Mapping Urban Growth of Dallas-Fort Worth Metropolitan Area from 1984 to 2021 Using Landsat Data

Keywords: Urbanization, Land cover change, Machine learning
Abstract Type: Paper Abstract

Abstract

The Dallas-Fort Worth (DFW) Metropolitan Area is one of the fastest-growing metropolitan areas in the U.S. Its rapid growth requires research investigation. Various studies have been conducted to understand the urbanization patterns and impacts of urban expansion using satellite data in this region. In this study, we will apply a machine learning method to retrieve the long-term impervious surface cover for the DFW Metropolitan Area. We will use high-resolution planimetric maps obtained from the municipalities and the National Agriculture Imagery Program (NAIP) data as reference data. Landsat data will be used to generate the annual continuous impervious surface maps. The Landsat images are composited to summer and winter predictor variables according to vegetation seasonality. Composited seasonal images are able to reduce the variation and noise caused by vegetation phenology, atmospheric effect, and cloud contamination. The random forest model is used to predict impervious surface cover for every year from 1984 to 2021. The resultant maps are per-pixel continuous representations of impervious surface cover at the spatial scale of 30-m annually from 1984 to 2019. The counties of Dallas, Tarrant, Denton, and Collin have the largest urban growth during the study time period. Tarrant, Denton, and Collin are also the three counties adjacent to Dallas county to the west, northwest, and southwest, respectively. This method can be potentially applied to other land cover types such as forest and cropland in other regions.