Quantifying the Carbon Reduction Potential of Urban Parks Under Extreme Heat Events Using Interpretable Machine Learning: A Case Study of Jinan, China
Abstract
:1. Introduction
2. Materials and Methods
2.1. Research Area and Data Collection
2.2. Methods
2.2.1. Research Framework
2.2.2. LST Retrieval
2.2.3. Quantifying the Carbon Reduction Potential and Offset Value of Urban Parks
2.2.4. Selection of Influencing Factors
2.2.5. CatBoost-Based Interpretable Machine Learning Model
3. Results
3.1. MODIS and RTE-Based LST Cross-Validation Results
3.2. Carbon Reduction Patterns in Urban Parks
3.3. Contribution of Urban Parks in Jinan to Carbon Neutrality
3.4. Correlation Analysis of Factors Influencing Carbon Reduction in Urban Parks
3.5. Analysis of Factors Affecting Carbon Emission Reduction
3.5.1. Contribution and Direction of Carbon Emission Reduction Impact Factors
3.5.2. Marginal Effects of Factors on Carbon Reduction in Parks
4. Discussion
4.1. Carbon Reduction Potential of Urban Parks
4.2. Interactions and Effects of Landscape Factors
4.3. How to Realize the Carbon Reduction Potential of Urban Parks
4.4. Limitations of the Study
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Oke, T.R. The energetic basis of the urban heat island. Q. J. R. Meteorol. Soc. 1982, 108, 1–24. [Google Scholar] [CrossRef]
- Santamouris, M. Heat islands: A review of the impact of urban heat islands on the energy consumption of buildings. Energy Build. 2015, 94, 119–124. [Google Scholar] [CrossRef]
- Akbari, H.; Pomerantz, M.; Taha, H. Cool surfaces and shade trees to reduce energy use and improve air quality in urban areas. Sol. Energy 2001, 70, 295–310. [Google Scholar] [CrossRef]
- Zhou, D.; Wang, X.; Zhang, Y.; Li, Q.; Liu, Z.; Li, X. Urban heat island effect and its impact on energy consumption in cities. Environ. Res. Lett. 2018, 13, 124002. [Google Scholar]
- Matzarakis, A.; Mayer, H.; Iziomon, M. The role of urban green spaces in mitigating the urban heat island effect. Int. J. Biometeorol. 2010, 54, 1–9. [Google Scholar]
- Yang, J.; Li, L.; Zhang, X.; Zhao, Y. The impact of urban green space on urban heat island effect: A case study of Beijing. Sustain. Cities Soc. 2015, 14, 1–10. [Google Scholar] [CrossRef]
- Bowler, D.E.; Buyung-Ali, L.; Knight, T.M.; Pullin, A.S.; Knight, T.M.; Pullin, A.S. Urban greening to cool towns and cities: A systematic review of the empirical evidence. Landsc. Urban Plan. 2010, 97, 147–155. [Google Scholar] [CrossRef]
- Lee, J.H.; Choi, J.; Lee, S.; Park, C.; Kim, H.; Lee, J. The role of urban green spaces in mitigating urban heat island effects: A review. Sustain. Cities Soc. 2018, 39, 1–10. [Google Scholar]
- Davis, A.J.; Nowak, D.J.; Endreny, T.A.; Green, J.L.; Heisler, G.M.; Mize, S.V. The role of urban trees in reducing energy consumption: A case study of the city of Atlanta. Urban For. Urban Green 2011, 10, 109–116. [Google Scholar]
- Li, D.; Zhou, Y.; Xu, Y.; Zhang, X.; Li, X.; Lin, Y. The cooling effect of urban green spaces on urban heat islands: A case study of Beijing. Urban For. Urban Green 2020, 48, 126563. [Google Scholar]
- Du, C.; Jia, W.; Wang, K. Valuing carbon saving potential of urban parks in thermal mitigation: Linking accumulative and accessibility perspectives. Urban Clim. 2023, 51, 101645. [Google Scholar] [CrossRef]
- Chen, M.; Jia, W.; Du, C.; Shi, M.; Henebry, G.M.; Wang, K. Carbon saving potential of urban parks due to heat mitigation in Yangtze River Economic Belt. J. Clean. Prod. 2023, 385, 135713. [Google Scholar] [CrossRef]
- Zhao, Y.; Liu, Y.; Li, W.; Zhang, Z.; Wang, X. The impact of park types on carbon sequestration in urban areas. Urban For. Urban Green 2019, 38, 123–130. [Google Scholar]
- Li, X.; Wang, J.; Zhang, T.; Li, D.; Zhang, Y. Landscape structure and its influence on carbon sequestration in urban parks. Ecol. Indic. 2021, 121, 107–115. [Google Scholar]
- Wang, J.; Li, X.; Zhang, T.; Li, D.; Zhang, Y. Effects of landscape features on carbon reduction potential in urban parks. Landsc. Urban Plan. 2022, 214, 104–112. [Google Scholar]
- Tran, M.; Nguyen, T.; Le, T.; Nguyen, P.; Pham, H. The role of urban green spaces in mitigating climate change: A review. Environ. Sci. Policy 2020, 112, 1–10. [Google Scholar]
- Chen, L.; Zhang, X.; Liu, Y.; Li, J.; Wang, L. Socioeconomic factors influencing urban forest ecosystem services. For. Ecol. Manag. 2020, 458, 117–125. [Google Scholar]
- Zhou, Q.; Liu, Y.; Zhang, Z.; Li, Y.; Wang, X. Urban heat island effect and its relationship with road network density. Sustain. Cities Soc. 2021, 65, 102–110. [Google Scholar]
- Zhang, H.; Liu, X.; Wang, J.; Li, Z.; Zhang, Y. The role of vegetation types in carbon reduction efficiency in urban parks. J. Environ. Manag. 2023, 310, 114–123. [Google Scholar]
- Lundberg, S.M.; Lee, S.I. A Unified Approach to Interpreting Model Predictions. arXiv 2017, arXiv:1705.07874. [Google Scholar]
- Qi, J.D.; Huang, J.Z.; Jia, X. Simulation and feature response of urban green space net carbon exchange based on XGBoost-ANN. Trans. Chin. Soc. Agric. Mach. 2019, 50, 269–278. [Google Scholar]
- Li, Z.; Rolston, N.; Flick, A.C.; Colburn, T.W.; Ren, Z.; Dauskardt, R.H.; Buonassisi, T. Machine learning with knowledge constraints for process optimization of open-air perovskite solar cell manufacturing. Joule 2022, 6, 834–849. [Google Scholar] [CrossRef]
- Zhang, H.; Li, Y.; Wang, X. Green infrastructure planning and implementation in Jinan, China: Challenges and opportunities. Landsc. Urban Plan. 2020, 195, 103711. [Google Scholar]
- Tzoulas, K.; Korpela, K.; Venn, S.; Ylenik, M.; Frith, M. Promoting ecosystem and human health in urban areas using green infrastructure: A literature review. Landsc. Urban Plan. 2007, 81, 167–178. [Google Scholar] [CrossRef]
- Li, S.; Jiang, G.-M. Land surface temperature retrieval from Landsat-8 data with the generalized split-window algorithm. IEEE Access 2018, 6, 18149–18162. [Google Scholar] [CrossRef]
- Feng, M.; Huang, C.; Channan, S.; Vermote, E.F.; Masek, J.G.; Townshend, J.R. Quality assessment of Landsat surface reflectance products using MODIS data. Comput. Geosci. 2012, 38, 9–22. [Google Scholar] [CrossRef]
- National Development and Reform Commission. China’s Oil and Gas Production Corporate Greenhouse Gas Emissions Accounting Methods and Reporting Guidelines (Trial); National Development and Reform Commission: Beijing, China, 2014. [Google Scholar]
- Oda, T.; Maksyutov, S.; Andres, R.J. The Open-source Data Inventory for Anthropogenic CO2, version 2016 (ODIAC2016): A global monthly fossil fuel CO2 gridded emissions data product for tracer transport simulations and surface flux inversions. Earth Syst. Sci. Data 2018, 10, 87–107. [Google Scholar] [CrossRef]
- Yuan, Y.; Guo, W.; Tang, S.; Zhang, J. Effects of patterns of urban green-blue landscape on carbon sequestration using XGBoost-SHAP model. J. Clean. Prod. 2024, 476, 143640. [Google Scholar] [CrossRef]
- Manesh, M.T.; Dehnavi, A.N.; Tahsildoost, M.; Alambeigi, P. Acoustic design evaluation in educational buildings using artificial intelligence. Build. Environ. 2024, 261, 111695. [Google Scholar] [CrossRef]
- Prokhorenkova, L.; Gusev, G.; Vorobev, A.; Dorogush, A.V.; Gulin, A. CatBoost: Unbiased boosting with categorical features. Adv. Neural Inf. Process. Syst. 2018, 2018, 6638–6648. [Google Scholar]
- Steurer, M.; Hill, R.J.; Pfeifer, N. Metrics for evaluating the performance of machine learning-based automated valuation models. J. Prop. Res. 2021, 38, 99–129. [Google Scholar] [CrossRef]
- Guo, R.; Yang, B.; Guo, Y.; Li, H.; Li, Z.; Zhou, B.; Hong, B.; Wang, F. Machine learning-based prediction of outdoor thermal comfort: Combining Bayesian optimization and the SHAP model. Build. Environ. 2024, 254, 111301. [Google Scholar] [CrossRef]
- Ekanayake, I.U.; Meddage, D.P.P.; Rathnayake, U. A novel approach to explain the black-box nature of machine learning in compressive strength predictions of concrete using Shapley additive explanations (SHAP). Case Stud. Constr. Mater. 2022, 16, e01059. [Google Scholar] [CrossRef]
- Ren, Z.; He, X.; Zheng, H.; Zhang, D.; Yu, X.; Shen, G.; Guo, R. Estimation of the relationship between urban park characteristics and park cool island intensity by remote sensing data and field measurement. Forests 2013, 4, 868–886. [Google Scholar] [CrossRef]
- Zhang, X.; Song, P. Estimating urban evapotranspiration at 10m resolution using vegetation information from Sentinel-2: A case study for the Beijing Sponge City. Remote Sens. 2021, 13, 2048. [Google Scholar] [CrossRef]
- Yan, L.; Jia, W.; Zhao, S. The cooling effect of urban green spaces in metacities: A case study of Beijing, China’s capital. Remote Sens. 2021, 13, 4601. [Google Scholar] [CrossRef]
- Feng, X.; Yu, J.; Xin, C.; Ye, T.; Wang, T.; Chen, H.; Zhang, X.; Zhang, L. Quantifying and comparing the cooling effects of three different morphologies of urban parks in Chengdu. Land 2023, 12, 451. [Google Scholar] [CrossRef]
- Yang, C.; He, X.; Yu, L.; Yang, J.; Yan, F.; Bu, K.; Chang, L.; Zhang, S. The cooling effect of urban parks and its monthly variations in a snow climate city. Remote Sens. 2017, 9, 1066. [Google Scholar] [CrossRef]
Data | Date | Type | Source |
---|---|---|---|
Landsat-8 TIRS | 10 June 2023 | Raster data | https://earthexplorer.usgs.gov/scene/metadata/full/5e83d14f2fc39685/LC91220352023161LGN00/ (accessed on 10 June 2023) |
MODIS | 10 June 2023 | Raster data | MOD11A1.A2023161.h27v05.061.2023164064226.hdf |
Park boundaries | 2020 | Vector data | https://www.openstreetmap.org (accessed on 20 July 2020) |
Administrative boundary | 2021 | Vector data | National Geomatics Center of China |
Factors | Variables | Description |
---|---|---|
Park inside | Park_Area | Park area (ha) |
Park_LSI | The park shape index, which indicates the degree of regularity of the park. The higher the value of Park_LSI, the more irregular the shape of the park. Ep is the perimeter of the park green space; Ap is the area of the park green space. | |
Park_meanTree | Average tree heights within the park. Study data were obtained through the global 1m canopy height dataset produced by Meta at the following URL: (accessed on 22 April 2024) https://sustainability.atmeta.com/blog/2024/04/22/using-artificial-intelligence-to-map-the-earths-forests/. | |
Park_DEM | Representing surface relief within the park. | |
Park_NDVI | The normalized vegetation index (NDVI) within the park, which expresses the density of vegetation cover, i.e., its growth pattern, is calculated using the following formula: | |
Park_Albedo | Park internal albedo, the ratio of radiance to irradiance. Study data were obtained through EEFlux (http://eeflu-level1.appspot.com/ (accessed on 24 September 2023)) and analyzed by METRIC model calculations. | |
Park_ET | Evapotranspiration within the park, i.e., the total amount of water vapor from soil evaporation and vegetation transpiration. The study data were obtained through EEFlux (http://eeflu-level1.appspot.com (accessed on 24 September 2023)) and calculated by the METRIC model. | |
Surrounding area | Buffer_Tree | The canopy area within the park’s surrounding buffer zone was determined using tree canopy height data. The research data were sourced from the global 1m canopy height dataset produced by Meta, available at the following website: https://sustainability.atmeta.com/blog/2024/04/22/using-artificial-intelligence-to-map-the-earths-forests/ (accessed on 24 September 2023). |
Buffer_POP | The population density within the park’s surrounding buffer zone was obtained from the WorldPop dataset, with data available at the following website: https://hub.worldpop.org/project/categories?id=3 (accessed on 24 September 2023). | |
Buffer_RD | The road network density within the park’s surrounding buffer zone was obtained from the data available at the following website: https://www.openstreetmap.org (accessed on 24 September 2023). |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yu, L.; Li, W.; Zheng, C.; Lin, X. Quantifying the Carbon Reduction Potential of Urban Parks Under Extreme Heat Events Using Interpretable Machine Learning: A Case Study of Jinan, China. Atmosphere 2025, 16, 79. https://doi.org/10.3390/atmos16010079
Yu L, Li W, Zheng C, Lin X. Quantifying the Carbon Reduction Potential of Urban Parks Under Extreme Heat Events Using Interpretable Machine Learning: A Case Study of Jinan, China. Atmosphere. 2025; 16(1):79. https://doi.org/10.3390/atmos16010079
Chicago/Turabian StyleYu, Lemin, Wenru Li, Changhui Zheng, and Xiaowen Lin. 2025. "Quantifying the Carbon Reduction Potential of Urban Parks Under Extreme Heat Events Using Interpretable Machine Learning: A Case Study of Jinan, China" Atmosphere 16, no. 1: 79. https://doi.org/10.3390/atmos16010079
APA StyleYu, L., Li, W., Zheng, C., & Lin, X. (2025). Quantifying the Carbon Reduction Potential of Urban Parks Under Extreme Heat Events Using Interpretable Machine Learning: A Case Study of Jinan, China. Atmosphere, 16(1), 79. https://doi.org/10.3390/atmos16010079