CDI-Type II: Collaborative Research: A Paradigm Shift in Ecosystem and Environmental Modeling: An Integrated Stochastic, Deterministic, and Machine Learning Approach

该项目将通过开发一套随机建模方法，结合地质统计学和机器学习技术，推动系统建模方法的发展。新的系统建模方法将利用现场和卫星遥感数据来改进系统模型参数和模型结构。这些新的发展，加上观察到的数据，将通过计算思维推动生态系统和环境科学的发展。拟议的方法将用于开发网络支持的随机碳天气系统，以提供更充分的区域碳交换量化，这对于更好地理解碳-气候-大气反馈和促进气候政策制定至关重要。拟议的方法将通过以下方式改变目前的系统建模方法：(1)开发生态系统和环境系统确定性微分方程模型的随机版本；(2)开发地理空间统计技术，以充分利用多方面的观测数据来改进模型参数化；(3)开发先进的统计和机器学习技术，以进一步利用观测数据来改进模型结构；以及(4)应用改进的模型来研究土地利用变化的社会和生物地球化学影响。拟议的网络支持的陆地生态系统模型的优势将包括：(1)有效地量化区域净碳交换和相关的不确定性；(2)使用先进的统计和机器学习技术以及在美国获取的时空数据来改进系统模型参数和结构。项目成果包括：(1)创新的网络支持的碳天气系统，该系统能够以高空间和时间分辨率量化美国大陆的净碳交换和相关的概率信息；(2)一套变革性的高级数学、统计和系统建模技术，可应用于其他复杂的建模领域(例如，水文建模)。该项目将用计算思维极大地推动生态系统科学的发展，并将为在高度跨学科的研究环境中培训新一代科学家提供独特的机会。

This project will advance systems modeling approaches by developing a suite of stochastic modeling approaches, coupled with geostatistical and machine learning techniques. The new system modeling approach will utilize both in situ and satellite remotely sensed data to improve system model parameters and model structure. These novel developments, together with observed data, will advance ecosystem and environmental sciences through computational thinking. The proposed approach will be used to develop a cyber-enabled stochastic carbon-weather system to provide more adequate quantification of regional carbon exchanges, which is critical to better understanding carbon-climate-atmosphere feedbacks and facilitating climate-policy making. The proposed approach will transform the current system modeling approach by (1) developing a stochastic version of the deterministic differential equation models of ecosystems and environmental systems; (2) developing geospatial statistical techniques to fully exploit multifaceted observational data to improve model parameterization; (3) developing advanced statistical and machine learning techniques to further utilize observational data to improve model structure; and (4) applying the improved model to examine the societal and biogeochemical impacts of land use change. Advantages of the proposed cyber-enabled terrestrial ecosystem model will include: (1) Efficiently quantifying regional net carbon exchanges and associated uncertainty and (2) Improving system model parameters and structure using advanced statistical and machine learning techniques and spatiotemporal data acquired over the U.S. Project deliverables include: (1) An innovative, cyber-enabled carbon-weather system that can quantify net carbon exchanges and associated probabilistic information at high spatial and temporal resolution for the continental U.S. and (2) a suite of transformative advanced mathematical, statistical and system modeling techniques that could be applied to other complex modeling fields (e.g., hydrological modeling). This project will significantly advance ecosystem sciences with computational thinking and will provide a unique opportunity to train a new generation of scientists in a highly interdisciplinary research environment.