Periodic Reporting for period 2 - SEO-DWARF (Semantic EO Data Web Alert and Retrieval Framework)
Reporting period: 2018-01-01 to 2019-12-31
SEO-DWARF project addresses the bridging of the gap between the raw information that remote sensing images provide and the knowledge gained from the marine application domain in order to retrieve relevant to the semantic query data.
To this end, an enhancement of the already provided Sentinel services take place, by altering the form, content and/or nature of the information, and thereby adding value to it. Therefore, the detection of marine phenomena - e.g. hot spots, upwelling, fronts, turbidity, etc - from Earth Observation (EO) images will be achieved. Moreover, the proposed alerting system to the users contributes to a compact integrated retrieval and alerting service for marine phenomena, depending on the user needs and preferences.
The main objective of SEO-DWARF is to realize the content-based search of earth observation images on an application specific basis. The marine application domain and data from Sentinels 1, 2, 3 and ENVISAT will be used. Queries such as “Calculate the rate of increasing chlorophyll in the Baltic Sea” will be answered by the SEO-DWARF, helping users to retrieve the appropriate EO images for their specific needs or alert them when a specific phenomenon occurs.
To this end, an enhancement of the already provided Sentinel services take place, by altering the form, content and/or nature of the information, and thereby adding value to it. Therefore, the detection of marine phenomena - e.g. hot spots, upwelling, fronts, turbidity, etc - from Earth Observation (EO) images will be achieved. Moreover, the proposed alerting system to the users contributes to a compact integrated retrieval and alerting service for marine phenomena, depending on the user needs and preferences.
The main objective of SEO-DWARF is to realize the content-based search of earth observation images on an application specific basis. The marine application domain and data from Sentinels 1, 2, 3 and ENVISAT will be used. Queries such as “Calculate the rate of increasing chlorophyll in the Baltic Sea” will be answered by the SEO-DWARF, helping users to retrieve the appropriate EO images for their specific needs or alert them when a specific phenomenon occurs.
The development of the system is articulated in many sequential tasks that allow to organize the work in specific working activities. In the beginning of the project, the user needs and requirements were examined, defined and analyzed. Feedback from the users was also gathered by composing an online questionnaire. Afterwards, the ontology scheme and the remote sensing algorithms that would be used were defined after a thorough investigation of the state of the art and in correspondence with the user requirements. The selected phenomena include hot spots, upwelling, phytoplankton blooms, fronts, oil spills, trophic status index, turbidity, winds, waves and shallow water places. Data mining algorithms for the EO image metadata were defined, followed by the establishment of the architecture design, connectivity and interoperability of the SEO-DWARF and the front-end of the web service design, taking into account the INSPIRE guidelines.
At a second stage of the work, the implementation of the service has been started. Currently, two main tasks have been achieved: 1. the remote sensing and data mining algorithms, and 2. the ontology with metadata formulation. It is stated that the aforementioned work was implemented during the secondments of the participants of the consortium.
As for the main results, two remote sensing pipelines were constructed: the first pipeline includes reading Sentinel 2 images, creation and application of masks for land and cloud removal, atmospheric correction, processing for producing a phenomenon product and modification of the INSPIRE file which contains the metadata. The second pipeline takes as input the SLSTR L2 product of Sentinel 3, extracts the bands of interests, processes them and stores the results into a GeoTiff image. The oils spills, upwelling and fronts phenomena have been implemented and a potential processing tool has been documented.
At a second stage of the work, the implementation of the service has been started. Currently, two main tasks have been achieved: 1. the remote sensing and data mining algorithms, and 2. the ontology with metadata formulation. It is stated that the aforementioned work was implemented during the secondments of the participants of the consortium.
As for the main results, two remote sensing pipelines were constructed: the first pipeline includes reading Sentinel 2 images, creation and application of masks for land and cloud removal, atmospheric correction, processing for producing a phenomenon product and modification of the INSPIRE file which contains the metadata. The second pipeline takes as input the SLSTR L2 product of Sentinel 3, extracts the bands of interests, processes them and stores the results into a GeoTiff image. The oils spills, upwelling and fronts phenomena have been implemented and a potential processing tool has been documented.
SEO-DWARF’s progress beyond the state of the art is the promotion of international and inter-sectorial collaboration through research and innovation staff exchanges, and sharing of knowledge and ideas from research to market for the advancement of science and the development of innovation.
The expected results of the project are the development and implementation of automatic algorithms for extracting metadata from remote sensing images and their association with the corresponding ontology. Therefore the retrieval and serving of data based on the semantic queries performed by the user will be achieved. The added value services correspond to a semantic web alert and retrieval system for EO data from the Copernicus satellites.
As for the impacts until the end of the project, the promotion of the skills and careers of the exchanged staff, the sharing of multidisciplinary knowledge and know-how among the partners and the aligning of different scientific cultures for the integration of the knowledge from the marine domain will be a significant asset for all partners. The seconded staff is going to be re-integrated to the sending companies/institutes with an in-build return mechanism for further exploitation of their newly acquired and enhanced skills and knowledge. Moreover, the conducted complementary research of the partners will be pushed to the market by creating added value services to the Copernicus EO program.
The expected results of the project are the development and implementation of automatic algorithms for extracting metadata from remote sensing images and their association with the corresponding ontology. Therefore the retrieval and serving of data based on the semantic queries performed by the user will be achieved. The added value services correspond to a semantic web alert and retrieval system for EO data from the Copernicus satellites.
As for the impacts until the end of the project, the promotion of the skills and careers of the exchanged staff, the sharing of multidisciplinary knowledge and know-how among the partners and the aligning of different scientific cultures for the integration of the knowledge from the marine domain will be a significant asset for all partners. The seconded staff is going to be re-integrated to the sending companies/institutes with an in-build return mechanism for further exploitation of their newly acquired and enhanced skills and knowledge. Moreover, the conducted complementary research of the partners will be pushed to the market by creating added value services to the Copernicus EO program.