Machine Learning Applications in Remote Sensing of the Environment

Since 1970, the National Aeronautics and Space Administration (NASA) has provided free of charge remote sensing data captured by several sensors with different characteristic ranges, from geostationary to suborbital sensors, including those of the National Oceanic and Atmospheric Administration (NOAA), Sea-Viewing Wide Field-of-View Sensor (SeaWiFS), Moderate Resolution Imaging Spectroradiometer (MODIS), Landsat images, Shuttle Radar Topographic Mission (SRTM). Additionally, the Japan Aerospace Exploration Agency (JAXA) has provide the Advanced Spaceborne Thermal Emission and Radiometer (ASTER) images and digital elevation model (DEM), as well as the Phased Array type L-band Synthetic Aperture Radar (PALSAR). The European Space Agency (ESA) has provided optical and active remote sensing data such as Sentinel-2A and Sentinel-2B. Other commercial remote sensing data with high and very high spatial resolution is collected from sensors such as QuickBird, IKONOS, World View, and RapidEye sensors. Besides these various remote sensing data, automated and semi-automated algorithms enable more reliable analysis in many more applications than were previously used, especially in inaccessible and remote regions. They enable the potential to modify low-cost novel methodologies over multiple scales such as hydrologic modeling, geological mapping, and vegetation analysis and change detection.

The main goal of this Research Topic is to cover research regarding the latest methodologies and novels and machine learning in the following remote sensing applications:

• Land use land cover (LULC) classification and analysis
• Geohazard mapping and monitoring
• Change detection
• Geological mapping
• Hydrological modeling
• Ore geology mapping
• Fish forecast
• Forest and vegetation species detection
• Glaciers mapping and change detection
• Impervious surface mapping

Submissions from attendees of the EOEC-GiT4NDM 2019 joint conference are welcomed.