SCEC Award Number 20129 View PDF
Proposal Category Individual Proposal (Data Gathering and Products)
Proposal Title Search, Map, and Analyze the Dynamics of Fragile Geologic Features
Name Organization
Ramon Arrowsmith Arizona State University Jnaneshwar Das Arizona State University
Other Participants Zhiang Chen (PhD student), Tyler Scott (MS student), Harish Anand (PhD student)
SCEC Priorities 1a, 4a, 5b SCEC Groups Geology, SAFS, EFP
Report Due Date 03/15/2021 Date Report Submitted 03/17/2021
Project Abstract
Robotic mapping is useful in scientific applications that involve surveying unstructured environments. This project presents a target-oriented mapping system for sparsely distributed geologic surface features, such as precariously balanced rocks (PBRs), whose geometric fragility parameters can provide valuable information on earthquake shaking history and landscape development for a region. With this geomorphology problem as the test domain, we demonstrate a pipeline for detecting, localizing, and precisely mapping fragile geologic features distributed on a landscape. To do so, we first carry out a lawn-mower search pattern in the survey region from a high elevation using an Unpiloted Aerial Vehicle (UAV). Once a potential PBR target is detected by a deep neural network, we track the bounding box in the image frames using a real-time tracking algorithm. The location and occupancy of the target in world coordinates are estimated using a sampling-based filtering algorithm, where a set of 3D points are re-sampled after weighting by the tracked bounding boxes from different camera perspectives. The converged 3D points provide a prior on 3D bounding shape of a target, which is used for UAV path planning to closely and completely map the target with Simultaneous Localization and Mapping (SLAM). After target mapping, the UAV resumes the lawn-mower search pattern to find the next target. We introduce techniques to make the target mapping robust to false positive and missing detection from the neural network. Our target-oriented mapping system has the advantages of reducing map storage and emphasizing complete visible surface features on specified targets.
Intellectual Merit This project advanced methodologies for searching and mapping precariously balanced rocks, and also to analyze them, leveraging modern physics simulation engines.
Broader Impacts Teaching: Course application in ASU SES 494/598 midterm features an assignment for students to plan UAS paths to map a precariously balanced rock, in a simulation, on a prior mapped terrain.

Training: The tools and methods are directly supporting dissertation work of a Ph.D. student (Zhiang Chen, lead author on submitted manuscript), and masters thesis work (Devin Keating).

Learning/(dissemination): Multiple presentations have been given, at SCEC Plenary, AGU session on AI for geosciences, and JPL 2nd Data Science Workshop.
Exemplary Figure Figures 6,7, and 8.