Systematic Labeling Bias in Galaxy Morphologies

Cabrera-Vives, G.; Miller, Christopher J.; Schneider, Jeff

doi:10.3847/1538-3881/aae9f4

Cited by 8 publications

(5 citation statements)

References 41 publications

(59 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We find that the morphology based on the supervised machine learning methods trained over photometric parameters demonstrates significantly less bias than morphology based on citizen-science classifiers. This conclusion is in agreement with the results by Cabrera-Vives et al (2018), who found that "this result holds even when there is underlying bias present in the training sets used in the supervised machine learning process. "…”

Section: Several Problem Points Of the Supervised Machinesupporting

confidence: 92%

Machine learning technique for morphological classification of galaxies from the SDSS

Vavilova

Dobrycheva

Vasylenko

et al. 2021

A&A

View full text Add to dashboard Cite

Context. Machine learning methods are effective tools in astronomical tasks for classifying objects by their individual features. One of the promising utilities is related to the morphological classification of galaxies at different redshifts. Aims. We use the photometry-based approach for the SDSS data 1) to exploit five supervised machine learning techniques and define the most effective among them for the automated galaxy morphological classification; 2) to test the influence of photometry data on morphology classification; 3) to discuss problem points of supervised machine learning and labeling bias; and 4) to apply the best fitting machine learning methods for revealing the unknown morphological types of galaxies from the SDSS DR9 at z < 0.1. Methods. We used different galaxy classification techniques: human labeling, multi-photometry diagrams, naive Bayes, logistic regression, support-vector machine, random forest, k-nearest neighbors. Results. We present the results of a binary automated morphological classification of galaxies conducted by human labeling, multiphotometry, and five supervised machine learning methods. We applied it to the sample of galaxies from the SDSS DR9 with redshifts of 0.02 < z < 0.1 and absolute stellar magnitudes of −24 m < M r < −19.4 m . For the analysis we used absolute magnitudes M

show abstract

Section: Several Problem Points Of the Supervised Machinesupporting

confidence: 92%

Machine learning technique for morphological classification of galaxies from the SDSS

Vavilova

Dobrycheva

Vasylenko

et al. 2021

A&A

View full text Add to dashboard Cite

show abstract

“…Galaxy Zoo and human bias" 5 . We refer to the paper by Cabrera et al [105], where the metric for human labeling measuring in the case of low-redshift spiral/elliptical galaxies is proposed in the frame of label's comparison between experts, GZ volunteers, and ML models. Hart et al [106] developed a reliable method for defining spiral galaxies, which eliminates the redshift-dependent bias in the GZ2 volunteer's answers.…”

Section: General Results and Discussionmentioning

confidence: 99%

Machine learning technique for morphological classification of galaxies from the SDSS. III. The CNN image-based inference of detailed features

Khramtsov¹,

Vavilova²,

Dobrycheva³

et al. 2022

Kosm. nauka tehnol.

View full text Add to dashboard Cite

This paper follows a series of our works on the applicability of various machine learning methods to morphological galaxy classification (Vavilova et al., 2021, 2022). We exploited the sample of ~315800 low-redshift SDSS DR9 galaxies with absolute stellar magnitudes of −24m < Mr < −19.4m at 0.003 < z < 0.1 redshifts as a target data set for the CNN classifier. Because it is tightly overlapped with the Galaxy Zoo 2 (GZ2) sample, we use these annotated data as the training data set to classify galaxies into 34 detailed features. In the presence of a pronounced difference in visual parameters between galaxies from the GZ2 training data set and galaxies without known morphological parameters, we applied novel procedures, which allowed us for the first time to get rid of this difference for smaller and fainter SDSS galaxies with mr < 17.7. We describe in detail the adversarial validation technique as well as how we managed the optimal train-test split of galaxies from the training data set to verify our CNN model based on the DenseNet-201 realistically. We have also found optimal galaxy image transformations, which help increase the classifier’s generalization ability. We demonstrate for the first time that implication of the CNN model with a train-test split of data sets and size-changing function simulating a decrease in magnitude and size (data augmentation) significantly improves the classification of smaller and fainter SDSS galaxies. It can be considered as another way to improve the human bias for those galaxy images that had a poor vote classification in the GZ project. Such an approach, like autoimmunization, when the CNN classifier, trained on very good galaxy images, is able to retrain bad images from the same homogeneous sample, can be considered co-planar to other methods of combating such a human bias. The most promising result is related to the CNN prediction probability in the classification of detailed features. The accuracy of the CNN classifier is in the range of 83.3—99.4 % depending on 32 features (exception is for “disturbed” (68.55 %) and “arms winding medium” (77.39 %) features). As a result, for the first time, we assigned the detailed morphological classification for more than 140000 low-redshift galaxies, especially at the fainter end. A visual inspection of the samples of galaxies with certain morphological features allowed us to reveal typical problem points of galaxy image classification by shape and features from the astronomical point of view. The morphological catalogs of low-redshift SDSS galaxies with the most interesting features are available through the UkrVO website (http://ukr-vo.org/galaxies/) and VizieR.

show abstract

“…Cabrera et al [16] explained how the human labeled biases in morphological photometry-based classification could be reduced through supervised ML. This coincides with our conclusion [101], where we discuss which factors and properties of galaxies exactly affect the accuracy of supervised methods.…”

Section: Discussionmentioning

confidence: 99%

Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02<z<0.1

Vavilova¹,

Khramtsov²,

Dobrycheva³

et al. 2022

Kosm. nauka tehnol.

View full text Add to dashboard Cite

We applied the image-based approach with a convolutional neural network (CNN) model to the sample of low-redshift galaxies with –24m<Mr<–19.4m from the SDSS DR9. We divided it into two subsamples, SDSS DR9 galaxy dataset and Galaxy Zoo 2 (GZ2) dataset, considering them as the inference and training datasets, respectively. To determine the principal parameters of galaxy morphology defined within the GZ2 project, we classified the galaxies into five visual types and 34 morphological features of galaxies from the inference dataset, which do not match with GZ2 training dataset. As a result, we created the morphological catalog of 315782 galaxies at 0.02<z<0.1, where these classes and features were defined for the first time for 216148 galaxies by image-based CNN classifier. For the rest of galaxies the initial morphological classification was re-assigned as in the GZ2 project. Main results are presented in the catalog of 19468 completely rounded, 27321 rounded in-between, 3235 cigar-shaped, 4099 edge-on, 18615 spiral, and 72738 general low-redshift galaxies of the studied SDSS sample. Our method shows the promising performance of morphological classification attaining >93 % of accuracy for five classes morphology prediction except the cigar-shaped (~75 %) and completely rounded (~83 %) galaxies. As for the classification of galaxies by their detailed structural morphological features, our CNN model gives the accuracy in the range of 92–99 % depending on features, a number of galaxies with the given feature in the inference dataset, and the galaxy image quality. As a result, for the first time we assigned 34 morphological detailed features (bar, rings, number of spiral arms, mergers, etc.) for more than 160000 low-redshift galaxies from the SDSS DR9. We demonstrate that implication of the CNN model with adversarial validation and adversarial image data augmentation improves classification of smaller and fainter SDSS galaxies with mr <17.7.

show abstract

Systematic Labeling Bias in Galaxy Morphologies

Cited by 8 publications

References 41 publications

Machine learning technique for morphological classification of galaxies from the SDSS

Machine learning technique for morphological classification of galaxies from the SDSS

Machine learning technique for morphological classification of galaxies from the SDSS. III. The CNN image-based inference of detailed features

Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02<z<0.1

Contact Info

Product

Resources

About