Periodic Reporting for period 2 - GEM (Global Earth Monitor)
Période du rapport: 2021-11-01 au 2023-08-31
The Global Earth Monitor project addresses the challenge of continuously monitoring large areas in a sustainable and cost-effective manner. The project aims to create a new, breakthrough model for the use of Earth observation data that will dramatically improve the use of Copernicus data and enable, for the first time, continuous monitoring of the planet on a global/regional scale at a sustainable cost. Breakthrough innovations in technology and methodology are planned, where a proprietary concept of Adjustable Data Cubes (a combination of static and dynamic data cubes) will be developed and integrated with the EO -oriented open-source machine learning (ML) framework eo-learn.The main impacts of Global Earth monitor are those that will influence the whole of human society by providing tools for better environmental monitoring and management - leading to a common goal: a sustainable environment
The key objectives are:
To take full advantage of the amount of data available, Copernicus needs a new model of data use - new processes that can run continuously - monthly, weekly or even daily - replacing brute force methods with smart techniques that scale cost-effectively. New methods of Earth observation (EO) are needed that work in a sustainable way - adding more value than their cost - at least on a continental if not global scale, able to automatically improve accuracy and detect changes as they occur. Users of data from Earth observations need a way to proactively monitor the entire globe and automatically look for changes and events worthy of closer examination. The primary goal of the Global Earth Monitor (GEM) project is to enable commercially viable continuous monitoring of the Earth, driven by a transition from traditional "strip mode" monitoring to "spot mode" monitoring (discovery of relevant details). This approach is based on the global monitoring and data use model of Global Earth Monitor.
The key objectives are:
To take full advantage of the amount of data available, Copernicus needs a new model of data use - new processes that can run continuously - monthly, weekly or even daily - replacing brute force methods with smart techniques that scale cost-effectively. New methods of Earth observation (EO) are needed that work in a sustainable way - adding more value than their cost - at least on a continental if not global scale, able to automatically improve accuracy and detect changes as they occur. Users of data from Earth observations need a way to proactively monitor the entire globe and automatically look for changes and events worthy of closer examination. The primary goal of the Global Earth Monitor (GEM) project is to enable commercially viable continuous monitoring of the Earth, driven by a transition from traditional "strip mode" monitoring to "spot mode" monitoring (discovery of relevant details). This approach is based on the global monitoring and data use model of Global Earth Monitor.
During the second reporting period, the remaining use-cases have been finalized. The use-cases have been employed to validate the GEM framework, used to drive the additional development, provided feedback, and served as a playground for various optimisations of the framework. While we have defined the AOIs and prepared majority of ground truth (GT) data already during the first reporting period, the second reporting period focused on demonstrating and validating the capabilities of GEM framework through the use-cases. Various approaches to change detection were also explored and used within use-cases. The use-cases demonstrated that it is possible to continually run models at low resolution at global scale in a repeated manner and at low costs, making cost-effective continuous monitoring a reality. We reflected on what can be achieved within the cost-effectiveness at scale constraint and showed drill-down and continuous monitoring approaches for the purpose of monitoring large areas (at continental scales), demonstrating clear (cost) benefits of drill-down mechanism.
Service for running large-scale, cost-effective, and continuous monitoring has also been developed with GEM framework during the second reporting period and presented in D5.7 - Demonstration deliverable, on a illustrative example of monitoring NDWI anomalies through time. The service was run for each Sentinel-2 observations since January 1, 2023, on a daily basis, and anomalies were detected with respect to historical data.
Novel ML approaches, methodologies and tools have been explored, and proof-of-concepts were investigated. Discussions about their usability within various use-cases pinpointed where (in use-cases) the novel approaches would work best. These studies were added to eo-learn-examples repository, extending eo-learn functionalities, particularly by bringing eo-learn and PyTorch closer together in a form that fosters easy and fast integration into research or inference pipelines.
We have built GEM processing framework (both eo-learn and eo-grow) to be cloud infrastructure agnostic. Particularly eo-learn is platform independent, meaning that the workflows can run on any infrastructure. During the second review period we have explored various cloud infrastructures for running the workflows, and openly shared several detailed examples and instructions on how to make use of GEM framework not only on AWS, but also on Copernicus Data Space Ecosystem (CDSE). Although commercially not as viable, and with (significantly) reduced capabilities, we understand the importance of CDSE and have spent significant effort preparing instructions how GEM framework can be leveraged there, despite CDSE not yet providing a commercial offering.
The results from use-cases have been made into data cubes, and are available through demonstration applications for general public, and can be accessed through GEM framework and Sentinel Hub services. A number of examples have been published on eo-learn-examples repository to facilitate uptake of the results.
Service for running large-scale, cost-effective, and continuous monitoring has also been developed with GEM framework during the second reporting period and presented in D5.7 - Demonstration deliverable, on a illustrative example of monitoring NDWI anomalies through time. The service was run for each Sentinel-2 observations since January 1, 2023, on a daily basis, and anomalies were detected with respect to historical data.
Novel ML approaches, methodologies and tools have been explored, and proof-of-concepts were investigated. Discussions about their usability within various use-cases pinpointed where (in use-cases) the novel approaches would work best. These studies were added to eo-learn-examples repository, extending eo-learn functionalities, particularly by bringing eo-learn and PyTorch closer together in a form that fosters easy and fast integration into research or inference pipelines.
We have built GEM processing framework (both eo-learn and eo-grow) to be cloud infrastructure agnostic. Particularly eo-learn is platform independent, meaning that the workflows can run on any infrastructure. During the second review period we have explored various cloud infrastructures for running the workflows, and openly shared several detailed examples and instructions on how to make use of GEM framework not only on AWS, but also on Copernicus Data Space Ecosystem (CDSE). Although commercially not as viable, and with (significantly) reduced capabilities, we understand the importance of CDSE and have spent significant effort preparing instructions how GEM framework can be leveraged there, despite CDSE not yet providing a commercial offering.
The results from use-cases have been made into data cubes, and are available through demonstration applications for general public, and can be accessed through GEM framework and Sentinel Hub services. A number of examples have been published on eo-learn-examples repository to facilitate uptake of the results.
We have built GEM processing framework (both eo-learn and eo-grow) to be cloud infrastructure agnostic. Particularly eo-learn is platform independent, meaning that the workflows can run on any infrastructure. During the second review period we have explored various cloud infrastructures for running the workflows, and openly shared several detailed examples and instructions on how to make use of GEM framework not only on AWS, but also on Copernicus Data Space Ecosystem (CDSE). Although commercially not as viable, and with (significantly) reduced capabilities, we understand the importance of CDSE and have spent significant effort preparing instructions how GEM framework can be leveraged there, despite CDSE not yet providing a commercial offering.
The results from use-cases have been made into data cubes, and are available through demonstration applications for public, and can be accessed through GEM framework and Sentinel Hub services. A number of examples have been published on eo-learn-examples repository to facilitate uptake of the results.The improvements to Sentinel Hub, to eo-learn, and the new eo-grow, all driven by the use-cases, are substantial. When talking about Sentinel Hub, the clear winner is the data cube engine (Batch Processing and Batch Statistical APIs), allowing to run large-scale processing at wide range of resolutions for large number of customers, allowing them to create static (stored for later retrieval) or dynamic Analysis Ready Data cubes with full power of custom scripts. Both eo-learn and eo-grow represent the basis of GEM framework and have proved indispensable in the GEM use-cases.
The results from use-cases have been made into data cubes, and are available through demonstration applications for public, and can be accessed through GEM framework and Sentinel Hub services. A number of examples have been published on eo-learn-examples repository to facilitate uptake of the results.The improvements to Sentinel Hub, to eo-learn, and the new eo-grow, all driven by the use-cases, are substantial. When talking about Sentinel Hub, the clear winner is the data cube engine (Batch Processing and Batch Statistical APIs), allowing to run large-scale processing at wide range of resolutions for large number of customers, allowing them to create static (stored for later retrieval) or dynamic Analysis Ready Data cubes with full power of custom scripts. Both eo-learn and eo-grow represent the basis of GEM framework and have proved indispensable in the GEM use-cases.