Using Deep Learning to Automate Inference of Meteoroid Pre-Entry Properties
Properly assessing the asteroid threat depends on the knowledge of asteroid pre-entry parameters, such as size, velocity, mass, density, and strength. Although a vast number of possible bodies to study exist, such characterization of asteroid populations is currently limited by substantial costs ass...
Main Authors: | , , , , |
---|---|
Format: | Other/Unknown Material |
Language: | unknown |
Published: |
2019
|
Subjects: | |
Online Access: | http://hdl.handle.net/2060/20200000439 |
id |
ftnasantrs:oai:casi.ntrs.nasa.gov:20200000439 |
---|---|
record_format |
openpolar |
spelling |
ftnasantrs:oai:casi.ntrs.nasa.gov:20200000439 2023-05-15T18:30:06+02:00 Using Deep Learning to Automate Inference of Meteoroid Pre-Entry Properties Tarano, Ana Maria Close, Sigrid Gee, Jonathan Mathias, Donovan Wheeler, Lorien Unclassified, Unlimited, Publicly available December 9, 2019 application/pdf http://hdl.handle.net/2060/20200000439 unknown Document ID: 20200000439 http://hdl.handle.net/2060/20200000439 Copyright, Public use permitted CASI Astronomy ARC-E-DAA-TN76511 AGU Fall 2019 Meeting; Dec 09, 2019 - Dec 13, 2019; San Francisco, CA; United States 2019 ftnasantrs 2020-02-01T23:47:41Z Properly assessing the asteroid threat depends on the knowledge of asteroid pre-entry parameters, such as size, velocity, mass, density, and strength. Although a vast number of possible bodies to study exist, such characterization of asteroid populations is currently limited by substantial costs associated with space rendezvous missions and rare meteorite findings. As asteroids fragment, ablate, and decelerate in the atmosphere, they emit light detectable by ground-based and space-borne instruments. Earths atmosphere, thus, becomes an accessible laboratory that enables impactor risk assessments by facilitating inference of the pre-entry parameters. These asteroid pre-entry conditions are typically deduced by modeling the entry and breakup physics that best reproduce the observed light or energy deposition curve. However, this process requires extensive manual trial-and-error of uncertain modeling parameters. Automating meteor modeling and inference would improve property distributions used in risk assessments and enable population characterization as more light curves become more readily available through the presence of space assets and ground-based camera networks. We previously developed a genetic algorithm to automate meteor modeling by using the fragment-cloud model (FCM) to search for the values of the FCM input parameters (e.g., diameter) that generate energy deposition profiles that match the observed one. Now, we apply deep learning to infer asteroid diameter, velocity, and density from observed energy deposition curves. We trained and tested our neural network models with synthetic energy deposition curves modeled using the FCM rubble pile implementation. We present an application of a 1D convolutional neural network and compare its performance to other attempted regressors and machine learning techniques, such as a fully connected neural network and Random Forest regression, to demonstrate its capabilities. We validate our model weights and approach using the Chelyabinsk, Tagish Lake, Beneov, Koice, and Lost City meteors. Other/Unknown Material Tagish NASA Technical Reports Server (NTRS) Tagish ENVELOPE(-134.272,-134.272,60.313,60.313) Tagish Lake ENVELOPE(-134.233,-134.233,59.717,59.717) |
institution |
Open Polar |
collection |
NASA Technical Reports Server (NTRS) |
op_collection_id |
ftnasantrs |
language |
unknown |
topic |
Astronomy |
spellingShingle |
Astronomy Tarano, Ana Maria Close, Sigrid Gee, Jonathan Mathias, Donovan Wheeler, Lorien Using Deep Learning to Automate Inference of Meteoroid Pre-Entry Properties |
topic_facet |
Astronomy |
description |
Properly assessing the asteroid threat depends on the knowledge of asteroid pre-entry parameters, such as size, velocity, mass, density, and strength. Although a vast number of possible bodies to study exist, such characterization of asteroid populations is currently limited by substantial costs associated with space rendezvous missions and rare meteorite findings. As asteroids fragment, ablate, and decelerate in the atmosphere, they emit light detectable by ground-based and space-borne instruments. Earths atmosphere, thus, becomes an accessible laboratory that enables impactor risk assessments by facilitating inference of the pre-entry parameters. These asteroid pre-entry conditions are typically deduced by modeling the entry and breakup physics that best reproduce the observed light or energy deposition curve. However, this process requires extensive manual trial-and-error of uncertain modeling parameters. Automating meteor modeling and inference would improve property distributions used in risk assessments and enable population characterization as more light curves become more readily available through the presence of space assets and ground-based camera networks. We previously developed a genetic algorithm to automate meteor modeling by using the fragment-cloud model (FCM) to search for the values of the FCM input parameters (e.g., diameter) that generate energy deposition profiles that match the observed one. Now, we apply deep learning to infer asteroid diameter, velocity, and density from observed energy deposition curves. We trained and tested our neural network models with synthetic energy deposition curves modeled using the FCM rubble pile implementation. We present an application of a 1D convolutional neural network and compare its performance to other attempted regressors and machine learning techniques, such as a fully connected neural network and Random Forest regression, to demonstrate its capabilities. We validate our model weights and approach using the Chelyabinsk, Tagish Lake, Beneov, Koice, and Lost City meteors. |
format |
Other/Unknown Material |
author |
Tarano, Ana Maria Close, Sigrid Gee, Jonathan Mathias, Donovan Wheeler, Lorien |
author_facet |
Tarano, Ana Maria Close, Sigrid Gee, Jonathan Mathias, Donovan Wheeler, Lorien |
author_sort |
Tarano, Ana Maria |
title |
Using Deep Learning to Automate Inference of Meteoroid Pre-Entry Properties |
title_short |
Using Deep Learning to Automate Inference of Meteoroid Pre-Entry Properties |
title_full |
Using Deep Learning to Automate Inference of Meteoroid Pre-Entry Properties |
title_fullStr |
Using Deep Learning to Automate Inference of Meteoroid Pre-Entry Properties |
title_full_unstemmed |
Using Deep Learning to Automate Inference of Meteoroid Pre-Entry Properties |
title_sort |
using deep learning to automate inference of meteoroid pre-entry properties |
publishDate |
2019 |
url |
http://hdl.handle.net/2060/20200000439 |
op_coverage |
Unclassified, Unlimited, Publicly available |
long_lat |
ENVELOPE(-134.272,-134.272,60.313,60.313) ENVELOPE(-134.233,-134.233,59.717,59.717) |
geographic |
Tagish Tagish Lake |
geographic_facet |
Tagish Tagish Lake |
genre |
Tagish |
genre_facet |
Tagish |
op_source |
CASI |
op_relation |
Document ID: 20200000439 http://hdl.handle.net/2060/20200000439 |
op_rights |
Copyright, Public use permitted |
_version_ |
1766213578995531776 |