No Access

Toward Autonomous Detection of Anomalous GNSS Data Via Applied Unsupervised Artificial Intelligence

Mike Dye

Ronin Institute, 127 Haddon Pl, Montclair, New Jersey 07043, USA

P.O. Box 56, Nederland, Colorado 80466, USA

E-mail Address: mike.dye@ronininstitute.org

Search for more papers by this author

D. Sarah Stamps

Department of Geosciences, Virginia Tech, 926 W. Campus Drive Blacksburg, Virginia 24061, USA

E-mail Address: dstamps@vt.edu

Search for more papers by this author

Myles Mason

Academy of Integrated Science, Virginia Tech, 800 W. Campus Drive, Blacksburg, Virginia 24061, USA

E-mail Address: mylesm18@vt.edu

Search for more papers by this author

, and

Elifuraha Saria

Department of Geospatial Sciences and Technology, Ardhi University, P.O. Box 35176, Observation Hill, Plot No. 3, Block L, University Road, Dar es Salaam, Tanzania

E-mail Address: saria.elifuraha@gmail.com

Search for more papers by this author

https://doi.org/10.1142/S1793351X22400025Cited by:3 (Source: Crossref)

This article is part of the issue:

Special Issue: Selected Papers from the 3rd IEEE International Conference on Transdisciplinary Artificial Intelligence (TransAI 2021)
Guest Editors: Gary B. Glesener and Julienne A. Greer

Abstract

Artificial intelligence applications within the geosciences are becoming increasingly common, yet there are still many challenges involved in adapting established techniques to geoscience data sets. Applications in the realm of volcanic hazards assessment show great promise for addressing such challenges. Here, we describe a Jupyter Notebook we developed that ingests real-time Global Navigation Satellite System (GNSS) data streams from the EarthCube CHORDS (Cloud-Hosted Real-time Data Services for the geosciences) portal TZVOLCANO, applies unsupervised learning algorithms to perform automated data quality control (“noise reduction”), and explores autonomous detection of unusual volcanic activity using a neural network. The TZVOLCANO CHORDS portal streams real-time GNSS positioning data in 1s intervals from the TZVOLCANO network, which monitors the active volcano Ol Doinyo Lengai in Tanzania, through UNAVCO’s real-time GNSS data services. UNAVCO’s real-time data services provide near-real-time positions processed by the Trimble Pivot system. The positioning data (latitude, longitude and height) are imported into the Jupyter Notebook presented in this paper in user-defined time spans. The positioning data are then collected in sets by the Jupyter Notebook and processed to extract a useful calculated variable in preparation for the machine learning algorithms, of which we choose the vector magnitude for further processing. Unsupervised K-means and Gaussian Mixture machine learning algorithms are then utilized to locate and remove data points (“filter”) that are likely caused by noise and unrelated to volcanic signals. We find that both the K-means and Gaussian Mixture machine learning algorithms perform well at identifying regions of high noise within tested GNSS data sets. The filtered data are then used to train an artificial intelligence neural network that predicts volcanic deformation. Our Jupyter Notebook has promise to be used for detecting potentially hazardous volcanic activity in the form of rapid vertical or horizontal displacement of the Earth’s surface.

Keywords:

Remember to check out the Most Cited Articles!
Check out our titles in Semantic Computing!

References

1. M. Dye, D. S. Stamps and M. Mason, Toward autonomous detection of anomalous GNSS data via applied unsupervised artificial intelligence GitHub repository, 2021, https://github.com/earthcube2021/ec21_dye_etal. Google Scholar
2. J. Bortnik and E. Camporeale , Ten ways to apply machine learning in Earth and space sciences, Eos 102 (2021). Crossref, Google Scholar
3. Y. LeCun and P. Haffner, L. Bottou and Y. Bengio , Object recognition with gradient-based learning, in Shape, Contour and Grouping in Computer Vision (Springer, Berlin, 1999), pp. 319–345. Crossref, Google Scholar
4. K. Cho, B. van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk and Y. Bengio , Learning phrase representations using RNN encoder–decoder for statistical machine translation, in Proc. 2014 Conf. Empirical Methods in Natural Language Processing, 2014, pp. 1724–1734. Crossref, Google Scholar
5. G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever and R. Salakhutdinov, Improving neural networks by preventing co-adaptation of feature detectors, preprint (2012), arXiv:abs/1207.0580. Google Scholar
6. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever and R. Salakhutdinov , Dropout: A simple way to prevent neural networks from overfitting, J. Mach. Learn. Res. 15(1) (2014) 1929–1958. Google Scholar
7. Global Volcanism Program, Ol Doinyo Lengai (222120) in volcanoes of the world, v. 4.10.1 (29 June 2021), ed. E. Venzke, Smithsonian Institution, 2013. Available at https://volcano.si.edu/volcano.cfm?vn=222120 (accessed on 30 July 2021). Google Scholar
8. D. S. Stamps, E. Saria, K. H. Ji, J. R. Jones, D. Ntambila, M. Daniels and D. Mencin, TZVOLCANO: OLO1-OLO1_OLO_TZA2016 P.S., UNAVCO, GPS Dataset, 2016. Google Scholar
9. D. S. Stamps, E. Saria, K. H. Ji, J. R. Jones, D. Ntambila, M. Daniels and D. Mencin, TZVOLCANO: OLO5-OLO5_OLO_TZA2016 P.S., UNAVCO, GPS Dataset, 2016. Google Scholar
10. D. S. Stamps, E. Saria, K. H. Ji, J. R. Jones, D. Ntambila, M. Daniels and D. Mencin, TZVOLCANO: OLO6-OLO6_OLO_TZA2017 P.S., UNAVCO, GPS Dataset, 2017. Google Scholar
11. D. S. Stamps, E. Saria, K. H. Ji, J. R. Jones, D. Ntambila, M. Daniels and D. Mencin, TZVOLCANO: OLO7-OLO7_OLO_TZA2017 P.S., UNAVCO, GPS Dataset, 2017. Google Scholar
12. D. S. Stamps, E. Saria, K. H. Ji, J. R. Jones, D. Ntambila, M. Daniels and D. Mencin, TZVOLCANO: OLO8-OLO8_OLO_TZA2017 P.S., UNAVCO, GPS Dataset, 2017. Google Scholar
13. D. S. Stamps, E. Saria, K. H. Ji, J. R. Jones, D. Ntambila, M. Daniels and D. Mencin, Tanzania Volcano Observatory — OLO9-OLO9_OLO_TZA2021 P.S., UNAVCO, GPS/GNSS Observations Dataset, 2021. Google Scholar
14. A. Adams, Ol Doinyo Lengai, TZ volcano monitoring [data set], International Federation of Digital Seismograph Networks, 2017. Google Scholar
15. M. D. Daniels, B. Kerkez, V. Chandrasekar, S. Graves, D. S. Stamps, C. Martin, M. Dye, R. Gooch, M. Bartos, J. Jones and K. Keiser, Cloud-Hosted Real-time Data Services for the Geosciences (CHORDS) software (Version 0.9), UCAR/NCAR — Earth Observing Laboratory, 2016. Google Scholar
16. B. Kerkez, M. Daniels, S. Graves, V. Chandrasekar, K. Keiser, C. Martin, M. Dye, M. Maskey and F. Vernon , Cloud hosted real-time data services for the geosciences (CHORDS), Geosci. Data J. 3(1) (2016) 4–8. Crossref, Web of Science, Google Scholar
17. D. S. Stamps, E. Saria, K. H. Ji, J. R. Jones, D. Ntambila, M. D. Daniels and D. Mencin, Real-time data from the Tanzania Volcano Observatory at the Ol Doinyo Lengai volcano in Tanzania (TZVOLCANO), UCAR/NCAR — Earth Observing Laboratory, 2016. Google Scholar
18. J. R. Jones and D. S. Stamps, M. D. Daniels and N. Hook, Optimization of TZVOLCANO to stream real-time GNSS data into Cloud Hosted Real-Time Data for the Geosciences (CHORDS), AGU Fall Meeting Abstracts, IN43D-0925, 2018. Google Scholar
19. D. S. Stamps, E. Saria, J. R. Jones, M. D. Daniels and D. Mencin, Tectono-magmatic investigations with societal implications: Progress on the Tanzania Volcano Observatory (TZVOLCANO), AGU Fall Meeting Abstracts, A31K-08, 2016. Google Scholar
20. A. Géron , Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, 2nd edn. (O’Reilly, Boston, 2019). Google Scholar
21. R. Leandro, H. Landau, M. Nitschke, M. Glocker, S. Seeger, X. Chen, A. Deking, M. BenTahar, F. Zhang and K. Ferguson, and others, RTX positioning: The next generation of cm-accurate real-time GNSS positioning, in Proc. 24th Int. Technical Meeting of the Satellite Division of the Institute of Navigation, 2011, pp. 1460–1475. Google Scholar
22. S. D. Peckham, M. Stoica, D. S. Stamps, J. Gallagher, N. Potter and D. Fulker, The BALTO Jupyter Notebook GUI, 2020, https://github.com/earthcube2020/ec20_peckham_etal, https://sites.google.com/vt.edu/balto/home. Google Scholar
23. J. Scheffer , Dealing with missing data, Res. Lett. Inf. Math. Sci. 3 (2002) 153–160. Google Scholar