Critical Aspects of Sustainability (CAS)-Climate: Actionable Heat and Carbon Mitigation by Urban Greening--Integrating Physical Modeling and Machine Learning for Decision Support

该项目通过使用城市绿色基础设施来减少热量，促进碳中和，并支持美国城市的决策过程，寻求可行的气候解决方案。在过去几十年中，全球城市化以及随之而来的人类活动的蓬勃发展，一直是气候变化的主要和最不可逆转的驱动因素。今天，城市地区容纳了世界56%的人口，消耗了约70%的能源，产生了约四分之三的全球碳排放。实际上，人类社会的可持续未来在很大程度上取决于城市的可持续性。这项研究有助于解开气候碳反馈，提高利益相关者、政策制定者和公众对地方和区域气候变化紧急模式的认识和准备。该项目通过定期会议和年度讲习班，积极吸引利益攸关方，特别是当地城市的利益攸关方参与项目评价和外联活动。此外，该项目还包括来自少数民族的大学预科生、本科生和研究生参与教育、研究和利益相关者参与，以促进公平、多样性和包容性的原则和倡议。该项目整合了大气科学、气候建模、数据科学、气候学和气候学等领域的跨学科定量和定性方法。和城市可持续性，以发现基于自然的解决方案，在不断变化的气候条件下实现城市可持续发展。总体目标是通过整合基于物理的城市系统动力学建模和基于机器学习的技术来开发一个变革性平台，以支持决策和城市规划。该项目的具体研究任务和成果包括：（i）提高城市系统动态与建筑环境中人为压力源之间复杂相互作用的建模能力，（ii）为城市气候建模创建基于机器学习的灵活替代模型，以克服高计算成本和其他技术障碍，以及（iii）弥合决策过程和气候建模之间的差距，并通过综合分析和多目标优化发现可持续的基于自然的解决方案。此外，认识到全球气候变化对世界各地城市的社会经济增长和可持续未来构成挑战，新的可扩展平台使政策制定者能够找到和评估可采取行动的缓解和适应战略，该奖项反映了NSF的法定使命，并被认为是值得通过评估使用基金会的知识优点和更广泛的影响审查标准。

This project seeks actionable climate solutions by using urban green infrastructure to mitigate heat, promote carbon neutrality, and support decision making processes in U.S. cities. Global urbanization in past decades, with concomitant burgeoning anthropogenic activities, has been the primary and the most irreversible driver to climate changes. Today, urban areas are accommodating 56% of the world population, consuming about 70% of energy, and producing about three quarters of global carbon emissions. Practically speaking, the sustainable future of human societies depends largely on urban sustainability. The research helps to unravel climate-carbon feedback and improve the awareness and preparedness of stakeholders, policy makers, and the general public to emergent patterns of local and regional climate changes. This project actively engages stakeholders, especially those from local cities, for project evaluation and outreach activities through regular meetings and annual workshops. In addition, this project involves participation of pre-college, undergraduate, and graduate students from ethnically underrepresented groups in education, research, and stakeholder engagement, to prompt the principle and initiatives of equity, diversity, and inclusion.This project integrates transdisciplinary quantitative and qualitative methods in the fields of atmospheric science, climate modeling, data science, and urban sustainability to discover nature-based solutions for sustainable urban development under changing climates. The overarching goal is to develop a transformative platform by integrating the physically based modeling of urban system dynamics and machine learning-based techniques in support of decision-making and urban planning. Specific research tasks and outcomes of this project include: (i) improving modeling capability of complex interplays between urban system dynamics and anthropogenic stressors in the built environment, (ii) creation of machine learning-based nimble surrogates for urban climate modeling to overcome high computational cost and other technical barriers, and (iii) bridging the gap between decision-making processes and climate modeling and enable discovery of sustainable nature-based solutions via synthesis analysis and multi-objective optimization. Furthermore, by recognizing that global climate changes are challenging to the socioeconomic growth and sustainable futures of cities worldwide, the new scalable platform enables policy makers to find and evaluate actionable mitigation and adaptation strategies that are tailored to city-specific development plans in a timely manner.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.