269 Planetary Geologic Mapping Across the Solar System (Posters)

We invite abstracts that showcase planetary geologic maps, discuss mapping strategies, and leverage map-based investigations of planetary surfaces at multiple scales.

Wednesday, 22 October 2025
8:00 AM - 5:30 PM
HBGCC, Hall 1

Preparing for VERITAS: Integrating Manual and Machine-Learning Approaches to Lava Flow Mapping on Venus

Paper number: 269-3
Program: Technical Sessions
Time: 8:00 AM – 8:00 AM

Authors

Abstract

Venus is covered in volcanic landforms, with strong evidence suggesting that volcanic processes may still be ongoing. Lava flows are key surface indicators of this activity and offer insight into the planet’s geologic processes and history. Volcanic flows occur globally and have not yet been systematically mapped. In support of future geologic mapping and mission data processing, this project explores a scalable approach to identifying lava flow boundaries using Magellan synthetic aperture radar (SAR) data and image segmentation and classification techniques.

 

Focusing on multiple lava flow fields across the southern hemisphere of Venus, we first manually digitized flow boundaries in ArcGIS Pro based on Magellan SAR backscatter characteristics, including flow shape, tonal variation, and edge sharpness. This manual process established a reference dataset and a standardized protocol for interpreting SAR imagery in the absence of optical data.

 

To evaluate the potential of machine learning for geologic mapping, we applied the Image Segmentation tool to Magellan SAR mosaics, experimenting with a range of parameters to optimize segmentation output. In parallel, we tested whether the addition of other data (i.e., topography and emissivity data) improves the detection of flow boundaries. Initial results show comparable performance to single-band SAR data, with minimal deviation. Ongoing efforts include creating training datasets and supervised classification techniques to assess whether meaningful distinctions in radar tone and texture can support reliable lava flow detection at scale.

 

This study demonstrates the potential for applying semi-automated techniques to SAR data for planetary surface mapping. Our iterative layered approach combining manual interpretation, segmentation, and classification offers a foundation for workflows applicable to large-scale radar datasets expected from upcoming NASA missions such as VERITAS. By testing and refining this process now, we aim to support more efficient geospatial analysis of Venus’ volcanic features as new mission data becomes available. This approach will also enable clearer comparisons, improving our ability to detect changes in lava flow patterns and activity over time.

Geological Society of America Abstracts with Programs. Vol. 57, No. 6

doi: 10.1130/abs/2025AM-414036

© Copyright 2025 The Geological Society of America (GSA), all rights reserved. Permission is hereby granted to the author(s) of this abstract to reproduce and distribute it freely, for noncommercial purposes. Permission is hereby granted to any individual scientist to download a single copy of this electronic file and reproduce up to 20 paper copies for noncommercial purposes advancing science and education, including classroom use, providing all reproductions include the complete content shown here, including the author information. All other forms of reproduction and/or transmittal are prohibited without written permission from GSA Copyright Permissions.