Applied Geospatial Data-science Initiative for Urban Climate Change Studies (AGDI-UCCS)

Predictive understanding

predictive understanding

Predictive understanding refers to the ability of a system, typically an artificial intelligence or machine learning model, to anticipate future events or outcomes based on historical data and patterns.

Source: Source

of the complex and interrelated urban processes and their impacts on heat build-up and local climate of rapidly growing cities is of critical need towards achieving urban climate change

climate change

A change in the average conditions — such as temperature and rainfall — in a region over a long period of time.

Source: NASA Climate Kids Source

resilience. This project will establish the Applied Geospatial Data-science Initiative for Urban Climate Change Studies (AGDI-UCCS). The overarching goal of AGDI-UCCS is to enhance collaborative research, education, experiential training, and professional development opportunities for students and emerging researchers from historically underrepresented minority communities. AGDI-UCCS research will focus on developing geospatial modeling applications by integrating remotely sensed data and products to achieve a predictive understanding of urban climate change impacts in general, and more specifically the dynamic processes of rapidly developing urban landscapes of mid-size cities and their suburban landscapes of the mid-south. AGDI-UCCS activities will expand and strengthen AAMU’s collaborations with two national laboratories (NLs): Pacific Northwest National Laboratory (PNNL) and Oak Ridge National Laboratory (ORNL).

The AGDI-UCCS will develop a geospatial modeling framework by integrating remotely sensed data products in WRF-UCM to improve UHI simulations over Alabama’s rapidly developing Huntsville metropolitan area being the primary case study site. For rapidly growing cities as in our study area, default LULC in the WRF model can lead to substantial mismatch between model inputs and actual LULC extents when applied at variable spatial scales and over different periods. Thus, we hypothesize that incorporating appropriate and timely representations (i.e. scale/resolution) of LULC and Urban Canopy Parameters (UCPs) in the model will substantially improve the model’s predictive capabilities at specific locations and across multiple scales. We will evaluate accuracies of UHI simulations at variable spatial resolutions by integrating remotely sensed data products as urban canopy parameter input in the WRF-UCM. Further, UHI intensities and their spatial patterns during recent extreme heat wave events will also be evaluated. Findings of this work will contribute to improve predictive capabilities of WRF-UCM to advance scientific understanding of urban-climate interactions and their impacts on incidences of heat waves, heat stress, and energy demands in rapidly growing cities.

In addition, this project will provide experiential learning, scientific research and geospatial training opportunities to students from traditionally underrepresented communities to actively engage students in scientific research and professional training activities at AAMU and collaborating national laboratories. We will recruit and train a total of 6 undergraduate students and 2 graduate students (MSc). Additionally summer research apprenticeship program will be introduced to train pre-college level students that will be recruited from local high schools predominantly serving historically underrepresented students. Through our training and mentoring activities, we aim to contribute to enhancing diversity in the future STEM workforce by forming a nucleus for a future pool of young scientists equipped with geospatial modeling skills and expertise.