ESSI4.3

Within the Italian Government’s guidelines on space and aerospace matters to achieve the strategic objectives of the national space policy [1], the “Telecommunications, Earth Observation and Navigation” (TLC/EO/NAV) sector is the first listed by priority order. TLC/EO/NAV satellite services and applications (the so-called “downstream”) will be exploited by citizens and valorized by Institutions under an integrated application perspective. The downstream sector is therefore a key element to maximize the socio-economic impact of investments in the space sector.

In this context, the Italian Space Agency (ASI) aims to bring its contribution, by stimulating the downstream development through initiatives aiming to promote the use of national and European space systems, and the demonstration of new techniques and procedures for information generation to create products and deliver innovation services.

The present paper focuses on the “scientific downstream”, i.e. the (pre-)operational exploitation of state-of-the-art processing and analytical workflows of TLC/EO/NAV data that have been designed, tested, validated and demonstrated by researchers and academia to formerly answer a specific technical-scientific question (e.g. a more accurate retrieval of a geophysical parameter such as soil moisture in vegetated and crop areas) and are brought to a development and engineered stage so as to generate end-use or value-added products (e.g. maps of multi-temporal spatial variation of soil moisture vs. rainfall and irrigation practices, at a temporal frequency as satellite data allow).

To accelerate a faster uptake of satellite-based technologies for the geosciences as new EO missions are launched and made operative – COSMO-SkyMed First and Second Generation in the Synthetic Aperture Radar domain, and PRISMA in the hyperspectral –, ASI is running several initiatives, including:

• data exploitation [e.g. 2], to make users more acquainted with satellite data and consolidate or prepare for new applications;
• joint research projects with the national scientific community [e.g. 3], to develop novel algorithms up to at least a Scientific Readiness Level (SRL) of 4, i.e. “Proof of concept”, according to ESA SRL Handbook EOP-SM/2776;
• dedicated R&D programs for SAR and hyperspectral algorithm developments, supporting projects that aim to address key application domains (e.g. precision agriculture, natural hazards, urban areas);
• prototyping thematic platforms allowing consolidated algorithms and processing routines to be used for generation of EO-based products [e.g. 4];
• launch a new program for demonstration projects to capitalize the above algorithm legacy and prepare the scientific downstream.

This paper will discuss ASI’s current activities, achievements, lessons learnt and ongoing developments in the accomplishment of the above roadmap.

[1] https://presidenza.governo.it/AmministrazioneTrasparente/Organizzazione/ArticolazioneUffici/UfficiDirettaPresidente/UfficiDiretta_CONTE/COMINT/DEL_20190325_aerospazio.pdf

[2] Battagliere et al. (2021) Satellite X-band SAR data exploitation trends in the framework of ASI’s COSMO-SkyMed Open Call initiative, Procedia Computer Science 181, 1041–1048.

[3] Tapete et al. (2020) Development of algorithms for the estimation of hydrological parameters combining COSMO-SkyMed and Sentinel time series with in situ measurements, IEEE M2GARSS 2020, 53–56.

[4] Candela et al. (2021) “The Italian Thematic Platform costeLAB: from Earth Observation Big Data to Products in support to Coastal Applications and Downstream,” Proceedings of the 2021 conference on Big Data from Space, EUR 30697 EN, ISBN 978-92-76-37661-3, doi:10.2760/125905, JRC125131.

How to cite: Tapete, D. and Coletta, A.: ASI’s roadmap towards scientific downstream applications of satellite data, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-5643, https://doi.org/10.5194/egusphere-egu22-5643, 2022.

The recent OGC Cloud Concept Development Study [1]  has shown that the major (big) Geospatial Data providers are going towards Cloud solutions not only to make more data more accessible, but also to locate data processing next to the data. Meanwhile, recent experiences from the H2020 e-shape project show that the EO developers community still needs support to fully adopt the Cloud all the more that based on the feedback received during e- shape’s first sprint, the Earth Observation Cloud platforms still need to mature to be more attractive. In order to support the good connection between Data providers, Technology providers and EO developers, it is critical that sponsors keep on supporting the efforts from the Earth Observation community at a number of levels: Enhancing Copernicus and other open data accessibility, developing Clouds and platforms interoperability and operational maturity, increasing cloud skills among developers and scientists, sustaining funding mechanisms long enough to allow the rendez-vous in the Cloud of all the critical stakeholders with good timing to reach the critical point of self-sustainability.

During this process it is important to not only develop the technical skills and new platforms capacities, but also to develop a good understanding of the pricing mechanisms and how to optimize the costs. This is very needed to develop the trust that outsourcing infrastructures will lead to the expected budget savings and  to trigger the budgets organization evolutions that  moving to Cloud technologies requires. 

[1]  Echterhoff, J., Wagermann, J., Lieberman, J.: OGC 21-023, OGC Earth Observation Cloud Platform COncept Development Study Report. Open Geospatial Consortium (2021). https://docs.ogc.org/per/21-023.html

How to cite: Voidrot-Martinez, M.-F., Hempelmann, N., and Lieberman, J.: Lessons learned from e-shape H2020 Project on the use of the Cloud for Earth Observation, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-5993, https://doi.org/10.5194/egusphere-egu22-5993, 2022.

Increasing agricultural production is inevitable in the future since population growth and climate change have led to significant pressure on global food security. One of the ways is to intensify the existing cropland by multi-cropping practice, allowing multiple uses of a single field during one year.  This research aims to identify and map double-cropping land using multi-temporal Sentinel 2 imagery from 2021 and advanced machine learning models. The case study focus is on Bačka and Srem, regions located in the Autonomous Province of Vojvodina, Republic of Serbia. These regions are characterized by fertile land and widespread agriculture production. However, there is a low presence of double-cropping practice due to usually dry summers, but with a tendency to change as the number of irrigation systems increase.

Considering the small amount of double-cropping fields, there is a need for direct ground truth data collection. For that reason, the first step was to reduce the area of interest to get insight into the locations of potential double-cropping land. This result was obtained by using the threshold method based on the phenology of crops during the year. The NDVI (Normalized Difference Vegetation Index) time series was utilized to define appropriate thresholds for feature two peak values to discriminate double-cropping within each pixel. The identification of the results was used on-site for collecting ground truth data. Based on the collected data and the analyzed NDVI time series, besides double-crop, three more classes of arable land were distincted and included in the classification: single winter crops, single summer crops and clover. The collected data contained 46 parcels of double crops, 43 single winter crops, 55 single summer crops and 27 parcels of clover. We used time-series images to create a dataset for training the pixel-based Random Forest classification. The results showed a very high overall accuracy of 99% and an  F-score higher than 0.9 for each of the classes.

This methodology is a suitable approach for detecting double-cropping systems, with further potential to identify exact crop types and the main practice of combining crops. The findings of this study showed that only about 2% of the study area was under this production. Except for positive economic outcomes, utilizing these systems brings significant environmental benefits and rational use of the soil without expanding physical cropland but with the same advantages. Therefore, the resulting geospatial datasets of double cropping croplands could help solve important questions relevant to food security, irrigation and climate change.

How to cite: Marković, M., Lugonja, P., Brdar, S., Živaljević, B., and Crnojević, V.: Detection of Double-Cropping Systems Using Machine Learning and Sentinel 2 Imagery - A Case Study of Bačka and Srem Regions, Serbia    , EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-6225, https://doi.org/10.5194/egusphere-egu22-6225, 2022.

Earth Observation plays important role in Precision Agriculture. Precision agriculture, holds great promise for modernization of agriculture both in terms of environmental sustainability and economic outlook.  The vast data archives made available through Copernicus and related infrastructures, combined with a low entry threshold into the domain of AI-technologies has made it possible, if not outright easy, to make meaningful predictions that divides individual agricultural fields into zones where variable rates of fertilizer, irrigation and/or pesticide are required for optimal soil productivity and minimized environmental impact. Usage of Earth Observation in Precision Agriculture is in many years subjects of intensive research, but there already exist commercial application. But full potential of EO is till now not utilised. This limits the uptake of precision agriculture technology and thus also the realization of its promised benefits. EO4Agri project in its Strategic Research Agenda identified as one from  priorities for future to support collaborative research of expert from different domains, EO, agriculture, Artificial Intelligence and also direct involvement of farmers or advisors. But till now there didn’t exist platforms, which will be able to support such collaborative research. Now The Map Whiteboard is opening new possibilities for such collaborative research in this domain.

The Map Whiteboard concept at the centre of this submission is intended to plug into the “traditional” workflow of variable rate applications and enables agricultural advisors/extension services and farmers to interact, adjust and share an understanding of the estimations made by the ‘black box’, thus increasing the trust in and improving the quality of the prediction models. The vision of the Map Whiteboard innovation was conceived out of a sequence of large-scale collaborative writing efforts using Google Docs. As opposed to traditional offline word processing tools, Google Docs allows multiple people to edit the same document]—at the same time—allowing all connected clients to see changes made to the document in real-time by synchronising all changes between all connected clients via the server. The ability to work on a shared body of text, avoiding the necessity to integrate fragments from multiple source documents and with multiple styles removed many obstacles associated with traditional document editing. The Map Whiteboard technology seeks to do the same for the traditional use of GIS tools. The overall vision for the technology is that a Map Whiteboard will be to GIS what Google Docs is to word processing. We are now introducing this technology as a tool for collaborative work farmers and advisory services offering them analysis of EO data. The Map Whiteboard is now in intensive tested  and now are integrated tools for online analysis of EO data.

How to cite: Charvat, K., Bergheim, R., Berzins, R., Langovskis, D., Zadrazil, F., and Kubickova, H.: Map WhiteBoard - New Technology in Collaborative Research in Smart FArming, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-12431, https://doi.org/10.5194/egusphere-egu22-12431, 2022.