top of page
AdobeStock_268518669.jpeg

Recent Publications from GEAR Lab

GEAR Lab members have recently published a number of collaborative articles investigating geospatial digital twins, GeoAI, spatial autocorrelation, geospatial big data, and their applications in COVID-19 modeling, disaster resilience, and coastal sustainability.

Rendered 3D model for the City of Galveston in CityEngine.

Probability of non-vehicle-related human harm during flash flooding in harris county (hypothetical event duration = 72 h, hypothetical precipitation = 35 inches)


The COVID-19 pandemic in Korea by the end of September 2020: (A) Timeline of the COVID-19 pandemic in Korea and Jeju from January 1, 2020 to September 30, 20201; (B) Province-level distribution of cumulative COVID-19 confirmed cases in Korea by September 30, 2020 2; (C) COVID-19 indicators and Google Trends Index from January 1, 2020 to September 30, 2020, including case fatality rate in Korea (the percentage of people who die from COVID-19 among all individuals confirmed with the disease in Korea), daily new cases in Korea, daily new cases in Jeju, Google Trends Index of the search term “COVID Korea”, and Google Trends Index of the search term “COVID Jeju”.


  • Xu, Y., Liu, C., Wang, L. and Zou, L., 2022. Exploring the Spatial Autocorrelation in Soil Moisture Networks: Analysis of the Bias from Upscaling the Texas Soil Observation Network (TxSON). Water, 15(1), p.87. https://www.mdpi.com/2073-4441/15/1/87


A schematic plot of the implementation of block kriging on top of the Thiessen polygon generated from the soil moisture stations (numbered 1–15). When spatial autocorrelation was detected, block kriging is used to remove the autocorrelation, using Thiessen polygons as blocks for the areal interpolation (blue indicates low soil moisture content and red indicates high soil moisture content), rather than point/pixel-based interpolation.


  • Wang, Z., Lam, N.S., Sun, M., Huang, X., Shang, J., Zou, L., Wu, Y. and Mihunov, V.V., 2022. A Machine Learning Approach for Detecting Rescue Requests from Social Media. ISPRS International Journal of Geo-Information, 11(11), p.570. https://www.mdpi.com/2220-9964/11/11/570

Model evaluation results after hyperparameter tuning and cross-validation (bars indicate standard deviations). Note: Although RF and CNN have the same F1 score (0.950), RF has a lower standard deviation (0.006 vs. 0.007).


Congratulations to the GEAR Lab members, and we look forward to hearing more achievements from GEAR Lab! Gig'em!

Comments


GearLab-Logo-White.png

Geospatial Exploration and Resolution (GEAR) Lab

bottom of page