Lior Rubanenko

Assistant Professor of Planetary Science

Tel Aviv University

About

Lior Rubanenko

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 an Assistant Professor at the Department of Earth and Planetary Sciences, Tel Aviv University. Previously, I was a postdoctoral scholar at the Department of Geological Sciences at Stanford University, where I worked 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 was the scientific editor-in-chief of "Mada Gadol Bektana" (lit. "Science in a Nutshell"), the largest science outreach non-profit organization in Israel, and give popular science talks aimed at general audiences and professional organizations. From time to time I also publish articles on planetary science or astronomy in Israeli news sites — for example, the potential discovery of a planetary mass object in the Kuiper Belt, based on this paper.

Current Research

Unsupervised deep learning analysis of spacecraft data

The vast volumes of information obtained by NASA spacecraft over the past decades require 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.

Read the DPS abstract

Autoencoder classification of impact crater freshness on the Moon
Autoencoder classification of impact crater freshness — Moon

Detecting and segmenting barchan 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 R-CNN, 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, based on OpenCV's convexity defects algorithm.

Read the paper

Detected barchan dunes with derived wind directions marked by arrows
Detected dunes and derived wind directions (red arrows) — MRO CTX

Training a crater detector on a few dozen samples

Classification of imagery data usually requires an expert human analyst to label and classify topographic features. Even binary classification using a fully convolutional neural network will typically have trouble converging until several hundred images have been labeled. Here I explore how generative adversarial networks can train a binary classifier to detect impact craters with only a few dozen training samples.

The model reaches 90% accuracy with 50 samples, where a fully convolutional network cannot converge at all on a dataset that small.

See the code on GitHub

Snapshot of the SGAN model latent space after training
SGAN latent space after 20 epochs of training

Publications

Peer-reviewed journals 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. JGR: 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 Lapôtre, M.G.A., 2021. Automatic detection and segmentation of barchan dunes on Mars and Earth using a convolutional neural network. IEEE JSTARS. Link
  7. Rubanenko, L., Powell, T.M., Williams, J.-P., Daubar, I., Edgett, K.S. and Paige, D.A., 2021. Challenges in crater chronology on Mars as reflected in Jezero crater. In Mars Geological Enigmas, Elsevier, c. 9. PDF
  8. Powell, T.M., Rubanenko, L., Williams, J.-P. and Paige, D.A., 2021. The role of secondary craters on Martian crater chronology. In Mars Geological Enigmas, 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. JGR: Planets, 125(6). Link
  10. Rubanenko, L., Venkatraman, J. and Paige, D.A., 2019. Thick ice deposits in shallow simple craters on the Moon and Mercury. Nature Geoscience. Link
  11. Rubanenko, L., Mazarico, E., Neumann, G.A. and Paige, D.A., 2018. Ice in micro cold-traps on Mercury: implications for age and origin. JGR: Planets, Wiley. Link
  12. Rubanenko, L. and Aharonson, O., 2017. Stability of ice on the Moon with rough topography. Icarus, Academic Press. Link
  13. Yair, Y., Price, C., Katzenelson, D., Rosenthal, N., Rubanenko, L., Ben-Ami, Y. and Arnone, E., 2015. Sprite climatology in the Eastern Mediterranean region. Atmospheric Research, 157, 108–118, Elsevier.
  14. Yair, Y., Rubanenko, L., Mezuman, K., Elhalel, G., Pariente, M., Glickman-Pariente, M., Ziv, B., Takahashi, Y. and Inoue, T., 2013. New color images of transient luminous events from dedicated observations on the International Space Station. JASTP, 102, 140–147, Elsevier.

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 Lapôtre, M.G.A., 2022. Deep learning for boulder detection on planetary surfaces. AGU Fall Meeting, pp.P23A-02.
  3. Rubanenko, L., Fenton, L., Chojnacki, M. and Lapôtre, M.G.A., 2022. Impact of surface volatiles on the slipface slope angle of Martian barchan dunes. AGU Fall Meeting, pp.EP43A-09.
  4. Lapôtre, M.G.A., Rubanenko, L., Ewing, R., Fenton, L. and Gunn, A., 2022. A distinct dune-formation regime on Mars. AGU Fall Meeting, pp.EP43A-06.
  5. Rubanenko, L., Lapôtre, 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., Lapôtre, M.G.A., Schull, J., Perez-Lopez, S., Fenton, L.K. and Ewing, R.C., 2021. Mapping Mars' surface winds from the global distribution of barchan dunes employing artificial intelligence. LPSC.
  7. Rubanenko, L., Lapôtre, M.G.A., Schull, J., Fenton, L.K. and Ewing, R., 2020. Morphologic analysis of eolian bedforms on Mars using fully convolutional instance segmentation networks. AGU Fall Meeting.
  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. and Paige, D.A., 2018. The depth of ice inside the smallest cold-traps on Mercury: implications for age and origin. Link
  12. Rubanenko, L., Hayne, P.O. and Paige, D.A., 2017. The effects of surface roughness on the apparent thermal and optical properties of the Moon. AGU Fall Meeting. Link
  13. Rubanenko, L., Mazarico, E., Neumann, G.A. and Paige, D.A., 2017. Evidence for surface and subsurface ice inside micro cold-traps on Mercury's north pole. LPSC. Link
  14. Neumann, G.A., Sun, X., Mazarico, E., Deutsch, A.N., Head, J.W., Paige, D.A., Rubanenko, L. and Susorney, H.C.M., 2017. Latitudinal variations in Mercury's reflectance from the Mercury Laser Altimeter. LPSC. Link
  15. Rubanenko, L., Mazarico, E., Neumann, G.A. and Paige, D.A., 2016. Estimating surface and subsurface ice abundance on Mercury using a thermophysical model. AGU Fall Meeting (poster).
  16. Rubanenko, L., Aharonson, O. and Schorghofer, N., 2016. Temperature distribution of rough airless bodies and volatile stability. LPSC. Link

Press

Contact

Department of Earth and Planetary Sciences
Tel Aviv University

Email liorr@tauex.tau.ac.il
GitHub github.com/liorruba