Galaxy morphology classification using neural ordinary differential equations

Gupta, Raghav; Srijith, P. K.; Desai, S.

doi:10.1016/j.ascom.2021.100543

Cited by 23 publications

(22 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3). The principal difference between our approach and the existing ones (see, for example, recent works [56,[84][85][86]) is the usage of 1) the pre-defined training-test split through adversarial validation of the classification accuracy on the inference-like test set, and 2) the specific data augmentation, which allowed us to decrease the difference in galaxy images related to the stellar magnitudes between the GZ2 and inference data sets.…”

Section: Cnn Five-class Morphological Classifiermentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Cnn Five-class Morphological Classifiermentioning

confidence: 99%

“…3). The deal with testing classification quality on different distributions (e.g., between training and target datasets) has a few implementations for galaxy morphology classifications ( [86,[111][112][113]). Below we note several of them.…”

Section: Train-test Split Transformation Of Images By Intensity and S...mentioning

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

show abstract

“…The first three categories of tasks are problem-driven, i.e., once the goals are well-defined, the tasks can be handled in a supervised manner by involving well-designed training sets. These tasks help improve the accuracy and precision of the models for describing mainstream objects, and relevant approaches are relatively mature and widely applied in astronomy (Lukic et al 2019;Zhu et al 2019;Cheng et al 2020;Gupta et al 2022;Chen et al 2022;Zhang et al 2022). On the other hand, astronomical anomalies/outliers constantly lead to unforeseen knowledge in astronomy, which may trigger revolutionary discoveries.…”

Section: Introductionmentioning

confidence: 99%

Identifying outliers in astronomical images with unsupervised machine learning

Han,

Zou,

et al. 2022

Preprint

View full text Add to dashboard Cite

Astronomical outliers, such as unusual, rare or unknown types of astronomical objects or phenomena, constantly lead to the discovery of genuinely unforeseen knowledge in astronomy. More unpredictable outliers will be uncovered in principle with the increment of the coverage and quality of upcoming survey data. However, it is a severe challenge to mine rare and unexpected targets from enormous data with human inspection due to a significant workload. Supervised learning is also unsuitable for this purpose since designing proper training sets for unanticipated signals is unworkable. Motivated by these challenges, we adopt unsupervised machine learning approaches to identify outliers in the data of galaxy images to explore the paths for detecting astronomical outliers. For comparison, we construct three methods, which are built upon the k-nearest neighbors (KNN), Convolutional Auto-Encoder (CAE) + KNN, and CAE + KNN + Attention Mechanism (attCAE KNN) separately. Testing sets are created based on the Galaxy Zoo image data published online to evaluate the performance of the above methods. Results show that attCAE KNN achieves the best recall (78%), which is 53% higher than the classical KNN method and 22% higher than CAE+KNN. The efficiency

show abstract

“…Katebi et al (2019) used Capsule Network (CapsNet) for regression and predicted probabilities for all of the questions in the Galaxy Zoo project and trained a CapsNet classifier that outperforms the baseline CNN by 36.5% error reduction. Gupta et al (2022) introduced a continuous depth version of the Residual Network called Neural Ordinary Differential Equations (NODE) which obtained an accuracy between 91%-95% depending on the classifications. DL methods used for galaxy morphological classifications are discussed in Tuccillo et al (2016), Khan et al (2019), Ghosh et al (2020), Bhambra et al (2022), Zhang et al (2022) and Vavilova et al (2022).…”

mentioning

confidence: 99%

Unsupervised Galaxy Morphological Visual Representation with Deep Contrastive Learning

Wei¹,

Li²,

Lu³

et al. 2022

PASP

View full text Add to dashboard Cite

Galaxy morphology reflects structural properties that contribute to the understanding of the formation and evolution of galaxies. Deep convolutional networks have proven to be very successful in learning hidden features that allow for unprecedented performance in the morphological classification of galaxies. Such networks mostly follow the supervised learning paradigm, which requires sufficient labeled data for training. However, the labeling of a million galaxies is an expensive and complicated process, particularly for forthcoming survey projects. In this paper, we present an approach, based on contrastive learning, with aim of learning galaxy morphological visual representation using only unlabeled data. Considering the properties of low semantic information and contour dominated of galaxy images, the feature extraction layer of the proposed method incorporates vision transformers and a convolutional network to provide rich semantic representation via the fusion of multi-hierarchy features. We train and test our method on three classifications of data sets from Galaxy Zoo 2 and SDSS-DR17, and four classifications from Galaxy Zoo DECaLS. The testing accuracy achieves 94.7%, 96.5% and 89.9%, respectively. The experiment of cross validation demonstrates our model possesses transfer and generalization ability when applied to new data sets. The code that reveals our proposed method and pretrained models are publicly available and can be easily adapted to new surveys. 6 6 https://github.com/kustcn/galaxy_contrastive

show abstract

Galaxy morphology classification using neural ordinary differential equations

Cited by 23 publications

References 75 publications

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 the SDSS. III. The CNN image-based inference of detailed features

Identifying outliers in astronomical images with unsupervised machine learning

Unsupervised Galaxy Morphological Visual Representation with Deep Contrastive Learning

Contact Info

Product

Resources

About