Integrating Machine Learning for Planetary Science: Perspectives for the Next Decade

Azari, Abigail; Biersteker, John B.; Dewey, R. M.; Doran, Gary; Forsberg, Emily J.; Harris, C. D. K.; Kerner, Hannah; Skinner, Katherine A.; Smith, Andy; Amini, Rashied; Cambioni, Saverio; Poian, Victoria Da; Garton, Tadhg M.; Himes, Michael D.; Millholland, Sarah; Ruhunusiri, S.

doi:10.3847/25c2cfeb.aa328727

Cited by 23 publications

(18 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We refer to the summary on machine learning by Sarker (2021) for further details on the other two types. Within the planetary sciences, the use of machine learning has grown in response to the exponential growth of planetary data from spacecraft missions over the last several decades, as well as Earth-based observatories and laboratories (Azari et al 2021;Kerner et al 2022).…”

Section: Introductionmentioning

confidence: 99%

Mapping Lunar Swirls with Machine Learning: The Application of Unsupervised and Supervised Image Classification Algorithms in Reiner Gamma and Mare Ingenii

et al. 2022

View full text Add to dashboard Cite

Lunar swirls are recognized as broad, bright albedo features in various regions of the Moon. These features are often separated by dark off-swirl lanes or terminate against the dark background, such as lunar maria. Prior mapping of swirls has been done primarily by albedo contrast, which is prone to subjectivity. Closer examination of on-swirl areas shows that they are not uniform, making the boundary between on- and off-swirl difficult to map with certainty. We have applied machine learning techniques to address these issues by identifying the number of swirl units and then mapping them based on actual reflectance, or I/F data. Using LROC NAC paired stereo images that are converted to I/F reflectance at a range of incidence angles, we applied both unsupervised K-means clustering and supervised Maximum Likelihood Classification algorithms to classify and map portions of lunar swirls in Reiner Gamma and Mare Ingenii. Results show that the classification maps are a reasonable match to the representative albedos for the two study regions. A third transitionary swirl unit, termed diffuse-swirl, is present in both the maps and the cumulative distribution plots of the reflectance values. Overall, we find that the use of both algorithms provides independent confirmation of both the number and location of these units and their interrelation. More importantly, the algorithms remove mapping subjectivity by using quantitative information. The data and the statistics generated from the maps also have value in future studies by placing limits for categorizing swirl units in different regions on the Moon.

show abstract

Section: Introductionmentioning

confidence: 99%

Mapping Lunar Swirls with Machine Learning: The Application of Unsupervised and Supervised Image Classification Algorithms in Reiner Gamma and Mare Ingenii

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Furthermore, ML identification methods allow the extrapolation of catalogues and allow for an investigation of more diverse events at different locations, and even make more accurate estimations of the mass budget of magnetospheres. As we rapidly approach a period of data flooding, developing tools to address this issue before it arises is essential for the future of planetary research (Azari et al, 2020).…”

Section: Discussionmentioning

confidence: 99%

Machine Learning Applications to Kronian Magnetospheric Reconnection Classification

Garton¹,

Jackman²,

Smith³

et al. 2024

Preprint

View full text Add to dashboard Cite

<p>Signatures of magnetic reconnection in Saturn's magnetotail are identified in magnetometer observations by characteristic deviations in the northward component of the magnetic field. These magnetic deflections are caused by travelling plasma structures created by reconnection rapidly passing over the observing spacecraft. The identification of these reconnection signatures has long been performed by eye, and more recently through semi-automated methods, however these methods are often limited through a required human verification step. Here, we present a fully automated, supervised learning machine learning (ML) model to identify evidence of reconnection in Cassini MAG (magnetometer) observations of the Kronian magnetosphere, constructed using the Smith et al, 2016. reconnection catalogue which contains hundreds of examples of plasmoids, travelling compression regions and dipolarizations. This ML model is capable of rapidly identifying reconnection events in large time-span Cassini datasets, tested against the full year of 2010 with a high level of accuracy (99\%), true skill score (0.97), and Heidke skill score (0.85). From this ML model, a full cataloguing and examination of magnetic reconnection in the Kronian magnetosphere across Cassini's near Saturn lifetime is now possible.</p>

show abstract

“…Geo-Soft-CoRe intends to be a dynamic collection, open to grow by the addition of new geoscientific software. For that reason, we aim at enlarging this collection by including software addressing other pressing research challenges in Earth science, for instance, planetary science (Azari et al, 2021), paleoclimate and climate science for a sustainable development (Asrar et al, 2012;Ludwig et al, 2019), and/ or environmental quality and its impact on the economy and society (e.g., Ike et al, 2020;Usman, 2022), as well as engage citizens within Earth sciences (Lee et al, 2020). In addition, with this initiative we want to meet the Agenda 2030 for the Sustainable Development Goals by ensuring public access to information (e.g., Bernal, 2021).…”

Section: Open Questions and Further Stepsmentioning

confidence: 99%

Towards a Digital Twin of the Earth System: Geo-Soft-CoRe, a Geoscientific Software & Code Repository

et al. 2022

View full text Add to dashboard Cite

The immense advances in computer power achieved in the last decades have had a significant impact in Earth science, providing valuable research outputs that allow the simulation of complex natural processes and systems, and generating improved forecasts. The development and implementation of innovative geoscientific software is currently evolving towards a sustainable and efficient development by integrating models of different aspects of the Earth system. This will set the foundation for a future digital twin of the Earth. The codification and update of this software require great effort from research groups and therefore, it needs to be preserved for its reuse by future generations of geoscientists. Here, we report on Geo-Soft-CoRe, a Geoscientific Software & Code Repository, hosted at the archive DIGITAL.CSIC. This is an open source, multidisciplinary and multiscale collection of software and code developed to analyze different aspects of the Earth system, encompassing tools to: 1) analyze climate variability; 2) assess hazards, and 3) characterize the structure and dynamics of the solid Earth. Due to the broad range of applications of these software packages, this collection is useful not only for basic research in Earth science, but also for applied research and educational purposes, reducing the gap between the geosciences and the society. By providing each software and code with a permanent identifier (DOI), we ensure its self-sustainability and accomplish the FAIR (Findable, Accessible, Interoperable and Reusable) principles. Therefore, we aim for a more transparent science, transferring knowledge in an easier way to the geoscience community, and encouraging an integrated use of computational infrastructure.Systematic Review Registration: https://digital.csic.es/handle/10261/193580.

show abstract

Integrating Machine Learning for Planetary Science: Perspectives for the Next Decade

Cited by 23 publications

References 1 publication

Mapping Lunar Swirls with Machine Learning: The Application of Unsupervised and Supervised Image Classification Algorithms in Reiner Gamma and Mare Ingenii

Mapping Lunar Swirls with Machine Learning: The Application of Unsupervised and Supervised Image Classification Algorithms in Reiner Gamma and Mare Ingenii

Machine Learning Applications to Kronian Magnetospheric Reconnection Classification

Towards a Digital Twin of the Earth System: Geo-Soft-CoRe, a Geoscientific Software & Code Repository

Contact Info

Product

Resources

About