TEAM 11: To Determine Fertilization Timing

TEAM LEADER: Karl Gutbrod

 

PROJECT IDEA: A common problem of farmer relates to the decision when and where to fertilize the soil in relation to a given crop stage, weather conditions or field topography. With this project idea we want to prepare for a potential user a set of tools helping him to decide about the feasibility and  rentability of going to the field and fertilize given a current weather and soil conditions in given relief and potentially also given a current crop stage.

Decision criteria are:

  • is nitrogen fertilisation useful  in that area (land use map) – not in forest, water
  • is nitrogen fertilisation permitted in that area (optional: map of water catchment areas, seasonal restrictions, protected areas)
  • is the crop at the right stage (Satellite maps: is the crop in a phenological phase that requires fertilizer? + photographs acquired from the smartphone (both optional))
  • is the soil not too wet to apply fertilizer and drive with a tractor (soil type and moisture ).

TEST CASE:

  • multiple corn fields in Austria

DATASETS:

  • Open land use map
  • Crop growth incrementation from Sentinel-2
  • Soil type
  • Climate: rainfall, wind.., as well as historical weather data
  • Soil moisture
  • topography

TEAM 10: Extension and Enrichment of SPOI Knowledge Base

TEAM LEADERS: Raúl Palma (PSNC), Otakar Čerba (UWB)

PROJECT IDEA: The goal of this working group is to improve the SPOI dataset, both by extending and improving the underlying model (ontology), and to enrich the knowledge base with links to other relevant datasets. Regarding the ontology, we aim to include properties definitions, mappings to other vocabularies to the current taxonomy of classes, and possibly additional terms for annotations/ratings. Regarding the dataset, we aim to discuss and find possibility of linking with review/ratings datasets, relevant eurostat indicators, and others that may be identified during the hackathon.

TEAM 9: Metadata and Semantics in the Era of Big Data

TEAM LEADERS: Tomáš Řezník (Masaryk University/Lesprojekt), Raúl Palma (PSNC)

PROJECT IDEA: Our team would like to share with you the latest development of the European Horizon 2020 research and development project called Data-Driven Bioeconomy (DataBio). This DataBio workshop on metadata and semantics in the Era of Big Data may be considered as a starting point for any activity aiming at new way of (geospatial) metadata handling.

More precisely, we would like to focus on the following issues:

  • Tight data and metadata together: ensure updated metadata despite Big data velocity updates.
  • Support metadata heterogeneity: enable discovery of static (e.g. datasets) as well as mobile/other resources (e.g. sensors active during agricultural machinery fleet tracking) in a unified platform.
  • Use efficient encodings: support XML-based format for backwards compatibility, on the contrary use visionary lightweight and semantics-based formats.
  • Integrate metadata in other tools: the best metadata platform is the one where a user does not notice that (s)he works with metadata.

TEAM 8: Delimiting of Agro-Climatic Zones

TEAM LEADER: Karel Jedlička, Carl Gutbrod

PROJECT IDEA: Current climate zones maps are very generic : they show large areas and display some differences in topography. Things like seaside buffer zones, weather divides and South-North differences are not shown. The idea is to provide local agro-climatic maps by processing detailed EO data.

Proposed workflow:

  • Define the Area of Interest (EU/World?)
  • Discuss if it would help to divide the area of interest to current climate zones or to propose different segmentation (e.g. Watersheds?).
  • Design a method of segmentation
  • Design a method of calculation of of average, mean, min and max, slope, aspect and altitude morphometric characteristics to each particular zone defined by vector overlay (Climate zone/Watershed/Open Land Use Zone/whatever)
  • Design a method of calculation of water buffers
  • Do a pilot study on smaller area (such as one country) as a proof of concept

TEAM 7: Lora and SigFox Connectors for SensLog

TEAM LEADER: Mara Musil

PROJECT IDEA:  Our vision is to build Senslog as universal web server, which will be able to integrated observation from different sensors, different platforms, different standards. The SensLog is expect to be in future some type of observation broaked with focus on localised data. From this reason, we would like integrate connectors for currently two most important “industrial” standards. Are you working with Lora or SigFox,  if yes join our team to cooperate on integration of this protocol and testing of connectivity among different platforms.

TEAM 6: Cloud Version of SensLog

TEAM LEADER: Ondřej Kaas

PROJECT IDEA: New version of SensLog was implemented during last months. This new version is more oriented on SensLog deployment in the cloud environment. New SensLog version is based on modern frameworks and with emphasize on real time processing.  The project is focused on testing of deployment of new SensLog and testing of API.

TEAM 5: SQL to NOSQL Migration for Senslog Database

TEAM LEADER: Andrey Sadovykh

PROJECT IDEA:

Sensors are used typically to monitor various physical or virtual world. The information retrieved from the sensors are generally stored in the database to be able to do the post processing and analysis. This database from sensors could grow exponentially. It often requires to have new database machines as the size increases. Cloud computing, virtualization and new database technologies are the key technologies to solve these problems.

Traditionally SQL databases are most widely used and have also proved reliable with time. However, with growing databases and availabilities of new database technologies, there is a possibility to get performance optimization. These technologies are often open source and highly scalable. With the new dynamics in the database technologies comparing existing SQL database to NOSQL database technology is highly recommended. Therefore, with the open sensor database and tools available from Senslog, we would like to do a proof of concept comparing these two technologies.

The first goal of the project is doing a proof of concept of Senslog database migration from SQL (PostgreSQL)  to NOSQL (MongoDB). Typical techniques of transforming SQL model to Mongodb schema: tables to collections, converting relations to table embedding and Reference-IDs. This transformation will be particular to Senslog database logic, however, a general conclusion will be extracted.

The second goal of the project will be performance testing and comparison between these two (PostgreSQL and MongoDB) databases. The idea will be to deploy PostgreSQL (old schema) and MongoDB(with new schema) two instances on same characteristics machine.  We will develop test scripts for performance testing (load testing and stress testing) with performance testing tool (Jmeter).

TEAM 4: REST API from Traffic Modelling

TEAM LEADER: František Kolovský/University of West Bohemia

PROJECT IDEA: The goal of the project is developing REST API for the traffic modeling. The traffic modeling will be provided as a service via API. The backend of the API will be based on Python programing language using Flask framework. The final API should be ensured complete data, account and modelling management for transport modelling for a city area. The API will be used by Javascript frontend application.

The computing of the traffic will be ensured by using Apache Spark with JobServer (REST API for Apache). PostgreSQL with PostGIS extension will be used for data storage. OpenTransportMap is a suitable data source for creating road network for modelling.

TEAM 3: Big Data for Fishery

TEAM LEADER: Karel Jedlička/University of West Bohemia

PROJECT IDEA: The main aim is to provide an easy to use web map application (based on HS Layers NG technology), which will help users (fleet manager, ship manager, …?) in decision making. Can be similar to https://www.windy.com/, but fed with fishery-related data and data from earth observation and meteorological forecast

The application will provide:

    • Several spatial data layers to create a custom map mashups:
      • Data from satellites (the way of visualisation will be defined for each layer) – Spacebel
        • Wind speed
        • Wind direction
        • Sea temperature
        • Chlorophyll
        • Temperature
        • Turbidity
      • Data from weather forecast (there meteo comp. As a partner of DataBio, MeteoBlue API)
        • Wind speed
        • Wind direction
        • ….
      • Other relevant data
        • Different management divisions (e.g. economic zones, large ecosystems and other)
      • Data about position of tuna fish species (both actually tracked and forecasted by a probabilistic model)
        • Including the probability in the case of forecasted data (by color saturation)
      • Data for ship routing
        • Visualise alternative routes with attributes of estimated fuel consumption and risk (by combination of route color and thickness or by detailed report when user click)
  • Challenge: provide a web interface to set up the start and end point of the route, then recalculate the route instantly to consider ship decisions
  • Dynamic visualisation of the data showing (a time slider will control, what is visualized):
    • Real time (=actual day) situation
    • Forecast (for how long?)
    • Historic data (just for fleet manager?) – an advanced visualization by WebGlayer can be prepared that allows not only visualization, but also basic analytics

The nature of the data is dynamics – all the data are changing in a half day period the most but each layer independently.

The map application will visualize data in various scales/levels of detail/granularity, but the initial granularity will be based on approx. 25 x 50 km (0.5 or 0.25 degrees) cells.

TEAM 2: Albatross

TEAM LEADER: Christian Zinke zinke(at)infai.org

TEAM MEMBERS: Stephan Bischoff, Jörg Schließer

PROJECT IDEA: Exploratory Data Visualisation
The idea is to gather and deploy more datasets into Albatross. If possible we will connect SenseLog with Albatross in order to process and analyse the IoT data. Further, we will implement more forecasting models into Albatross.