The spatial dimensions and temporal resolutions of the change detection analyses have been limited by traditional methologies (i.e., desktop computing, open source). For decades, Remote Sensing (RS) have been collected large amounts of data, which are difficult to manage and analyzed using standard software packages and desktop computing resources. For this, Google developed the Google Earth Engine (GEE) cloud computing to successfully meet the issues of large data analysis. GEE is a cloud-based computing as a planetary-scale geospatial platform for Earth science data and analysis, allows these spatiotemporal constraints to be lifted and handle massive amounts of geodata over wide areas and to monitor the environment over long periods of time. We summarize the GEE data catalog’s big geospatial data such as Climate and weather for surface temperature, climate, atmospheric and weather. It also contains Imagery like Landsat, Sentinel, MODIS and High-resolution Imagery and Geophysical information contains of terrain, land cover, cropland, and other geophysical data. Furthermore, supervised machine and unsupervised machine algorithms   were used for several applications for Land Use Land Cover (LULC), hydrology, urban planning, natural disasters, and climate assessments. The research describes the utilization to resolve the big data using machine learning algorithm.

Keywords: Remote Sensing, GEE, cloud-based, machine learning, geospatial data