Spatiotemporal Changes in Urban Water Resources: A Comparative Study of Geospatial and Remote Sensing Tools and Techniques

As urban expansion continues, understanding water resource dynamics in urban areas is crucial for sustainable city planning, flood risk mitigation, and long-term water security. Accurately identifying spatiotemporal changes in urban water resources is important for environmental monitoring and management. Geospatial and remote sensing tools and techniques enable efficient monitoring of water resources in rapidly growing cities, aiding in decision-making for sustainable urban planning. By leveraging advanced geospatial tools and techniques, this research examined spatiotemporal changes in 17 lakes within the rapidly expanding Dallas-Fort Worth (DFW) metropolitan area in the United States from 1984 to 2021, using the Global Surface Water (GSW) dataset via cloud-based remote sensing (Google Earth Engine, GEE) and non-cloud-based remote sensing (ArcGIS Pro). The research employed iso-cluster unsupervised classification and deep learning-supervised classification methods for land cover analysis. The study utilized ArcGIS Pro’s pre-trained deep learning model, based on the National Land Cover Database (NLCD), to classify Landsat images. A comparative analysis was conducted to statistically compare the classification outcomes of the Landsat/NLCD-ArcGIS Pro and GSW-GEE methods in estimating changes in urban lakes. The findings indicate that there is no statistically significant difference between the two datasets and methods. This suggests that both the Landsat/NLCD-ArcGIS Pro and GSW-GEE methods can effectively detect changes in lakes over space and time, although their accuracy may vary slightly depending on the specific lake and classification approach used. Moreover, the total surface area of all lakes estimated using the GSW-GEE method is slightly larger than that estimated using the Landsat-ArcGIS Pro method. Overall, this study highlights the importance of selecting the appropriate dataset and method for analyzing spatiotemporal changes in urban lake environments. The findings have practical implications for environmental researchers, managers, and policymakers involved in urban lake conservation and management.