Evolution, reconfiguration and low-carbon performance of green space pattern under diverse urban development scenarios: A machine learning-based simulation approach
Ecological restoration, green space morphology, and carbon emissions are intricately interconnected. Previous research utilizing case studies and econometric modeling has demonstrated that effective ecological restoration and well-structured green space configurations can significantly enhance carbo...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Ecological Indicators |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1470160X2401402X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850256014297792512 |
|---|---|
| author | Yujie Ren Mengdie Zhou Antian Zhu Shucheng Shi Hao Zhu Yuzhu Chen Shanshan Li Tianhui Fan |
| author_facet | Yujie Ren Mengdie Zhou Antian Zhu Shucheng Shi Hao Zhu Yuzhu Chen Shanshan Li Tianhui Fan |
| author_sort | Yujie Ren |
| collection | DOAJ |
| description | Ecological restoration, green space morphology, and carbon emissions are intricately interconnected. Previous research utilizing case studies and econometric modeling has demonstrated that effective ecological restoration and well-structured green space configurations can significantly enhance carbon sequestration, reduce carbon emissions, and mitigate the adverse effects of climate change during urbanization. However, as urban land-use patterns become increasingly complex and development trajectories more diverse, the relationship between green space morphology and carbon dynamics (emissions and sequestration) reveals notable heterogeneity and non-linear characteristics. Understanding these complex, non-linear relationships and the underlying mechanisms is both theoretically and technically innovative, with profound implications for urban planning, policy formulation, climate change mitigation, and ecological conservation. In this study, we applied machine learning algorithms to model the non-linear relationships and threshold effects between green space evolution and carbon emissions/sequestration at different stages of ecological restoration in the Yangtze River Basin, China. Furthermore, we simulated the low-carbon performance of green spaces under various urban development scenarios. The key findings include: (1) Wetlands, particularly those composed of shallow water bodies and land–water interfaces such as marshes and mangroves, are critical determinants of the low-carbon performance of green spaces, with their effects on carbon emissions and sequestration exhibiting significant temporal dynamics throughout different stages of ecological restoration. (2) The fragmentation and shape complexity of green spaces substantially influence carbon efficiency. Preserving the connectivity and integrity of green spaces, particularly in large-scale forests and wetlands, while minimizing fragmentation and reducing shape complexity, can enhance carbon sequestration capacity. (3) Carbon performance varies markedly across different urban development trajectories. In cities prioritizing ecological restoration, future carbon emissions tend to stabilize, whereas in rapidly growing megacities, despite recent declines in carbon emissions, further optimization of green space configurations is required to effectively manage emissions and bolster sequestration. In summary, this study provides robust scientific evidence for ecological restoration and green space planning in the Yangtze River Basin, offering valuable insights for carbon management and ecological restoration in similar regions globally. These findings contribute to global environmental governance efforts and the ongoing fight against climate change. |
| format | Article |
| id | doaj-art-2b52cfac2afb4409b24a0df27cab9dce |
| institution | OA Journals |
| issn | 1470-160X |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Indicators |
| spelling | doaj-art-2b52cfac2afb4409b24a0df27cab9dce2025-08-20T01:56:44ZengElsevierEcological Indicators1470-160X2024-12-0116911294510.1016/j.ecolind.2024.112945Evolution, reconfiguration and low-carbon performance of green space pattern under diverse urban development scenarios: A machine learning-based simulation approachYujie Ren0Mengdie Zhou1Antian Zhu2Shucheng Shi3Hao Zhu4Yuzhu Chen5Shanshan Li6Tianhui Fan7Department of Urban and Rural Planning, Nanjing Forestry University, ChinaDepartment of Urban and Rural Planning, Nanjing Forestry University, ChinaDepartment of Urban and Rural Planning, Nanjing Forestry University, ChinaDepartment of Urban and Rural Planning, Nanjing Forestry University, ChinaDepartment of Urban and Rural Planning, Nanjing Forestry University, ChinaDepartment of Urban and Rural Planning, Nanjing Forestry University, ChinaDepartment of Urban and Rural Planning, Nanjing Forestry University, ChinaGraduate School of Global Environmental Studies, Kyoto University, Japan; International Institute for Carbon-Neutral Energy Research, Kyushu University, Japan; Corresponding author at: Graduate School of Global Environmental Studies, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan.Ecological restoration, green space morphology, and carbon emissions are intricately interconnected. Previous research utilizing case studies and econometric modeling has demonstrated that effective ecological restoration and well-structured green space configurations can significantly enhance carbon sequestration, reduce carbon emissions, and mitigate the adverse effects of climate change during urbanization. However, as urban land-use patterns become increasingly complex and development trajectories more diverse, the relationship between green space morphology and carbon dynamics (emissions and sequestration) reveals notable heterogeneity and non-linear characteristics. Understanding these complex, non-linear relationships and the underlying mechanisms is both theoretically and technically innovative, with profound implications for urban planning, policy formulation, climate change mitigation, and ecological conservation. In this study, we applied machine learning algorithms to model the non-linear relationships and threshold effects between green space evolution and carbon emissions/sequestration at different stages of ecological restoration in the Yangtze River Basin, China. Furthermore, we simulated the low-carbon performance of green spaces under various urban development scenarios. The key findings include: (1) Wetlands, particularly those composed of shallow water bodies and land–water interfaces such as marshes and mangroves, are critical determinants of the low-carbon performance of green spaces, with their effects on carbon emissions and sequestration exhibiting significant temporal dynamics throughout different stages of ecological restoration. (2) The fragmentation and shape complexity of green spaces substantially influence carbon efficiency. Preserving the connectivity and integrity of green spaces, particularly in large-scale forests and wetlands, while minimizing fragmentation and reducing shape complexity, can enhance carbon sequestration capacity. (3) Carbon performance varies markedly across different urban development trajectories. In cities prioritizing ecological restoration, future carbon emissions tend to stabilize, whereas in rapidly growing megacities, despite recent declines in carbon emissions, further optimization of green space configurations is required to effectively manage emissions and bolster sequestration. In summary, this study provides robust scientific evidence for ecological restoration and green space planning in the Yangtze River Basin, offering valuable insights for carbon management and ecological restoration in similar regions globally. These findings contribute to global environmental governance efforts and the ongoing fight against climate change.http://www.sciencedirect.com/science/article/pii/S1470160X2401402XGreen space patternLow-carbon performanceUrban development scenarios |
| spellingShingle | Yujie Ren Mengdie Zhou Antian Zhu Shucheng Shi Hao Zhu Yuzhu Chen Shanshan Li Tianhui Fan Evolution, reconfiguration and low-carbon performance of green space pattern under diverse urban development scenarios: A machine learning-based simulation approach Ecological Indicators Green space pattern Low-carbon performance Urban development scenarios |
| title | Evolution, reconfiguration and low-carbon performance of green space pattern under diverse urban development scenarios: A machine learning-based simulation approach |
| title_full | Evolution, reconfiguration and low-carbon performance of green space pattern under diverse urban development scenarios: A machine learning-based simulation approach |
| title_fullStr | Evolution, reconfiguration and low-carbon performance of green space pattern under diverse urban development scenarios: A machine learning-based simulation approach |
| title_full_unstemmed | Evolution, reconfiguration and low-carbon performance of green space pattern under diverse urban development scenarios: A machine learning-based simulation approach |
| title_short | Evolution, reconfiguration and low-carbon performance of green space pattern under diverse urban development scenarios: A machine learning-based simulation approach |
| title_sort | evolution reconfiguration and low carbon performance of green space pattern under diverse urban development scenarios a machine learning based simulation approach |
| topic | Green space pattern Low-carbon performance Urban development scenarios |
| url | http://www.sciencedirect.com/science/article/pii/S1470160X2401402X |
| work_keys_str_mv | AT yujieren evolutionreconfigurationandlowcarbonperformanceofgreenspacepatternunderdiverseurbandevelopmentscenariosamachinelearningbasedsimulationapproach AT mengdiezhou evolutionreconfigurationandlowcarbonperformanceofgreenspacepatternunderdiverseurbandevelopmentscenariosamachinelearningbasedsimulationapproach AT antianzhu evolutionreconfigurationandlowcarbonperformanceofgreenspacepatternunderdiverseurbandevelopmentscenariosamachinelearningbasedsimulationapproach AT shuchengshi evolutionreconfigurationandlowcarbonperformanceofgreenspacepatternunderdiverseurbandevelopmentscenariosamachinelearningbasedsimulationapproach AT haozhu evolutionreconfigurationandlowcarbonperformanceofgreenspacepatternunderdiverseurbandevelopmentscenariosamachinelearningbasedsimulationapproach AT yuzhuchen evolutionreconfigurationandlowcarbonperformanceofgreenspacepatternunderdiverseurbandevelopmentscenariosamachinelearningbasedsimulationapproach AT shanshanli evolutionreconfigurationandlowcarbonperformanceofgreenspacepatternunderdiverseurbandevelopmentscenariosamachinelearningbasedsimulationapproach AT tianhuifan evolutionreconfigurationandlowcarbonperformanceofgreenspacepatternunderdiverseurbandevelopmentscenariosamachinelearningbasedsimulationapproach |