Multi-temporal spatial prediction techniques that leverage long-term historical observations can yield more accurate and more interpretable predictions than the more commonly used pair-wise change detection techniques. ![]() With the greater availability of low-latency and global multi-temporal remote sensing data, opportunities exist to exploit detection of time-dependent features of highly temporal Earth science observations. For change detection techniques, however, most methods have focused on paired before/after observations. In the AIST-2014 effort, for example, the team prototyped automated classification of phase unwrapping features in processed Level 2 interferograms from the ESA (European Space Agency) Sentinel-1A/B satellite data streams. ML approaches for Earth science data have typically been applied to single scene feature detection. Automating these time domain-based feature detection procedures is challenging because of the complexity of processing, the need to process large temporally co-registered data stacks, and the human expertise needed to assess the time domain signals. The steps in change detection, which require a human-in-the-loop, have become a bottleneck for rapid and reliable exploitation of geodetic SAR data for both long-term monitoring and event rapid response. These change detection approaches are often processed with threshold values set on the underlying SAR measurement values of either amplitude or coherence. This requires change detection-based approaches utilizing before and after event scenes. A limiting factor, however, has been the continued need for expert analysis for detection of features in the Level 2 data products as well as transients in the Level 3 time-series data products.ĭecision support products are most useful if they are generated rapidly and with simplified information (e.g., damaged/not damaged, flooded/not flooded, etc.). The team’s NASA Earth Science Technology Office (ESTO) Advanced Information System Technology (AIST) AIST-2011 and AIST-2014 efforts towards an Advanced Rapid Imaging and Analysis (ARIA) data system successfully demonstrated the capability to automate high-volume SAR image analysis in a cloud computing environment. Any anomalies that pass thresholds can be used to notify these experts for their in-depth analysis. While individual subject matter volcano, flood, and landslide experts will provide their own in-depth analysis for actual events, the value of an automated approach is to automatically process Level 3 time series data covering a broad number of AOIs and then apply machine learning (ML) for detecting potential anomalies that otherwise were not actively being monitored. The value-added to end-users through this ACCESS project is the ability to have an automated system using SAR data to monitor a large number of areas having a high probability of three natural hazards:Ī machine learning (ML)-based approach to detecting anomalies in multi-temporal SAR data by querying EOSDIS DAACs for relevant data over areas of interest(s) (top row), processing from Level 1 Single Look Complex (SLC) to Level 3 time series (middle row), and detecting potential anomaly signals in the time domain (bottom row). For example, barriers to rapid hazard response include the lack of automated data triggers from forecasts, the need for specialized processing parameters that currently rely on intervention by subject matter experts, and the manual delivery of actionable science data products to decision support communities. ![]() The ability to effectively utilize SAR data for areas including research, long-term monitoring of spatial areas of interest (AOIs), and rapid hazard response has been limited by barriers including large data volumes, processing complexity, and long latencies. SAR imagery also can be used to monitor and detect warning signs of natural hazards such as volcano inflation preceding an eruption or changes in a slope in advance of a landslide. This allows high-relief SAR imagery to be created day or night, rain or shine across all biomes. ![]() In addition, the wavelengths used for creating SAR imagery can penetrate clouds, smoke, soil, ice, and tree canopies. ![]() Since SAR relies on reflected radar to create imagery, it does not need illumination from an outside source (such as the Sun). Synthetic Aperture Radar (SAR)-based geodetic imaging has revolutionized Earth science research in many areas, including studies of the solid earth, ecosystems, and cryosphere. Principal Investigator (PI): Hook Hua, NASA's Jet Propulsion Laboratory Overview
0 Comments
Leave a Reply. |