AutoSourceID-Classifier
star-galaxy classification using a convolutional neural network with spatial information
Abstract
Aims: Traditional star-galaxy classification techniques often rely on feature estimation from catalogs, a process susceptible to introducing inaccuracies, thereby potentially jeopardizing the classification’s reliability. Certain galaxies, especially those not manifesting as extended sources, can be misclassified when their shape parameters and flux solely drive the inference. We aim to create a robust and accurate classification network for identifying stars and galaxies directly from astronomical images.
Methods: The AutoSourceID-Classifier (ASID-C) algorithm developed for this work uses 32x32 pixel single filter band source cutouts
generated by the previously developed AutoSourceID-Light (ASID-L) code. By leveraging convolutional neural networks (CNN) and
additional information about the source position within the full-field image, ASID-C aims to accurately classify all stars and galaxies within a survey. Subsequently, we employed a modified Platt scaling calibration for the output of the CNN, ensuring that the derived probabilities were effectively calibrated, delivering precise and reliable results.
Results: We show that ASID-C, trained on MeerLICHT telescope images and using the Dark Energy Camera Legacy Survey (DECaLS) morphological classification, is a robust classifier and outperforms similar codes such as SourceExtractor. To facilitate a rigorous comparison, we also trained an eXtreme Gradient Boosting (XGBoost) model on tabular features extracted by SourceExtractor.
While this XGBoost model approaches ASID-C in performance metrics, it does not offer the computational efficiency and reduced
error propagation inherent in ASID-C’s direct image-based classification approach. ASID-C excels in low signal-to-noise ratio and crowded scenarios, potentially aiding in transient host identification and advancing deep-sky astronomy.
Keywords
astronomical databases;data analysis;statistics;image processing;
Data
| Language: | English |
|---|---|
| Year of publishing: | 2023 |
| Typology: | 1.01 - Original Scientific Article |
| Organization: | UNG - University of Nova Gorica |
| UDC: | 52 |
| COBISS: |
177027843
|
| ISSN: | 1432-0746 |
| Views: | 83 |
| Downloads: | 0 |
| Average score: | 0 (0 votes) |
| Metadata: |
|
Other data
| Pages: | str. 1-16 |
|---|---|
| Volume: | ǂVol. ǂ |
| Issue: | ǂ[article no.] ǂ |
| Chronology: | 2023 |
| DOI: | 10.1051/0004-6361/202347576 |
| ID: | 21654627 |
Recommended works:
AutoSourceID-Classifier
2023,
star-galaxy classification using a convolutional neural network with spatial information
AutoSourceID-Light
2022,
fast optical source localization via U-net and Laplacian of Gaussian
AutoSourceID-FeatureExtractor
2023,
optical image analysis using a two-step mean variance estimation network for feature estimation and uncertainty characterisation
Analiza podatkov sistema SUMO s pomočjo storitev računalništva v oblaku
2022,
magistrsko delo