top of page
dune_1102_det.jpg

MRO CTX

1.jpg

About

I seek to understand how planetary surfaces form and evolve, and how they interact with ice, wind, and the harsh environment of space. To accomplish this goal, I harness the vast amount of remote sensing data gathered by NASA spacecraft and analyze them using statistics, machine and deep learning. As a member of the LRO Diviner team, I work on a variety of problems related to the way surface roughness affects the temperature and the stability of ice on the Moon.

Currently, I am a postdoctoral scholar at the Department of Geological Sciences at Stanford University, working with Mathieu Lapotre on applying Artificial Intelligence to map and investigate topographic features on the surface of Mars. Before that, I completed my PhD at UCLA, working with David Paige on problems related to radiometry and geomorphology on the Moon and Mercury, and my Master's degree at the Weizmann Institute of Science, where I worked with Oded Aharonson on modeling temperatures and ice stability on airless planetary surfaces. My undergraduate research projects focussed on characterizing Transient Luminous Events (TLEs) with Yoav Yair (the Open University) and Colin Price (Tel-Aviv University).


Apart from research, I am also very much involved in science outreach. I write for, and until recently was the scientific editor-in-chief of, "Mada Gadol Bektana" (lit.; "Science in a Nutshell"), the largest science outreach non-profit organization in Israel, which operates a popular Facebook page and website. From time to time I also publish articles on planetary science or astronomy in Israeli news sites (e.g. potential discovery of a planetary mass object in the Kuipter Belt, based on this paper).

Anchor 1

Current Research

Unsupervized Deep Learning Analysis of Spacecraft Data

The vast volumes of information obtained by NASA spacecraft over the past decades requires reevaluating traditional, manual, methods for geospatial analysis of surface features. In this work, we use convolutional autoencoders to extract information from visible, thermal, and multi-spectral satellite and spacecraft data. This non-linear dimensionality reduction technique allows quantifying physical and geophysical phenomena in a reproducible manner for studying complex and long-term environmental and geologic processes. The example shown here uses an autoencoder to automatically classify the freshness of impact craters on the Moon:
















Please see this DPS abstract for more information

figure_5.png

Deep learning analysis of imagery data

Employing an instance segmentation neural network to detect and mask dunes on Mars

In this project, I am leading an effort to automatically detect and outline ​barchan dunes on Mars to extract local and global wind directions. I use Mask-RCNN, an instance segmentation neural network, to find dunes in images obtained by the Mars Reconnaissance Orbiter Context Camera (CTX). The network outputs the dunes' outlines, which are automatically analyzed using a slipface detection algorithm we developed which is based on opencv's convexity defects algorithm.

Please see my paper to read more about detection of barchan dunes using deep learning

dunes.png

Detected dunes and derived wind directions (red arrows)

Can we efficiently train a neural network to detect impact craters with only a few dozens of training samples?

The study of planetary surface processes greatly benefited from the wealth of spacecraft data collected in the past decades. However, the unprecedented rate at which new data is collected is far greater than the rate it is analyzed. The exciting advancements made over the recent years in the field of artificial intelligence (AI) gave birth to mature, robust tools that have revolutionized remote sensing, becoming the new industry standard in many fields.

​

One major problem of classification of imagery data is that it requires an expert human analyst, whose role is to label and classify topographic features. Even binary classification using a fully convolutional neural network will typically have trouble converging until a few hundreds of images have been labeled. In this project, I explore how generative adversarial networks (GAN) can be used to train a binary classifier to detect impact craters with only a few dozens of training samples.

​

The model achieves accuracy of 90% with only 50 samples. As a comparison, I show that a fully convolutional neural network cannot converge with such a small dataset.

​

See my github for more info

fake_samples_at_ts_1600.png

A snapshot of the SGAN model latent space after training for 20 epochs 

Publications in Peer Reviewed Journal and Books

  1. Williams, J.P. and Rubanenko, L., 2024. Cold-trapped ices at the poles of Mercury and the Moon. In Ices in the Solar-System (pp. 1-29). Elsevier (Link).

  2. Rubanenko, L., Gunn, A., Pérez‐López, S., Fenton, L.K., Ewing, R.C., Soto, A. and Lapôtre, M.G.A., 2023. Global surface winds and Aeolian sediment pathways on Mars from the morphology of barchan dunes. Geophysical Research Letters, 50(18), p.e2022GL102610 (Link).

  3. Prieur, N.C., Amaro, B., Gonzalez, E., Kerner, H., Medvedev, S., Rubanenko, L., Werner, S.C., Xiao, Z., Zastrozhnov, D. and Lapôtre, M.G., 2023. Automatic Characterization of Boulders on Planetary Surfaces From High‐Resolution Satellite Images. Journal of Geophysical Research: Planets, 128(11), p.e2023JE008013.

  4. Rubanenko, L., Lapôtre, M.G., Ewing, R.C., Fenton, L.K. and Gunn, A., (2022). A distinct ripple-formation regime on Mars revealed by the morphometrics of barchan dunes. Nature Communications, 13(1), pp.1-7 (Link).

  5. Gunn, A., Rubanenko, L. and Lapôtre, M.G., 2022. Accumulation of windblown sand in impact craters on Mars. Geology (Link).

  6. Rubanenko, L., Perez-Lopez, S., Schull J., and Lapotre, M.G.A, "Automatic Detection and Segmentation of Barchan Dunes on Mars and Earth Using a Convolutional Neural Network," (2021). IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, doi: 10.1109/JSTARS.2021.3109900 (Link)

  7. Rubanenko, L., Powell, T.M, Williams, J.-P., Daubar, I., Edgett, K. S., Paige, D. A., (2021). Challenges in crater chronology on Mars as Reflected in Jezero crater, in Soare R. J. (ed.), Conway, S. J. (ed.), Oehler, D. (ed.), Williams, J.-P. (ed.) Mars Geological Enigmas: From the Late Noachian Epoch to the Present Day. Elsevier, c. 9 (Link).

  8. Powell, T.M, Rubanenko, L., Williams, J.-P., Paige, D. A., In Press (2021). The Role of Secondary Craters on Martian Crater Chronology, in Soare R. J. (ed.), Conway, S. J. (ed.), Oehler, D. (ed.), Williams, J.-P. (ed.) Mars Geological Enigmas: From the Late Noachian Epoch to the Present Day. Elsevier, c. 9.

  9. Rubanenko, L., Schorghofer, N., Greenhagen, B.T. and Paige, D.A. (2020). Equilibrium Temperatures and Directional Emissivity of Sunlit Airless Surfaces With Applications to the Moon. Journal of Geophysical Research: Planets, 125(6) (Link).

  10. Rubanenko, L., Venkatraman, J. and Paige, D.A., Thick ice deposits in shallow simple craters on the Moon and Mercury, Nature Geoscience, 2019. 10.1038/s41561-019-0405-8. (Link).

  11. Rubanenko, L., Mazarico, E., Neumann, G.A. and Paige, D.A., Ice In Micro Cold‐Traps on Mercury: Implications for Age and Origin, JGR: Planets, 2018, Wiley (Link).

  12. Rubanenko, L., Aharonson, O., Stability of Ice on the Moon with Rough Topography, Icarus, 2017, Academic Press (Link).

  13. Yair, Y., Price, C., Katzenelson, D., Rosenthal, N., Rubanenko, L., Ben-Ami, Y., Arnone, E., Sprite climatology in the Eastern Mediterranean Region, Atmospheric Research, 157, 108-118, 2015, Elsevier (Link).

  14. Yair, Y., Rubanenko, L., Mezuman, K., Elhalel, G., Pariente, M., Glickman-Pariente, M., Ziv, B., Takahashi, Y., Inoue, T. ,New color images of transient luminous events from dedicated observations on the International Space Station, Journal of Atmospheric and Solar-Terrestrial Physics, 102, 140-147, 2013, Elsevier (Link).

Selected conference presentations

  1. Rubanenko, L., Paige, D.A., Moon, S. and Kakaria, R., 2023. CNN Detected Boulders across the Jezero Western Delta Fan Indicate Significantly Higher Flood Discharge Compared to Previous Estimates. AGU23.

  2. Prieur, N.C., Amaro, B., Gonzalez, E., Rubanenko, L., Kerner, H.R., Xiao, Z., Werner, S.C. and Lapotre, M.G.A., 2022, December. Deep Learning for Boulder Detection on Planetary Surfaces. In AGU Fall Meeting Abstracts (Vol. 2022, pp. P23A-02).

  3. Rubanenko, L., Fenton, L., Chojnacki, M. and Lapotre, M.G.A., 2022, December. Impact of Surface Volatiles on the Slipface Slope Angle of Martian Barchan Dunes. In AGU Fall Meeting Abstracts (Vol. 2022, pp. EP43A-09).

  4. Lapotre, M.G.A., Rubanenko, L., Ewing, R., Fenton, L. and Gunn, A., 2022, December. A Distinct Dune-Formation Regime on Mars. In AGU Fall Meeting Abstracts (Vol. 2022, pp. EP43A-06).

  5. Rubanenko, L., Lapotre, M. G. A., Schull, J., Perez-Lopez, S., Fenton, L. K., and Ewing, R. C., 2021. “Mapping Surface Winds on Mars from the Global Distribution of Barchan Dunes Employing an Instance Segmentation Neural Network”, EGU General Assembly.

  6. Rubanenko, L., Lapotre, M.G.A. Schull, J., Prerz-Lopez, S., Fenton, L.K. and Ewing, R.C., Mapping Mars' Surface Winds from the Global Distribution of Barchan Dunes Employing Artificial Intelligence. Lunar and Planetary Science Conference, 2021.

  7. Rubanenko, L., Lapotre, M.G.A., Schull, J., Fenton, L.K. and Ewing, R., 2020, December. Morphologic Analysis of Eolian Bedforms on Mars using Fully Convolutional Instance Segmentation Networks. In AGU Fall Meeting 2020. AGU.

  8. Rubanenko, L., Schorghofer, N., Greenhagen, B.T. and Paige, D.A., 2020. Equilibrium Temperatures and Directional Emissivity of Sunlit Rough Surfaces with Applications to the Moon. LPI, (2326), p.2876.

  9. Schorghofer, N., Prettyman, T.H., Rubanenko, L., Sizemore, H.G. and Yamashita, N., 2020. Impact Mixing of Ice-Rich Regolith on Ceres and on the Moon. LPI, (2326), p.1794.

  10. Paige, D.A. and Rubanenko, L., 2020. The Perfect Landing Site for the First Lunar South Polar Lander. LPI Contributions, 2241, p.5150.

  11. Rubanenko, L., Mazarico, E., Neumann, G.A., Paige, D.A.,The Depth of Ice Inside the Smallest Cold-Traps on Mercury: Implications for Age and Origin, Mercury: Current and Future Science of the Innermost Planet, 2018 (Link).

  12. Rubanenko, L., Hayne, P.O., Paige, D.A., The Effects of Surface Roughness on the Apparent Thermal and Optical Properties of the Moon, AGU Fall Meeting, 2017 (Link).

  13. Rubanenko, L., Mazarico, E., Neumann, G.A.; Paige, D.A., Evidence for Surface and Subsurface Ice Inside Micro Cold-Traps on Mercury's North Pole. Lunar and Planetary Science Conference, 2017 (Link).

  14. Neumann, G.A., Sun, X., Mazarico, E., Deutsch, A.N., Head, J.W., Paige, D.A., Rubanenko, L., Susorney, H.C.M. ",Latitudinal Variations in Mercury's Reflectance from the Mercury Laser Altimeter, Lunar and Planetary Science Conference, 2017 (Link).

  15. Rubanenko, L., Mazarico, E., Neumann, G.A., Paige, D.A., Estimating Surface and Subsurface Ice Abundance on Mercury Using a Thermophysical Model. AGU Fall Meeting Abstracts, 2016 (Poster).

  16. Rubanenko, L., Aharonson, O. Schorghofer, N., Temperature Distribution of Rough Airless Bodies and Volatile Stability, Lunar and Planetary Science Conference, 2016 (Link).

Anchor 2
bottom of page