2020 ESIP Winter Meeting

The Analytic Center Framework (ACF) is a concept to support scientific investigations with a harmonized collection of data from a wide range of sources and vantage points, tools and computational resources. Four recent NASA AIST competitive awards are focused on either ACFs or components which could feed into AQ ACF's. Previous projects have developed tools and improved the accessibility and usability of data for Air Quality analysis, and have tried to address issues related to inconsistent metadata, uncertainty quantification, interoperability among tools and computing resources and visualization to aid scientific investigation or applications. The format for this meeting will be a series of brief presentati.ons by invited speakers followed by a discussion. This generally follows the panel model How to Prepare for this Session: A link to a set of pre-read materials will be provided.

View Recording: https://youtu.be/fy4eoOfSbpo.

Takeaways

• Is there enough interest to start an Air Quality cluster? Yes!
• Technologists and scientists should both be involved in the cluster to ensure usability through stakeholder engagement
  
  

"Brains! Brains! Give us your brains!""
- Friendly neighbourhood machine minds
The collective knowledge in the ESIP community is immense and invaluable. During this session, we'd like to make sure that this knowledge drives the semantic technology (ontologies) being developed to move data with machine-readable knowledge in Earth and planetary science.
What we'll do:

In the first half hour of this session, we'll a) sketch out how and why we build ontologies and b) show you how to request that your knowledge gets added to ontologies (with nanocrediting).
We'll then have a 30-minute crowdsourcing jam session, during which participants can share their geoscience knowledge on the SWEET issue tracker. With a simple post, you can shape how the semantic layer will behave, making sure it does your field justice! Request content and share knowledge here: https://github.com/ESIPFed/sweet/issues
In the last, 30 minutes we'll take one request and demonstrate how we go about ""ontologising"" it in ENVO and how we link that to SWEET to create interoperable ontologies across the Earth and life sciences.

Come join us and help us shape the future of Geo-semantics!

Stuff you'll need:
A GitHub account available at https://github.com/
An ORCID (for nanocrediting your contributions) available at https://orcid.org How to Prepare for this Session:

Presentations:

View Recording: https://youtu.be/tr0coi5ZQvM

Takeaways

• Working toward a future (5-10 year goal) of making an open Earth & Space Science Foundry (from SWEET) similar to the OBO (Open Biological and Biomedical Ontology) Foundry. “Humans write queries”. Class definitions need to be machine-readable for interoperability, but must remain human-readable for authoring queries, ontology reuse, etc.
• Please feel free to add phenomena of interest to the SWEET https://github.com/ESIPFed/sweet/issues/ or ENVO https://github.com/EnvironmentOntology/envo/issues/ issue trackers. 
• At AGU they added a convention for changes to ontologies. Class level annotation convention. Can get now get textual defs from DBpedia for SWEET terms. See https://github.com/ESIPFed/sweet/wiki/SWEET-Class-Annotation-Convention
  
  

Political, economic, social or scientific decision making is often based on integrated data from multiple sources across potentially many disciplines. To be useful, data need to be easy to discover and integrate.
This session will feature presentations highlighting recent breakthroughs and lessons learned from experimentation and implementation of open knowledge graph, linked data concepts and Discrete Global Grid Systems. Practicality and adoptability will be the emphasis - focusing on incremental opportunities that enable transformational capabilities using existing technologies. Best practices from the W3C Spatial Data on the Web Working Group, OGC Environmental Linked Features Interoperability Experiment, ESIP Science on Schema.org; implementation examples from Geoscience Australia, Ocean Leadership Consortium, USGS and other organisations will featured across the entire session.
This session will highlight how existing technologies and best practices can be combined to address important and common use cases that have been difficult if not impossible until recent developments. A follow up session will be used to seed future collaborative development through co-development, github issue creation, and open documentation generation.

How to Prepare for this Session: Review: https://opengeospatial.github.io/ELFIE/, https://github.com/ESIPFed/science-on-schema.org, https://www.w3.org/TR/sdw-bp/, and http://locationindex.org/.

Notes, links, and attendee contact info here.

View Recording: https://youtu.be/-raMt2Y1CdM

Session Agenda:
1.  2.00- 2.10,  Sylvain Grellet, Abdelfettah Feliachi, BRGM, France
'Linked data' the glue within interoperable information systems
“Our Environmental Information Systems are exposing environmental features, their monitoring systems and the observation they generate in an interoperable way (technical and semantic) for years. In Europe, there is even a legal obligation to such practices via the INSPIRE directive. However, the practice inducing data providers to set up services in a "Discovery > View > Download data" pattern hides data behind the services. This hinders data discovery and reuse. Linked Data on the Web Best Practices put this stack upside down and data is now back in the first line. This completely revamp the design and capacities of our Information Systems. We'll highlight the new data frontiers opened by such practices taking examples on the French National Groundwater Information Network”
View Slides: https://doi.org/10.6084/m9.figshare.11550570.v1

2.  2.10 - 2.20,  Adam Leadbetter, Rob Thomas, Marine Institute, Ireland
Using RDF Data Cubes for data visualization: an Irish pilot study for publishing environmental data to the semantic web
The Irish Wave and Weather Buoy Networks return metocean data at 5-60 minute intervals from 9 locations in the seas around Ireland. Outside of the Earth Sciences an example use case for these data is in supporting Blue Economy development and growth (e.g. renewable energy device development). The Marine Institute, as the operator of the buoy platforms, in partnership with the EU H2020 funded Open Government Intelligence project has published daily summary data from these buoys using the RDF DataCube model[1]. These daily statistics are available as Linked Data via a SPARQL endpoint making these data semantically interoperable and machine readable. This API underpins a pilot dashboard for data exploration and visualization. The dashboard presents the user with the ability to explore the data and derive plots for the historic summary data, while interactively subsetting from the full resolution data behind the statistics. Publishing environmental data with these technologies makes accessing environmental data available to developers outside those with Earth Science involvement and effectively lowers the entry bar for usage to those familiar with Linked Data technologies.
View Slides: https://doi.org/10.6084/m9.figshare.11550570.v1

3. 2.20 - 2.30,  Boyan Brodaric, Eric Boisvert, Geological Survey of Canada, Canada; David Blodgett, USGS, USA
Toward a Linked Water Data Infrastructure for North America
We will describe progress on a pilot project using Linked Data approaches to connect a wide variety of water-related information within Canada and the US, as well as across the shared border
View Slides: https://doi.org/10.6084/m9.figshare.11541984.v1

4.  2.30 - 2.40,  Dalia Varanka, E. Lynn Usery, USGS, USA
The Map as Knowledge Base; Integrating Linked Open Topographic Data from The National Map of the U.S. Geological Survey
This presentation describes the objectives, models, and approaches for a prototype system for cross-thematic topographic data integration based on semantic technology. The system framework offers a new perspectives on conceptual, logical, and physical system integration in contrast to widely used geographic information systems (GIS).
View Slides: https://doi.org/10.6084/m9.figshare.11541615.v1

5.  2.40 – 2.50,  Alistair Ritchie, Landcare, New Zealand
ELFIE at Landcare Research, New Zealand
Landcare Research, a New Zealand Government research institute, creates, manages and publishes a large set of observational and modelling data describing New Zealand’s land, soil, terrestrial biodiversity and invasive species. We are planning to use the findings of the ELFIE initiatives to guide the preparation of a default view of the data to help discovery (by Google), use (by web developers) and integration (into the large environmental data commons managed by other agencies). This integration will not only link data about the environment together, but will also expose more advanced data services. Initial work is focused on soil observation data, and the related scientific vocabularies, but we anticipate near universal application across our data holdings.
View Slides: https://doi.org/10.6084/m9.figshare.11550369.v1

6.  2.50 - 3.00,  Irina Bastrakova, Geoscience Australia, Australia
Location Index Project (Loc-I) – integration of data on people, business & the environment
Location Index (Loc-I) is a framework that provides a consistent way to seamlessly integrate data on people, business, and the environment.
Location Index aims to extend the characteristics of the foundation spatial data of taking geospatial data (multiple geographies) which is essential to support public safety and wellbeing, or critical for a national or government decision making that contributes significantly to economic, social and environmental sustainability and linking it with observational data. Through providing the infrastructure to suppo

This working session will follow on the "Advancing Data Integration approaches of the structured data web” session and the Coverage Analytics sprint as an opportunity for those interested in building linked data information products that integrate spatial features, coverage data, and more. As such, inspiration will be drawn from projects like science on schema.org, the Environmental Linked Features Interoperability Experiment, the Australian Location Index, and those that session attendees take part in. Participants will self organize into use-case or technology focused groups to discuss and synthesize the outcomes of the sprint and structured data web session. Session outcomes could take a number of forms: linked data and web page mock ups, ideas and issues for OGC, W3C, or ESIP groups to consider, example data or use cases for relevant software development projects to consider, or work plans and proposals for suture ESIP work. The session format is expected to be fluid with an ideation and group formation exercise followed by structured discussion to explore a set of ideas then narrow on a focused valuable outcome. Participants will be encouraged to work together prior to the meeting to design and plan the session structure. Outcomes of the session will be reported at an Information Technology and Interoperability webinar in early 2020. How to Prepare for this Session: Attend the coverage sprint and the "Advancing Data Integration approaches of the structured data web" session.

Shared document for session here.

Full Notes: https://doi.org/10.6084/m9.figshare.11559087.v1

Presentations:

View Recording: https://youtu.be/u2x3I0cr46A

• Takeaways
  Breakout session information interoperability committee and webinar series. See notes: https://docs.google.com/document/d/1LpcTMwP0mAD4G4Gb8mStI5uSDV61_qWPUkQ9nI1x1cI/edit?usp=sharing
• Foster cross-project consistency via breakouts. Such as dealing with science on schema.org issue of Links to “in-band” linked (meta)data and “out of band” linked data. Content negotiation and in-band and out of band links Use blank nodes with link properties for rdf elements that are URI for out of band content. Identify in band links with sdo @id, out of band links with sdo:URL
• Incorporating Spatial Coverages in Knowledge Graphs; Next Steps? Need to explore more on tessellations as an intermediate index. Will carry forward some of these ideas at the EDR SWG Will represent some of these ideas to the OGC-API Coverages SWG Will mention these ideas to the UFOKN Role of ‘spatial’ knowledge graphs Will spatial data analysis and transformation tools grow to adopt/support RDF as an underlying data structure for spatial information or will RDF continue to be a ‘view’ of existing (legacy) spatial data in GI systems?
• 
  

The ESIP community and others in machine learning regularly lament the lack of labeled datasets, needed for certain classes of training algorithms. Generating accurate, useful labels is a hard problem, with no general automated solution in sight. Thus, labeling generally involves human effort, which is challenging because the volume of data needed for training can be very large.

Tools exist to help in labeling data. This session will demonstrate three labeling tools and associated processes:

• Image Labeler, a fast, scalable cloud-based tool to facilitate the rapid development of Earth science event databases, to aid in automated ML-based image classification, Rahul Ramachandran
• Labelimg, an open source graphical image annotation tool, https://github.com/tzutalin/labelImg, Ziheng Sun
• Bokeh, a Python based plotting and annotation tool set for building arbitrary labeling workflows, https://bokeh.org/, Jim Bednar

Time permitting, the session will conclude with a short discussion of thoughts and tradeoffs about the tools.

This session is followed by a hands-on workshop for using Labelimg and Bokeh. Please see the session abstract for "Hands on Labeling Workshop" for information on preparing for that workshop if you are interested in participating.

Presentations
https://doi.org/10.6084/m9.figshare.11629110.v1
https://doi.org/10.6084/m9.figshare.11591739.v1

View Recording: https://youtu.be/3ufBOoD3M1E

Takeaways

• Machine learning based classification applications require high-quality labelled data sets for both model training and evaluation. There are many existing tools for labeling images (including earth science data), but labeling tasks are very labor and time intensive.
• If the pre-built labeling tools don’t work for your problem, Anaconda provides a general-purpose labeler-building toolkit based on Bokeh for Python users; see https://examples.pyviz.org/ml_annotators/ml_annotators.html
• There is opportunity in combining partly automated, partly human labeling, to automate the easy cases while leaving the final call to a person. Currently not much tool support or good practices, hard to integrate.The art of avoiding extra work!

Intended as a follow on to the "Do You Have a Labeling Problem?" session and to get your feet wet, this working session is for people to experiment with two of the tools presented in that session, Labelimg and Bokeh. Presenters will provide some sample data for participants to work with. Attendees can also bring some of their own data to work with in the time remaining after the planned activities.

It would be best for workshop participants to preinstall Labelimg before coming to the session.   Regarding Bokeh, Anaconda is providing 25 accounts for workshop participants. (Thank you, Jim and Anaconda!).  Installing Bokeh is also an option.  Links for getting these tools are:

• Labelimg via https://github.com/tzutalin/labelImg#installation
• Bokeh as part of the HoloViz suite via http://holoviz.org/installation.html

Presentations

View Recording: https://youtu.be/y8NqTLgT8Ao

Takeaways