Quantifying the Carbon Reduction Potential of Urban Parks Under Extreme Heat Events Using Interpretable Machine Learning: A Case Study of Jinan, China
Greenhouse gas emissions are primary drivers of climate change, and the intensification of extreme heat and urban heat island effects poses serious threats to urban ecosystems, public health, and energy consumption. This study systematically evaluated the carbon reduction potential of 369 urban park...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/16/1/79 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589152549339136 |
|---|---|
| author | Lemin Yu Wenru Li Changhui Zheng Xiaowen Lin |
| author_facet | Lemin Yu Wenru Li Changhui Zheng Xiaowen Lin |
| author_sort | Lemin Yu |
| collection | DOAJ |
| description | Greenhouse gas emissions are primary drivers of climate change, and the intensification of extreme heat and urban heat island effects poses serious threats to urban ecosystems, public health, and energy consumption. This study systematically evaluated the carbon reduction potential of 369 urban parks in Jinan during extreme heat events using land surface temperature (LST) retrieval, combined with CatBoost + SHAP machine learning methods. Results indicate that the LST in Jinan ranged from 1.77 °C to 59.44 °C, and 278 parks exhibited significant cooling effects, collectively saving 2943 tons of CO<sub>2</sub> per day—offsetting 11.28% of the city’s fossil fuel emissions. Small parks, such as community parks, demonstrated higher carbon-saving efficiency (CSE), while large ecological parks showed greater carbon-saving intensity (CSI). CSE was strongly correlated with vegetation coverage and surrounding population density, with efficiency increasing when the vegetation index was within 0.3–0.7 and population density ranged 0–5000 or 15,000–22,500 people. CSI was influenced by evapotranspiration and park geometric form, increasing significantly when the park area exceeded 250 hectares or evapotranspiration ranged 2.5–6.0. However, elevation and albedo negatively impacted both metrics, with the lowest CSI observed when elevation exceeded 150 m or albedo surpassed 18%. |
| format | Article |
| id | doaj-art-ec3f58f9dc8f49d892d22751c0902476 |
| institution | Kabale University |
| issn | 2073-4433 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj-art-ec3f58f9dc8f49d892d22751c09024762025-01-24T13:21:57ZengMDPI AGAtmosphere2073-44332025-01-011617910.3390/atmos16010079Quantifying the Carbon Reduction Potential of Urban Parks Under Extreme Heat Events Using Interpretable Machine Learning: A Case Study of Jinan, ChinaLemin Yu0Wenru Li1Changhui Zheng2Xiaowen Lin3School of Modern Agriculture and Environment, Weifang Institute of Technology, Weifang 261000, ChinaCollege of Landscape Architecture and Arts, Northwest A&F University, Xianyang 712100, ChinaCollege of Humanities and Development, China Agricultural University, Beijing 100083, ChinaCollege of Landscape Architecture, Beijing Forestry University, Beijing 100083, ChinaGreenhouse gas emissions are primary drivers of climate change, and the intensification of extreme heat and urban heat island effects poses serious threats to urban ecosystems, public health, and energy consumption. This study systematically evaluated the carbon reduction potential of 369 urban parks in Jinan during extreme heat events using land surface temperature (LST) retrieval, combined with CatBoost + SHAP machine learning methods. Results indicate that the LST in Jinan ranged from 1.77 °C to 59.44 °C, and 278 parks exhibited significant cooling effects, collectively saving 2943 tons of CO<sub>2</sub> per day—offsetting 11.28% of the city’s fossil fuel emissions. Small parks, such as community parks, demonstrated higher carbon-saving efficiency (CSE), while large ecological parks showed greater carbon-saving intensity (CSI). CSE was strongly correlated with vegetation coverage and surrounding population density, with efficiency increasing when the vegetation index was within 0.3–0.7 and population density ranged 0–5000 or 15,000–22,500 people. CSI was influenced by evapotranspiration and park geometric form, increasing significantly when the park area exceeded 250 hectares or evapotranspiration ranged 2.5–6.0. However, elevation and albedo negatively impacted both metrics, with the lowest CSI observed when elevation exceeded 150 m or albedo surpassed 18%.https://www.mdpi.com/2073-4433/16/1/79urban parkscarbon reduction potentialheat island mitigationSHAPcarbon-saving model |
| spellingShingle | Lemin Yu Wenru Li Changhui Zheng Xiaowen Lin Quantifying the Carbon Reduction Potential of Urban Parks Under Extreme Heat Events Using Interpretable Machine Learning: A Case Study of Jinan, China Atmosphere urban parks carbon reduction potential heat island mitigation SHAP carbon-saving model |
| title | Quantifying the Carbon Reduction Potential of Urban Parks Under Extreme Heat Events Using Interpretable Machine Learning: A Case Study of Jinan, China |
| title_full | Quantifying the Carbon Reduction Potential of Urban Parks Under Extreme Heat Events Using Interpretable Machine Learning: A Case Study of Jinan, China |
| title_fullStr | Quantifying the Carbon Reduction Potential of Urban Parks Under Extreme Heat Events Using Interpretable Machine Learning: A Case Study of Jinan, China |
| title_full_unstemmed | Quantifying the Carbon Reduction Potential of Urban Parks Under Extreme Heat Events Using Interpretable Machine Learning: A Case Study of Jinan, China |
| title_short | Quantifying the Carbon Reduction Potential of Urban Parks Under Extreme Heat Events Using Interpretable Machine Learning: A Case Study of Jinan, China |
| title_sort | quantifying the carbon reduction potential of urban parks under extreme heat events using interpretable machine learning a case study of jinan china |
| topic | urban parks carbon reduction potential heat island mitigation SHAP carbon-saving model |
| url | https://www.mdpi.com/2073-4433/16/1/79 |
| work_keys_str_mv | AT leminyu quantifyingthecarbonreductionpotentialofurbanparksunderextremeheateventsusinginterpretablemachinelearningacasestudyofjinanchina AT wenruli quantifyingthecarbonreductionpotentialofurbanparksunderextremeheateventsusinginterpretablemachinelearningacasestudyofjinanchina AT changhuizheng quantifyingthecarbonreductionpotentialofurbanparksunderextremeheateventsusinginterpretablemachinelearningacasestudyofjinanchina AT xiaowenlin quantifyingthecarbonreductionpotentialofurbanparksunderextremeheateventsusinginterpretablemachinelearningacasestudyofjinanchina |