Tyler O'Neal, Staff Editor

SpaceML makes AI-ready datasets available to researchers working in space science, exploration

The SETI Institute and Frontier Development Lab (FDL.ai) have launched SpaceML.org. SpaceML is a resource that makes AI-ready datasets available to researchers working in space science and exploration, enabling rapid experimentation and reproducibility. As SpaceML continues to grow it will help bridge the gap between data storage, code sharing and server side (cloud) analysis.

The SpaceML Repo is a machine learning toolbox and community-managed resource to enable researchers to more effectively engage in AI for space science and exploration. It is designed to help bridge the gap between data storage, code sharing, and server-side (cloud) analysis.

SpaceML.org includes analysis-ready datasets, space science projects, and MLOPS tools designed to fast-track existing AI workflows to new use-cases. The datasets and projects build on five years of cutting-edge AI application completed by FDL teams of early-career PhDs in AI/ML and multidisciplinary science domains in partnership with NASA, ESA, and FDL's commercial partners. Challenge areas include earth science, lunar exploration, astrobiology, planetary defense, exploration medicine, disaster response, heliophysics, and space weather.

"The most impactful and useful applications of AI and machine learning techniques require datasets that have been properly prepared, organized, and structured for such approaches," said Bill Diamond, CEO of the SETI Institute. "Five years of FDL research across a wide range of science domains has enabled the establishment of a number of analysis-ready datasets that we are delighted to now make available to the broader research community."

FDL applies AI and machine learning (ML) technologies to science to push the frontiers of research and develop new tools to help solve some of humanity's biggest challenges, both here on Earth and in space.

Projects hosted on SpaceML.org for the research community include:

  • A project tackling the problem of how to use ML to auto-calibrate space-based instruments used to observe the Sun. After years of exposure to our star, these instruments degrade over time - a bit like cataracts. Recalibration requires expensive-sounding rockets. Using ML, the team has been able to augment the data, in effect "removing" cataracts."The hurdle for many researchers to start using the SDOML dataset, and to begin developing ML solutions, is the friction they experience when first starting," said Mark Cheung, Sr. Staff Physicist at Lockheed Martin and Principal Investigator for NASA Solar Dynamics Observatory/Atmospheric Imaging Assembly. "SpaceML gives them a jumpstart by reducing the effort needed for exploratory data analysis and model deployment. It also demonstrates reproducibility in action."
  • Another project demonstrates how the data reduction of a meteor surveillance network known as CAMS (Cameras for Allsky Meteor Surveillance) could be automated to identify new meteor shower clusters - potentially the trails of ancient Earth-crossing Comets. Since the AI pipeline has been put into place a total of 9 new meteor showers have been discovered via CAMS."SpaceML helped accelerate impact by bringing in a team of citizen scientists who deployed an interpretable Active Learning and AI-powered meteor classifier to automate insights, allowing the astronomers focused research for the SETI CAMS project," said Siddha Ganju, Self Driving, and Medical Instruments AI Architect, Nvidia (founding member of SpaceML's CAMS and Worldview Search Initiatives). "During SpaceML we (1) standardized the processing pipeline to process the decade long meteor dataset collected by CAMS, and, established the state of the art meteor classifier with a unique augmentation strategy; (2) enabled active learning in the CAMS pipeline to automate insights; and, (3) updated the NASA CAMS Meteor Shower Portal which now includes celestial reference points and a science communication tool. And the best thing is that future citizen scientists can partake in the CAMS project by building on the publicly accessible trained models, scripts, and web tools."
  • SpaceML also hosts INARA (Intelligent ExoplaNET Atmospheric RetrievAI), a pipeline for atmospheric retrieval based on a synthesized dataset of three million planetary spectra, to detect evidence of possible biological activity in exoplanet atmospheres - in other words, 'Are We Alone?'

SpaceML.org seeks to curate a central repository of project notebooks and datasets generated from projects similar to those listed above. These project repositories contain a Google 'Co-Lab' notebook that walks users through the dataset and includes a small data snippet for a quick test drive before committing to the entire data set (which are invariably very large).

The projects also house the complete dataset used for the challenges, which can be made available upon request. Additionally, SpaceML seeks to facilitate the management of new datasets that result from ongoing research and in due course run tournaments to invite improvements on ML models (and data) against known benchmarks.

"We were concerned on how to make our AI research more reproducible," said James Parr, FDL Director and CEO, Trillium Technologies. "We realized that the best way to do this was to make the data easily accessible, but also that we needed to simplify both the on-boarding process, initial experimentation, and workflow adaptation process."

"The problem with AI reproducibility isn't necessarily, 'not invented here' - it's more, 'not enough time to even try. We figured if we could share analysis-ready data, enable rapid server-side experimentation and good version control, it would be the best thing to help make these tools get picked up by the community for the benefit of all."

FDL launches its 2021 program on June 16, 2021, with researchers in the US addressing seven challenges in the areas of Heliophysics, Astronaut Health, Planetary Science, and Earth Science. The program will culminate in mid-August, with teams showcasing their work in a virtual event.

Visit SpaceML.org.

FAU built model reveals origin of ‘motion of the ocean’ in the straits of Florida

Tyler O'Neal, Staff Editor

Eddies are circular currents of water with a whirlpool motion that moves nutrients to the water’s surface.Ocean currents sometimes pinch off sections that create circular currents of water called “eddies.” This “whirlpool” motion moves nutrients to the water’s surface, playing a significant role in the health of the Florida Keys coral reef ecosystem. 

Using a numerical model that simulates ocean currents, researchers from Florida Atlantic University’s Harbor Branch Oceanographic Institute and collaborators from the Alfred-Wegener-Institute in Germany and the Institut Universitaire European De La Mer/Laboratoire d’Océonographie Physique et Spatiale in France are shedding light on this important “motion of the ocean.” They have conducted a first-of-its-kind study identifying the mechanisms behind the formation of sub-mesoscale eddies in the Straits of Florida, which have important environmental implications. 

Despite the swift flow of the Florida Current, which flows in the Straits of Florida and connects the Loop Current in the Gulf of Mexico to the Gulf Stream in the Western Atlantic Ocean, eddies provide a mechanism for retaining marine organisms like fish and coral larvae. Since they trap the nutrient-rich West Florida Shelf waters, they provide habitat to many reefs and pelagic species within the Florida Keys Reef Track region, which sustains the very high productivity of this region.

Moreover, despite the tendency of the West Florida Shelf to overflow into the Straits of Florida, the formation of eddies provides a mechanism that limits the cross-shelf transport of nutrient-laden waters. As a result, the formation of eddies stops the export of the West Florida Shelf waters across the Straits of Florida, preventing events such as red tides from crossing over to Cuba or the Bahamas. Conversely, toxic red tide waters emanating from the shelf remain longer in the vicinity of the Florida Keys Reef Tract coral reef ecosystem, adversely affecting the ecosystem’s health.

These small-scale frontal eddies are frequently observed and present a wide variety of numbers, shapes, and sizes, which suggest different origins and formation mechanisms. Their journey through the Straits of Florida is at a time characterized by the formation and presence of mesoscale, but mostly sub-mesoscale frontal eddies on the cyclonic side of the current. Animation shows the formation of eddies in the Straits of Florida.

The study, published in the Journal of Physical Oceanography, provides a comprehensive overview and understanding of the Straits of Florida shelf-slope dynamics based on a realistic two-way nested high-resolution Regional Oceanic Modeling System (ROMS) simulation of the South Florida oceanic region. The full two-way nesting allowed the interaction of multiscale dynamics across the nest boundaries.

Results showed that the formation of the sub-mesoscale frontal eddies in the Straits of Florida is associated with the Florida Current sloshing, which consists of the oscillation of the distance of the current core from the shelf. When the Florida Current core is pushed up against the shelf, the shear on the shelf increases, and sub-mesoscale frontal eddies can be formed by barotropic instability. When this position is relaxed, baroclinic instability instead is likely to form sub-mesoscale eddies. Unlike barotropic instability, which is shear-driven, baroclinic instability is driven by changes in density anomalies.

“In the Straits of Florida, eddies smaller than their open ocean relative are formed. Those eddies, called sub-mesoscale eddies, are common and can be easily observed in ocean color imagery,” said Laurent Chérubin, Ph.D., senior author and an associate research professor, FAU Harbor Branch. “Unlike the larger open ocean mesoscale eddies, they are not in geostrophic balance, meaning that their circulation is not sustained by the balance between the pressure gradient and the Coriolis forces. Instead, some of the frontal eddies in the Straits of Florida are in gradient wind balance, which indicates that a third force, the centrifugal force, is large enough to modify the geostrophic balance.” 

The Florida Current is part of the western branch of the wind-driven North Atlantic anti-cyclonic gyre, which is intensified on the western side of the North Atlantic basin in comparison to its eastern side. Similar types of currents also are found on the western side of ocean basins such as the Agulhas Current in the southern Indian Ocean or the Kuroshio in the northern Pacific Ocean. They are called boundary currents because they impinge on the continental shelf and as such, they undergo a significant amount of friction on the ocean floor. This friction, which acts vertically and horizontally on the boundary current, contributes to the formation of a sheared boundary layer.

“Our study shows that this shear layer can become unstable and form eddies. This process is in fact a pathway for the dissipation of wind energy injected into the ocean. Therefore, in the Straits of Florida, eddies smaller than their open ocean relative are formed,” said Chérubin.

In addition to sub-mesoscale eddies formed locally in the Straits of Florida, there are incoming mesoscale eddies that transit in the Straits of Florida, such as the Tortugas Gyre.

“Findings from our research also show that mesoscale eddies can be squeezed on the shelf and transformed into sub-mesoscale eddies when the Florida Current is in its protracted position or remains relatively unaffected if the Florida Current is retracted from the shelf,” said Chérubin.

Astra hires IBM Watson, Apple veteran Stratos Davlos to lead software

Tyler O'Neal, Staff Editor

Davlos brings two decades of leadership in AI and machine learning to Astra

Astra announced today that Stratos Davlos joined the company as Senior Vice President of Software. Davlos has an extensive background in artificial intelligence and machine learning with senior leadership roles at IBM Watson and Apple.

“I am incredibly proud to lead the team responsible for the software that will power Astra’s mission to improve life on Earth from space,” said Stratos. “From rocket manufacturing to mission control, the software is at the very heart of what will allow Astra to operate at unprecedented velocity and scale.”

Davlos will spearhead the development of the intelligent operating system that underpins the company’s space platform and connects customers to Astra’s services. One of Davlos’ priorities is to build out the software team with a diverse range of engineers.

“Stratos is a proven leader with the creativity to redefine how our data creates a competitive advantage for Astra,” said Benjamin Lyon, Chief Engineer at Astra. “Software is foundational to our entire enterprise and bringing Stratos onboard reflects how serious we are about this strategy.”

Stratos is the latest addition to Astra’s all-star leadership team that now includes top leaders from Apple, Amazon, Google, and Tesla.