissions of CO2, NOx, and SO2 compared with those in 2015. Together with the most stringent end-of-pipe control measures, the emissions of VOCs and primary PM2.5 are effectively reduced by 66% and 78%. The annual average PM2.5 and MDA8 (daily maximum 8 h O3) concentrations in Guangdong are 33.8 and 85.9 μg/m3 in 2015, with 63.4 thousand premature deaths (95% CI: 57.1-70.8) due to environmental exposure. Under the baseline scenario, no improvement is gained in air quality or public health by 2050. In contrast, the PM2.5 and MDA8 concentrations decline to 21.7 and 75.5 μg/m3 under the scenario with energy structure transformation, and total premature deaths are reduced to 35.5 thousand (31.9-39.5). When further combined with the most stringent end-of-pipe control measures, the PM2.5 concentrations decrease to 16.5 μg/m3, but there is no significant improvement for ozone, with premature deaths declining to 20.6 thousand (18.5-23.0). This study demonstrates that the transformation of energy structure toward climate goals could be effective in mitigating air pollution in Guangdong and would bring significant health benefits. Compared with the end-of-pipe control policies, transformation of the energy structure is a more effective way to improve regional air quality in the long term, and synergistic promotion of both is crucial for regional development.

Dataset Information

Machine learning approaches reveal highly heterogeneous air quality co-benefits of the energy transition.

Publications

Machine learning approaches reveal highly heterogeneous air quality co-benefits of the energy transition.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets