CRESCYNT Toolbox – Workflows as Collaboration Space and Workbench Blueprint

puzzle-juggling_pixabayScientists need better ways to analyze and integrate their data and collaborate with other scientists; new computing technologies and tools can help with this. However, it’s difficult to overcome the challenge of disparate perspectives and the absence of a common vocabulary: this is true of multidisciplinary science teams, and true when scientists try to talk with computer scientists. Workflows, as a way to help design and implement a workbench, are needed both as a collaboration space and a blueprint for implementation.

Take a look at a recent presentation to the EarthCube science committee (video) or an earlier presentation offered at ASLO 2017 (slides and voice) to see a flexible and low-tech way to simultaneously (1) facilitate necessary sci-tech interactions for your own lab and (2) begin to sketch out a blueprint for work that needs to be done. Subsequent technical implementation is possible with new tools including Common Workflow Language (CWL) as a set of specifications, Dockers as modular and sharable containers for either fully developed tools or small pieces of code, and Nextflow as an efficient and highly scalable definitive software language to make the computational work happen. Look for a post in the near future by Mahdi Belcaid to describe the technical implementation of these workflows.

OPPORTUNITY! We will be hosting one or two in-person skills training workshops in the coming months, with your expenses covered by our NSF EarthCube CRESCYNT grant, focused particularly on training early career professionals, and will work through some challenging coral reef use cases and their cyberinfrastructure needs. We collected some great use cases at ICRS, but would like additional cases to consider, so we invite you to describe your own research challenges through this google form. Please contact us for more on this, or other issues. Thanks!

CRESCYNT Toolbox – Workflows as Collaboration Space and Workbench Blueprint

CRESCYNT Toolbox – EarthCube Sci-Tech Matchup – Lightning Talks

Get a fast intro to new Ready-for-Science EarthCube Tools!

We’ve helped arrange a series of lightning talks that will feature tools developed by EarthCube “building block” projects for direct use by scientists. Many EarthCube-built tools are designed to serve as internal components of an EarthCube platform. Other tools were built for scientists as direct end users, and a collection of these are now ripe for adoption. Will some of these help you with your research work?
The current collection will be shown over a span of two online sessions. Find log-in details for Wed., Feb. 15 and Fri., Feb. 17 (no RSVP required – just show up).
Join us!

Wednesday, Feb. 15, 2017
4-5pm EST / 1-2pm PST / 11am-12pm HST – login link HERE
GeoDataspace/GeoTrust, Tanu Malik
ECOGEO Virtual Machine, Elisha Wood-Charlson
LinkedEarth, Julien Emile-Geay
OntoSoft, Yolanda Gil
Flyover Country, Amy Myrbo

Friday, Feb. 17, 2017
4-5:30pm EST / 1-2:30pm PST / 11am-12:30pm HST – login link HERE
CHORDS, Mike Daniels
SuAVE, Ilya Zaslavsky
CINERGI, Ilya Zaslavsky
X-DOMES Ontology Registry, Janet Fredericks
X-DOMES SensorML Registry, Janet Fredericks
iSamplesIGSN, Kerstin Lehnert
GeoDeepDive, Shanan Peters
Digital Crust, Shanan Peters
ECITE, Sara Graves
Earth System Bridge, Scott Peckham

UPDATE: All of the videos from the first rounds of talks are now on the EarthCube YouTube channel – here’s the playlist. Slides are now accessible at the EarthCube Tools Inventory, including additional presentations.

CRESCYNT Toolbox – EarthCube Sci-Tech Matchup – Lightning Talks

CRESCYNT Toolbox – Data Repositories – Estate Planning for your Data

“Hypotheses come and go but data remain.”    – Ramon y Cajal

Taking care of our data for the long term is not just good practice, allowing us to share our data, defend our work, reassess conclusions, collaborate with colleagues, and examine broader scales of space and time – it’s also estate planning for our data, and a primary way of communicating with future scientists and managers.

egg-gold

Here are some great options for long-term data storage, highlighting repositories friendly to coral reef science.

First, there are some important repository networks useful for coral reef data – these can unify standards and offer collective search portals: we like DataONE (members here) and bioCaddie (members here).

KNB – the Knowledge Network for Biocomplexity offers open and private data uploads; ecological orientation. DataONE network.

NOAA CoRIS: Coral Reef Information System – often free to use and can accept coral reef related data beyond NOAA’s own data; contact them first.

BCO-DMO – Biological and Chemical Oceanography Data Management Office – if you have an NSF grant that requires data storage here, you’re fortunate. Good data management guidelines and metadata templates, excellent support staff. Now a DataONE member.

Dataverse – supported by Harvard endowments. There are multiple organizational dataverses – the Harvard Dataverse is free to use. bioCaddie member.

Zenodo – free to use, supported by the European Commission (this is a small slice of CERN’s enormous repository for the Large Hadron Collider). Assigns dois. We invite you to include the “Coral Reef” community when you upload. bioCaddie member.

NCBI – the National Center for Biotechnology Information is very broadly accepted for ‘omics data of all types. A bioCaddie member.

DataCite – not a repository, but if you upload a dataset at a repository that does not assign its own doi’s, you can get one at DataCite and include it when publishing your datasets.

We’ve not listed more costly repositories such as Dryad (focused on journal requirements) or repositories restricted to institutions. What about other storage options such as GitHub, Amazon Web Services, websites? Those have important uses, but are not curated repositories with long-term funding streams, so are not the best data legacy options.

eggs-stacked-imagesMost of these repositories allow either private (closed) or public (open) access, or later conversion to open access. Some have API’s for automated access within workflows. These are repositories we really like for storing and accessing coral reef work. Share your favorite long-term data repository – or experiences with any of the repositories listed here – in the comments.

CRESCYNT Toolbox – Data Repositories – Estate Planning for your Data

CoralNet: deploying deep learning in the shallow seas – by Oscar Beijbom

coralnet_oscar-beijbom

Having dedicated my PhD to automating the annotation of coral reef survey images, I have seen my fair share of surveys and talked to my fair share of coral ecologists. In these conversations, I always heard the same story: collecting survey images is quick, fun and exciting. Annotating them is, on the other hand, slow, boring, and excruciating.

When I started CoralNet (coralnet.ucsd.edu) back in 2012 the main goal was to make the manual annotation work less tedious by deploying automated annotators alongside human experts. These automated annotators were trained on previously annotated data using what was then the state-of-the-art in computer vision and machine learning. Experiments indicated that around 50% of the annotation work could be done automatically without sacrificing the quality of the ecological indicators (Beijbom et al. PLoS ONE 2015).

The Alpha version of CoralNet was thus created and started gaining popularity across the community. I think this was partly due to the promise of reduced annotation burden, but also because it offered a convenient online system for keeping track of and managing the annotation work. By the time we started working on the Beta release this summer, the Alpha site had over 300,000 images with over 5 million point annotations – all provided by the global coral community.

There was, however, a second purpose of creating CoralNet Alpha. Even back in 2012 the machine learning methods of the day were data-hungry. Basically, the more data you have, the better the algorithms will perform. Therefore, the second purpose of creating CoralNet was quite simply to let the data come to me rather than me chasing people down to get my hands on their data.

At the same time the CoralNet Alpha site was starting to buckle under increased usage. Long queues started to build up in the computer vision backend as power-users such as NOAA CREP and Catlin Seaview Survey uploaded tens of thousands of images to the site for analysis assistance. Time was ripe for an update.

As it turned out the timing was fortunate. A revolution has happened in the last few years, with the development of so-called deep convolutional neural networks. These immensely powerful, and large nets are capable of learning from vast databases to achieve vastly superior performance compared to methods from the previous generation.

During my postdoc at UC Berkeley last year, I researched ways to adapt this new technology to the coral reef image annotation task in the development of CoralNet Beta. Leaning on the vast database accumulated in CoralNet Alpha, I tuned a net with 14 hidden layers  and 150 million parameters to recognize over 1,000 types of coral substrates. The results, which are in preparation for publication, indicate that the annotation work can be automated to between 80% and 100% depending on the survey. Remarkably: in some situations, the classifier is more consistent with the human annotators than those annotators are with themselves. Indeed, we show that the combination of confident machine predictions with human annotations beat both the human and the machine alone!

Using funding from NOAA CREP and CRCP, I worked together with UCSD alumnus Stephen Chan to develop CoralNet Beta: a major update which includes migration of all hardware to Amazon Web Services, and a brand new, highly parallelizable, computer vision backend. Using the new computer vision backend the 350,000 images on the site were re-annotated in one week! Software updates include improved search, import, export and visualization tools.

With the new release in place we are happy to welcome new users to the site; the more data the merrier!

_____________

– Many thanks to Oscar Beijbom for this guest posting as well as significant technological contributions to the analysis and understanding of coral reefs. You can find Dr. Beijbom on GitHub, or see more of his projects and publications here. You can also find a series of video tutorials on using CoralNet (featuring the original Alpha interface) on CoralNet’s vimeo channel, and technical details about the new Beta version in the release notes.

 

>>>Go to NSF EarthCube or the CRESCYNT website or the blog Masterpost.<<<

CoralNet: deploying deep learning in the shallow seas – by Oscar Beijbom

CRESCYNT Toolbox – Disaster Planning and Recovery

With computers, the question is not whether they will fail, but when.

tl;dr – It’s very practical to have cloud storage backup in addition to still-useful external hard drive backup routines. Here are some secure cloud alternatives.

itcrowd_giphyPersonal note. I’ve had hard drive failures due to lightning strike; simultaneous death of mirrored hard drives within a RAID; drenching from an upper floor emergency shower left flowing by a disgruntled chemistry student; and most recently, demise of my laptop by sudden immersion in salt water (don’t ask). By some intersection of luck and diligence, on each occasion recent backups were available for data recovery. In the most recent remake, it was a revelation how much work is now backed up via regular entry into the casual cloud.

This latest digital landing was mercifully soft (…cloudlike). Because of work portability, my recent sequential backup habit has been to a paid unshared Dropbox account; $10/mo is a bargain for peace of mind (beyond a certain size, restoration is not drag-and-drop). A surprising number of files these days are embedded in multiple team projects – much on Google Drive – so all of that was available, with revision history. Group conversations and files were on Slack and email. One auxiliary brain (iPhone)  was in a waterproof case with cloud backup, and another auxiliary brain (project/task tracking) was in a web app, KanbanFlow. Past years of long-term archives were already on external hard drives in two different cities. GitHub is an amazing place to develop, document, recover and share work in progress and products, but it is not a long-term curated data repository. For valuable datasets, the rule is to simplify formats, attach metadata, and update media periodically.

Thinking about your own locations for data storage and access? Check out this review of more secure alternatives to – and apps on top of – Dropbox. Some, like OwnCloud, can serve as both storage and linked access for platforms like Agave. A strength of some current analytical platforms is that they can access multiple data storage locations; for example, Open Science Framework can access Dropbox, Google Drive, GitHub, Box, figshare, and now Dataverse and Amazon Web Services as well.

A collaborator recently pointed out that the expense of any particular type of data storage is really the expense of its backup processes: frequency, automation, security, and combination of archiving media. Justifying the expense can come down to this question: What would it cost to replace these data? Some things are more priceless than others.

Disaster Planning and Recovery tools.  To go beyond data recovery in your planning, here’s an online guide for IT disaster recovery planning and cyberattacks. How much of a problem is this really? See Google’s real-time attack map (hit “play”). Better to plan than fear. You did update those default passwords on your devices, yes?

Feel free to share your own digital-disaster-recovery story in the comments.

CRESCYNT Toolbox – Disaster Planning and Recovery

CRESCYNT Toolbox – EarthCube Tool for Visual Exploration of Images and Survey Data

suaveSuAVE is a new online tool for sharing and visually exploring surveys and image collections. It originated in the CINERGI Building Block project and has been used to analyze the EarthCube Member Survey, and then create CINERGI Community Resource Viewers. SuAVE is Survey Analysis via Visual Exploration, and was created by Ilya Zaslavsky and his team at the San Diego Supercomputer Center.

With SuAVE you can publish your data online (mixed numeric and text data, and images), slice and dice the data based on any combination of attributes, visualize general patterns and drill down to outliers, explore various data views, annotate your findings, and share annotations with collaborators. See examples of SuAVE in the geosciences and other fields including sociology, biology and ecology, archaeology, art history and humanities, urban planning, and medical informatics.

To see SuAVE in action and learn how you can create a viewer for your own data, join the session of “Doing Geoscience with EarthCube Tools” on Friday, Nov. 18th, 2016, at 2pm EDT (11am PDT). If you miss it, check back later for a link to a recording of the webinar.

PREVIEW: check out a new resource search widget from EarthCube’s CINERGI project. Find a working copy at the bottom of the crescynt.org page (wordpress does not play nicely with widgets, sadly), or test and download the widget for yourself here.


Coral research resources are being steadily added to the database for this search.

CRESCYNT Toolbox – EarthCube Tool for Visual Exploration of Images and Survey Data