Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDetecting solar system objects with convolutional neural networks
201
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
In the preparation for ESAs Euclid mission and the large amount of data it will produce, we train deep convolutional neural networks on Euclid simulations classify solar system objects from other astronomical sources. Using transfer learning we are able to achieve a good performance despite our tiny dataset with as few as 7512 images. Our best model correctly identifies objects with a top accuracy of 94% and improves to 96% when Euclids dither information is included. The neural network misses ~50% of the slowest moving asteroids (v < 10 arcsec/h) but is otherwise able to correctly classify asteroids even down to 26 mag. We show that the same model also performs well at classifying stars, galaxies and cosmic rays, and could potentially be applied to distinguish all types of objects in the Euclid data and other large optical surveys.
rate research
Read More
Despite extensive searches and the relative proximity of solar system objects (SSOS) to Earth, many remain undiscovered and there is still much to learn about their properties and interactions. This work is the first in a series dedicated to detecting and analyzing SSOs in the all-sky NOIRLab Source Catalog (NSC). We search the first data release of the NSC with CANFind, a Computationally Automated NSC tracklet Finder. NSC DR1 contains 34 billion measurements of 2.9 billion unique objects, which CANFind categorizes as belonging to stationary (distant stars, galaxies) or moving (SSOs) objects via an iterative clustering method. Detections of stationary bodies for proper motion (mu) less than 2.5/hr (0.017 degrees/day) are identified and analyzed separately. Remaining detections belonging to hi-mu objects are clustered together over single nights to form tracklets. Each tracklet contains detections of an individual moving object, and is validated based on spatial linearity and motion through time. Proper motions are then calculated and used to connect tracklets and other unassociated measurements over multiple nights by predicting their locations at common times forming tracks. This method extracted 527,055 tracklets from NSC DR1 in an area covering 29,971 square degrees of the sky. The data show distinct groups of objects with similar observed mu in ecliptic coordinates, namely Main Belt Asteroids, Jupiter Trojans, and Kuiper Belt Objects. Apparent magnitudes range from 10-25 mag in the ugrizY and VR bands. Color-color diagrams show a bimodality of tracklets between primarily carbonaceous and siliceous groups, supporting prior studies.
The search for minor bodies in the solar system promises insights into its formation history. Wide imaging surveys offer the opportunity to serendipitously discover and identify these traces of planetary formation and evolution. We aim to present a method to acquire position, photometry, and proper motion measurements of solar system objects in surveys using dithered image sequences. The application of this method on the Kilo-Degree Survey is demonstrated. Optical images of 346 square degree fields of the sky are searched in up to four filters using the AstrOmatic software suite to reduce the pixel to catalog data. The solar system objects within the acquired sources are selected based on a set of criteria depending on their number of observation, motion, and size. The Virtual Observatory SkyBoT tool is used to identify known objects. We observed 20,221 SSO candidates, with an estimated false-positive content of less than 0.05%. Of these SSO candidates, 53.4% are identified by SkyBoT. KiDS can detect previously unknown SSOs because of its depth and coverage at high ecliptic latitude, including parts of the Southern Hemisphere. Thus we expect the large fraction of the 46.6% of unidentified objects to be truly new SSOs. Our method is applicable to a variety of dithered surveys such as DES, LSST, and Euclid. It offers a quick and easy-to-implement search for solar system objects. SkyBoT can then be used to estimate the completeness of the recovered sample.
A machine learning technique with two-dimension convolutional neural network is proposed for detecting exoplanet transits. To test this new method, five different types of deep learning models with or without folding are constructed and studied. The light curves of the Kepler Data Release 25 are employed as the input of these models. The accuracy, reliability, and completeness are determined and their performances are compared. These results indicate that a combination of two-dimension convolutional neural network with folding would be an excellent choice for the future transit analysis.
We present a methodology for automated real-time analysis of a radio image data stream with the goal to find transient sources. Contrary to previous works, the transients we are interested in occur on a time-scale where dispersion starts to play a role, so we must search a higher-dimensional data space and yet work fast enough to keep up with the data stream in real time. The approach consists of five main steps: quality control, source detection, association, flux measurement, and physical parameter inference. We present parallelized methods based on convolutions and filters that can be accelerated on a GPU, allowing the pipeline to run in real-time. In the parameter inference step, we apply a convolutional neural network to dynamic spectra that were obtained from the preceding steps. It infers physical parameters, among which the dispersion measure of the transient candidate. Based on critical values of these parameters, an alert can be sent out and data will be saved for further investigation. Experimentally, the pipeline is applied to simulated data and images from AARTFAAC (Amsterdam Astron Radio Transients Facility And Analysis Centre), a transients facility based on the Low-Frequency Array (LOFAR). Results on simulated data show the efficacy of the pipeline, and from real data it discovered dispersed pulses. The current work targets transients on time scales that are longer than the fast transients of beam-formed search, but shorter than slow transients in which dispersion matters less. This fills a methodological gap that is relevant for the upcoming Square-Kilometer Array (SKA). Additionally, since real-time analysis can be performed, only data with promising detections can be saved to disk, providing a solution to the big-data problem that modern astronomy is dealing with.
Advances in radio spectro-polarimetry offer the possibility to disentangle complex regions where relativistic and thermal plasmas mix in the interstellar and intergalactic media. Recent work has shown that apparently simple Faraday Rotation Measure (RM) spectra can be generated by complex sources. This is true even when the distribution of RMs in the complex source greatly exceeds the errors associated with a single component fit to the peak of the Faraday spectrum. We present a convolutional neural network (CNN) that can differentiate between simple Faraday thin spectra and those that contain multiple or Faraday thick sources. We demonstrate that this CNN, trained for the upcoming Polarisation Sky Survey of the Universes Magnetism (POSSUM) early science observations, can identify two component sources 99% of the time, provided that the sources are separated in Faraday depth by $>$10% of the FWHM of the Faraday Point Spread Function, the polarized flux ratio of the sources is $>$0.1, and that the Signal-to-Noise radio (S/N) of the primary component is $>$5. With this S/N cut-off, the false positive rate (simple sources mis-classified as complex) is $<$0.3%. Work is ongoing to include Faraday thick sources in the training and testing of the CNN.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
