Data products

    In our research projects at the FHNW Institute of Data Science, we are generating a variety of data products.

    Some of them are freely available. This concerns data archives, data sets for machine learning and tools that support the access to data as well as their investigation and analysis: user interfaces, image processing and machine learning algorithms or data visualization software.

    Open data products are created in the context of publicly funded research in solar physics, for example. Projects in the fields of speech recognition or word processing also generate scientific data products that are freely available to all and can be used for further investigations.

    The only exception concerns products that are subject to data protection regulations or non-disclosure agreements with customers.

    Freely available data products

    The Swiss Parliaments Corpus (SPC) is an automatically aligned Swiss German speech to Standard German text corpus. More specifically, it is a collection of sentence-level audio-text pairs. The current version of the corpus is based on publicly available data of the Bernese cantonal parliament and consists of 293 hours of data.

    To the data set 

    A collection of 1139 medical reports from the US Food and Drug Administration (FDA) Adverse Events Reporting System (FAERS)

    To the text collection  

    A collection of 240000 summaries of Wikipedia texts in German

    To the text collection 

    To the corresponding publication 

    Image files of the Solar Dynamics Observatory SDO space telescope to develop prediction systems for solar flares using machine learning

    To the project and the data set on github 

    To the project and the data set on Kaggle 

    All data and tools related to the operation of the X-ray telescope STIX and the scientific processing of its observations

    To the STIX data center  

    To the STIX project page 

    Functionality to read IRIS level 2 data by the IRIS satellite and to process it for big data applications. The IRISreader works best with a Jupyter notebook.

    To the library

    To the project page @I4DS 

    Observations of the Sun in radio frequencies

    Data: dynamic solar spectra

    Frequency range: 20 - 5000 MHz

    Instruments: radio spectrometer e-Callisto, Phoenix-3, Phoenix-4

    Time range: 2002 - today

    To the data and quick looks @I4DS  

    To the data on ESA's space weather portal  

    To the project page @I4DS   

    To the international project page  

    Observations of solar flares in the X-ray range

    Data: raw data, observing summary

    Energy range: X-ray (~3 keV) to gamma rays (up to ~20 MeV)

    Instrument: X-ray space telescope RHESSI

    Time range: 2002 - 2018

    To the RHESSI data archive 

    To the RHESSI browser   

    To the project page @I4DS   

    To the international project page   

    3D visualization tool for exploring solar data

    Data: solar images of the main solar observatories from three different servers

    Data format: JPEG (compression standard 2000)

    Functions: timeline with image time series, events from the Heliophysics Events Knowledgebase and more

    To the visualization app  

    Interactive timeline for exploring solar activity in time

    Data: GOES X-ray flow, SDO AIA 171, SOHO EIT 171

    Time range: 1981 - today (almost in real time)

    Special feature: The preview images are linked to the NASA visualization application helioviewer.org  which allows to examine interesting solar events in detail

    Web application: no software installation required

    To the visualization app  

    An app for predicting the probability that a solar flare will occur in a given time

    Data: magnetograms (HMI) of the Solar Dynamics Observatory SDO

    Web application: no software installation required

    To the forecast app

    To the forecast app @ESA's Space Weather Portal   

    To the project page @I4DS  

    To the international project site  

    Contact