8. Analysis of climatic trends in selected regions

Mentor: Jaroslav Šmejkal

The main components of EUXDAT & Stargate Climatic data processing HUB are the following:

  • EUXDAT Portal: It is the entrance point to EUXDAT functionalities. It provides a web GUI which gives access to the workflow execution tool, monitoring of data analytics execution, the catalogue and other useful tools;
  • Identity and Authorization Manager: This component is responsible of managing user accounts and managing access to the functionalities and data in EUXDAT, according to security policies and to the rights granted to each user;
  • Data & Algorithms Catalogue: It keeps a record of all the algorithms, applications and datasets which are available in EUXDAT;
  • Data & Algorithms Repository: This component deals with the storage of datasets, algorithms and images, in general, that will be used for running data analyses;
  • Data Manager: It is the component in charge of moving data to the proper location. It will configure and operate extraction APIs for accessing several data sources. For doing so, it also has all the data connectors that are necessary;
  • SLA Manager: It agrees on quality attributes to fulfil and the values to be met for each attribute. It also retrieves information about the monitoring of such attributes in order to detect SLA breaches;
  • Orchestrator: It deals with the management of resources, mainly from the functional perspective, deploying the algorithms and the corresponding data in the optimal location. It also deals with the application profiles generation and management;
  • Monitoring: It retrieves information about the resources execution and status, as well as about the algorithms execution and datasets status.

Challenge Description: Analysis of climatic trends in selected regions

Analysis of situation and climatic trends in regions for following variabled: precipitation, evaporation, sunny days and temperature.

Prague INSPIRE Hackathon 2020 – Second Stage

We are ready to start the second part of Prague INSPIRE Hackathon – the so-called remote stage. You are invited to join the Prague INSPIRE hackathon. This stage is as indicated happening remotely (online, virtually, in cyber space).  We have identified a set of challenges that you are encouraged to answer or contribute to solve during this remote stage of the hackathon commencing on 2nd December 2019 and ending 12th January 2020. See our inspiring challenges and how to join below. The final stage* of the hackathon will take place in Prague on 27 – 29 January 2020.  

The goal of the Prague  INSPIRE Hackathon 2020 is to promote utilisation of digital innovation hubs in agriculture and transport.

For more details about registration and challenges, please go to https://www.plan4all.eu/prague-inspire-hackathon-2020/

7. Testing possibilities of Sentinel 1 data for yield forecast

Mentors: Karel Charvat, Jiri Kvapil

WirelessInfo is part of the SmartAgirHub project. Currently we are also closely cooperating with the PoliRural project in this direction. We see three roles of Digital Innovation Hubs in the future:

  • Social space and educational materials, where different groups of users can share their experiences and where users could be trained
  • Place where different types of users can test new applications
  • Place for developers, where advanced infrastructure will be available for practical testing

Our work during the hackathon will be focused on the last topic. We are now publishing on our cloud set of tools for EO, IoT, Big Data Management, AI, etc. We are also implementing tools like Jupyter Notebook.  Set of tools like SensLog, Orfeo Geotool, R, Grass, Micka, HSLayers NG and others are available. The hub also offer graphical card and framework for Artificial intelligence

The part of Hub are also Sentinel 1 and 2 images from Moravia and farm data from Rostenice

Challenge Description Testing possibilities of Sentinel 1 data for yield forecast: 

Tested possibilities of uf utilisation of Sentinel 1 data for yield monitoring and forecast on Rostenice farm and comparison with utilisation of Sentinel 2 and Landsat dataSpecial prize: One year of free access to the SmartAgriHub innovation hub.

6. Using AI algorithms for defining boundaries of agriculture fields on the base of Sentinel 2 Images.

Mentors: Hana Kubickova, Jan Horak, Ondrej Kaas, Jiri Kvapil

WirelessInfo is part of the SmartAgirHub project. Currently we are also closely cooperating with the PoliRural project in this direction. We see three roles of Digital Innovation Hubs in the future:

  • Social space and educational materials, where different groups of users can share their experiences and where users could be trained
  • Place where different types of users can test new applications
  • Place for developers, where advanced infrastructure will be available for practical testing

Our work during the hackathon will be focused on the last topic. We are now publishing on our cloud set of tools for EO, IoT, Big Data Management, AI, etc. We are also implementing tools like Jupyter Notebook.  Set of tools like SensLog, Orfeo Geotool, R, Grass, Micka, HSLayers NG and others are available. The hub also offer graphical card and framework for Artificial intelligence

The part of Hub are also Sentinel 1 and 2 images from Moravia and farm data from Rostenice

Challenge Description Using AI algorithms for defining boundaries of agriculture fields on the base of Sentinel 2 Images: 

To test different deep learning methods for analysis of multitemporal Sentinel 2 data to detect boundaries of fields

Special prize for best student or freelance  in EU: coverage of cost related with participation on in situ part of Prague Hackathon including tickets and hotel

5. Clustering of European NUTS 3 regions based on different parameters

Mentor: Karel Charvat

The Polirural innovation Hub will be central real and virtual space, where all stakeholder (policymakers, public servant, regional development agencies, NGO, citizens, scientist, developers, data experts, planners) will meet and share their needs and achievements to improve policy and decision making on local, regional and eventually national level. The core  of Innovation Hub will be platform Digital Innovation Hub (DiH). This DiH will also support sharing of information with other projects and initiatives. Innovation Hub objectives:

  • offer access to data cross European NUTS3 regions
  • Offering other pan european Data sets like Open Land Use, Smart Point of Interest
  • offer development environment based on Jupyter notebook and list of other tools supporting development of new application
  • HSlayers NG

Challenge Description Clustering of European NUTS 3 regions based on different parameters: The goal is to develop applications, which will support clustering of European NUTS 3 . The Apps will allow to select different parameters from existing database, provide clustering on base of this parameters and visualise results

4. Web solution for attractiveness of regions

Mentor: Otakar Cerba

The PoliRural innovation hub will be a central real and virtual space, where all stakeholders (policymakers, public servant, regional development agencies, NGO, citizens, scientist, developers, data experts, planners) will meet and share their needs and achievements to improve policy and decision making on local, regional and eventually national level. The PoliRural Digital Innovation Hub will support sharing of information with other projects and initiatives. The Innovation Hub objectives are:

  • offer access to data cross European NUT3 regions
  • Offering other pna European Data sets like Open Land Use, Smart Point of Interest
  • offer development environment based on Jupyter notebook and list of other tools supporting development of new applications
  • HSlayers NG

Challenge Description: Web solution for attractiveness of regions

1. Development of web tool dealing with rural attractiveness data. The tool will use pre-prepared data. It will enable to filter data (select concrete data sets or group of data sets corresponding with an attribute of rural attractiveness) and to weight data (assign weight/importance to concrete data or groups of data sets).

2. Development of a live database following selected resources. The database will provide data for calculation of rural attractiveness, including providing information about the quality and reliability of data in particular NUTS3 regions
Special prize for best student in EU: coverage of cost related with participation on in situ part of Prague Hackathon including tickets and hotel

3. AI applications for Earth Observation-based crop field risk management

Mentor: Kristina Šermukšnytė-Alešiūnienė

‘AgriFood Lithuania’ (www.agrifood.lt) is a Digital Innovation Hub (DIH) that brings together major research, business and public stakeholders in Lithuania for the common mission of transforming agriculture, food and associated sectors with digital-based innovations.

The mission of AgriFood Lithuania DIH is to contribute towards achieving the vision outlined in the EU Declaration of ‘A smart and sustainable digital future for European agriculture and rural areas’. As the only agriculture and food-focused DIH in Lithuania, the Hub is extensively working with and promoting breakthrough technology applications in AgriFood. Key areas of technological expertise include Artificial Intelligence, Internet of Things, remote sensing, Blockchain and Robotics. The DIH links its stakeholders with international and cross-sector initiatives to provide all-round support in the research, development and deployment of AgriFood Tech innovations, as well as strengthening the national and European technological infrastructure.

The DIH is participating in national and international agriculture and food focused innovation development and support projects, both directly and through its member organizations. AgriFood Lithuania is participating in the EU large-scale project SmartAgriHubs (www.smartagrihubs.eu) and acts as a national coordinating DIH in the organizational structure. The DIH is also co-organizing the international conference for business and policy leaders the ‘AgriBusiness Forum’ (www.digitalfarm.lt), and ‘Hack AgriFood’ (www.hackagrifood.lt) – the first hackathon in Lithuania focused on agriculture and food technology.Challenge Description: Exploratory solutions for AI model applications in various crop monitoring and disease risk management using satellite imagery and spectral data

2. Agroclimatic map of selected region

Mentor: Pavel Hájek

The main components of EUXDAT & Stargate Climatic data processing HUB are the following:

  • EUXDAT Portal: It is the entrance point to EUXDAT functionalities. It provides a web GUI which gives access to the workflow execution tool, monitoring of data analytics execution, the catalogue and other useful tools;
  • Identity and Authorization Manager: This component is responsible of managing user accounts and managing access to the functionalities and data in EUXDAT, according to security policies and to the rights granted to each user;
  • Data & Algorithms Catalogue: It keeps a record of all the algorithms, applications and datasets which are available in EUXDAT;
  • Data & Algorithms Repository: This component deals with the storage of datasets, algorithms and images, in general, that will be used for running data analyses;
  • Data Manager: It is the component in charge of moving data to the proper location. It will configure and operate extraction APIs for accessing several data sources. For doing so, it also has all the data connectors that are necessary;
  • SLA Manager: It agrees on quality attributes to fulfil and the values to be met for each attribute. It also retrieves information about the monitoring of such attributes in order to detect SLA breaches;
  • Orchestrator: It deals with the management of resources, mainly from the functional perspective, deploying the algorithms and the corresponding data in the optimal location. It also deals with the application profiles generation and management;
  • Monitoring: It retrieves information about the resources execution and status, as well as about the algorithms execution and datasets status.

Challenge Description: Agroclimatic map of selected region

This challenge is focused on how the temperature changes through time can provide invaluable information for broad number of professionals in agriculture, environmental scientists or historians.  The example of such a map is an Agroclimatic Atlas Of Canada, particularly e.g. a map of Fall Freeze Dates: Average Dates of First Fall Freeze. 

This challenge is about data processing, data analysis and model-based producing of detailed agroclimatic data of a region based on more coarse data (weather, topography, hydrology, soil type and so on).

1. Mechelen Pilot – TraMod/Spotbooking integration

Mentor. Daniel Beran 

Traffic Modeller (TraMod) is a tool for transport modeling developed in collaboration between traffic engineers, IT and GIS specialist. It can be fully implemented in server environment with an application programming interface for mobile and web applications. This creates an opportunity for a city or a region government representatives to test various traffic scenarios within seconds without a need to install and learn how to use desktop traffic modelling software or contacting traffic engineers every time a new roadwork appears in the region.Challenge Description: Mechelen Pilot – TraMod/Spotbooking integration

Results of San Juan INSPIRE Hackathon 2019

San Juan Hackathon winning ceremony

The #SanJuanINSPIREHackathon is over. All the teams did excellent work! The jury was impressed and it was really hard to evaluate the projects and select the winner.

Finally, the results are:

  • 1st place – Agrohacks
  • 2nd place – Cammalot
  • 3rd place (with the equal score) – Equipo INAUT & P.G.I.C.H
  • 4th place – Remote Sensing UNSJ Argentina

Final presentations of the team’s projects follow.

Agrohacks

Down To Earth ~ a tool alerting farmers about forecasted severe weather conditions

Cammalot

Forecast enhancement with weather station data

Prezi prezentation

Equipo INAUT

Application for reduction of agrochemicals in crops

PGICH

Water and temperatures analysis for wine production

RS UNSJ

Remote sensing data for agriculture