**The manuscript has been submitted to Urban Climate for peer review.Estimating street-level air temperature is a challenging task due to the highly heterogeneous urban surfaces, canyon-like street morphology, and the diverse physical processes in the built environment. Though pioneering studies have embarked on investigations via data-driven approaches, many questions remain to be answered. In this study, we leveraged an innovative framework and redefined the street-level temperature estimation problem using Graph Neural Networks (GNN) with spatial embedding techniques. The results showed that GNN models are more capable and consistent of estimating street-level temperature among tested locations, benefiting from its unique strength in handling extensive data over unstructured graph topology. In addition, we conducted an in-depth analysis of feature importance to enhance the model interpretability. Among the urban features analyzed in this study, the time-variant canopy density and meter-level land use data emerge as crucial factors. Our findings highlight GNN’s high potential in capturing the complex dynamics between urban elements and their impacts on microclimate, thus offering valuable insights for comprehensive urban data collection and urban climate modeling in general. Collectively, this study also contributes to urban planning and policy by providing avenues to enhance city resilience against climate change, thereby advancing the agenda for environmental stewardship and urban sustainability.

** The latest version of this paper has been published in the Journal of Advances in Modeling Earth Systems (JAMES) from AGU. Please refer to the latest version on JAMES and cite as: Li, P., & Sharma, A. (2024). Hyper-local temperature prediction using detailed urban climate informatics. Journal of Advances in Modeling Earth Systems, 16, e2023MS003943. https://doi.org/10.1029/2023MS003943 Modeling urban microclimate accurately is challenging due to the high surface heterogeneity of urban land cover and the vertical structure of street morphology. Recent years have witnessed significant efforts in numerical modeling and data collection of the urban environment. Nonetheless, it is difficult for the physical-based models to fully utilize the high-resolution data under the constraints of computing resources. The advancement in machine learning techniques offers the computational strength to handle the massive volume of data. In this study, we proposed a machine learning approach to estimate point-scale street-level air temperature from the urban-resolving mesoscale climate model and a suite of hyper-resolution urban informatics, including three-dimensional urban morphology, parcel-level land use inventory, and a dense weather observation network. We implemented this approach in the City of Chicago as a case study. The proposed approach vastly improves the resolution of temperature predictions in cities, which will help the city with walkability, drivability, and heat-related behavioral studies. Moreover, we tested the model's reliability on out-of-sample locations to investigate the application potentials to the other areas. This study also aims to gain insights into next-gen urban climate modeling and guide city observation efforts to build the strength for the holistic understanding of urban microclimate dynamics.

** The latest version of this paper has been published in the Journal of Advances in Modeling Earth Systems (JAMES) from AGU. Please refer to the latest version on JAMES and cite as: Li, P., Sharma, A., Wang, Z.-H., & Wuebbles, D. (2023). Assessing impacts of environmental perturbations on urban biogenic carbon exchange in the Chicago region. Journal of Advances in Modeling Earth Systems, 15, e2023MS003867. https://doi.org/10.1029/2023MS003867