Application of Google earth engine python']python API and NAIP imagery for land use and land cover classification: A case study in Florida, USA

The analysis of land use and land cover data provides invaluable support to a variety of land management and conservation activities. However, historically its application has been limited by high costs associated with data acquisition, analysis, and classification. In recent years, freely available satellite imagery and geospatial data sets and rapid advancement in data analysis capabilities provide immense opportunities to understand and solve the real-world environmental problems. Open-source platforms such as Google Earth Engine (GEE) provide a planetary-scale environmental science data and analyses capability at much greater efficiency and accuracy than the traditional workflows. We evaluated the GEE Python API utility for classifying the freely available NAIP aerial imagery of 2017 to derive the land use land cover (LULC) information of a Panhandle area of Florida, USA. We identified eight major LULC classes with an overall accuracy of 86% and Kappa value of 79%. We completed all remote sensing data analyses procedures including data retrieval, classification, and report preparation in the Jupyter notebook, an open-source web application. Computation time for the procedure was less than 15 min. Our results demonstrate the usefulness of this approach for conducting land use and land cover analysis using much less time, money, and human resources. The open-source nature of GEE Python API and its library of remote sensing data could benefit remote sensing projects throughout the world, especially where access to commercial image processing software packages and remote sensing data are limited.