Machine learning technique for morphological classification of galaxies from SDSS. IV. CNN-Assisted Expert Validation of Morphological Catalogues for Merging, Irregular, Edge-on, Barred, Ringed, and Dust-lane Galaxies at 0.003 < z < 0.1

arXiv:2604.24471 · astro-ph.GA · Submitted 2026-04-27 · Read on arXiv

Listen

Radio episode about this paper

Transcript

Introduction to the show: ident: Astrophysics Radio. Generated commentary on the latest astrophysics papers.

Vera: We're looking at the paper: "Machine learning technique for morphological classification of galaxies from SDSS. IV. CNN-Assisted Expert Validation of Morphological Catalogues for Merging, Irregular, Edge-on, Barred, Ringed, and Dust-lane Galaxies at 0.003 < z < 0.1".

Jocelyn: Here's the gist of the paper. Machine learning technique for morphological classification of galaxies from SDSS.

Vera: IV.

Jocelyn: CNN-Assisted Expert Validation of Morphological Catalogues for Merging, Irregular, Edge-on, Barred, Ringed, and Dust-lane Galaxies at 0.003 < z < 0.1 is a comprehensive visual inspection of SDSS galaxies to assess the completeness and typical failure modes of CNN-based classifications and to construct homogeneous, visually verified catalogues of galaxies with these morphological features.

Vera: Pruning redundant reasoning tokens The aim of this work is to perform a comprehensive visual inspection of SDSS galaxies at 0.02 < z < 0.1 previously classified by a CNN as merging, irregular and edge-on galaxies as well as galaxies with bar, ring, and dust lane.

Title and authors: Vera: To summarize what this paper is doing more broadly, it’s taking an existing machine learning classification for SDSS galaxies and subjecting those results to a rigorous visual inspection by experts. They are focusing on specific galaxy shapes—merging, irregular, edge-on, barred, ringed, and dust lane galaxies—at redshifts between zero point zero two and zero point one <ref:2604.24471#pg1,merging, irregular, edge-on, barred, ringed, and>.

Jocelyn: The core goal is to assess the completeness of the CNN's classifications and identify the typical failure modes of that machine learning system when it deals with these specific features. They are trying to create catalogues where every galaxy has been visually verified for its morphology, making them homogeneous in a way that a purely automated classification might not achieve.

Subrahmanyan: This process also involves an additional objective: determining the type of nuclear activity for most galaxies in these different morphological groups by using BPT diagrams, and spotting any rare systems that the inspection reveals.

Vera: So, to put it plainly, they are checking if the machine is reliable for these types of galaxies and then building a gold standard catalogue where human eyes have confirmed everything about those features.

Jocelyn: It’s essentially a quality control step for automated morphological studies, ensuring that when we use these galaxy catalogues later in our cosmological modelling or structure formation studies, they are as accurate as possible.

Subrahmanyan: This is important because if the underlying classification tool has systematic biases—say, if it consistently misidentifies edge-on galaxies—then those systematic errors will get baked into our larger simulations or analyses (reference: <ref:2604.24471#pg1>). So validating the tool upfront saves a lot of work later.

Vera: Exactly. They are using this visual inspection to build a dataset that is not just machine-generated, but one that is confirmed by experts for its morphological features and other physical properties they're measuring.

Jocelyn: The results show that this verification process actually uncovered a lot of things, like how many irregular galaxies were truly irregular, and how few dust lane galaxies the CNN was actually finding initially.

Subrahmanyan: Those findings on completeness are key. If the CNN is undercounting a certain class—like dust lanes—it means our theoretical models predicting that structure might be less common than the machine suggests (reference: <ref:2604.24471#pg6>).

Vera: So, this paper moves beyond just reporting an accuracy score to actually showing *where* and *why* the classification is failing in a physical context. It's about understanding the limitations of the technology itself.

Jocelyn: And by linking morphology to nuclear activity, they are adding another layer of astrophysical information that isn't immediately obvious from just looking at shape alone.

Subrahmanyan: That kind of multi-faceted analysis is what we need to move from descriptive catalogues to truly predictive ones in cosmology (reference: <ref:2604.24471#pg6>). It’s about linking the observable structure to the underlying physics.

The paper's summary: Vera: So, when we look at what this paper suggests as improvements, they are really focusing on making that CNN model more robust by using adversarial validation and a train-test split in conjunction with optimal image transformations. This helps it better simulate the effect of decreasing magnitude and size.

Jocelyn: They used these specific techniques to try and improve how well the machine handles those GZ2 galaxy images that got a poor vote classification, which is where human bias was strongest. It’s an attempt to refine the model specifically around known weak points.

Subrahmanyan: From a theoretical side, this suggests that by carefully controlling the input image space—simulating size and magnitude changes—we can push the model's performance beyond what it could achieve with standard training alone (reference: <ref:2604.24471#pg3>). It’s about finding the optimal way to train a model for specific observational constraints.

Vera: The paper shows that this refined approach did achieve accuracy above ninety-three percent for three classes, but it still had those noted exceptions where cigar-shaped and completely rounded galaxies were less accurate, around seventy-five and eighty-three percent respectively.

Jocelyn: So the improvement is incremental; it’s pushing the ceiling higher on some features but not fixing all of them, which is realistic for complex astronomical data. It shows a nuanced performance profile instead of just a blanket high accuracy number.

Subrahmanyan: That nuance is what matters most in astrophysics. A model that gets ninety-nine percent accuracy on one class but seventy-five percent on another tells us exactly where the physical degeneracy lies in the data, which is incredibly useful for guiding future survey design (reference: <ref:2604.24471#pg3>).

Vera: And then they use that improved model to conduct the visual inspection, which is where the real validation happens—cross-matching those CNN predictions with Galaxy Zoo two data to refine their results. This closes the loop between machine prediction and expert truth.

Jocelyn: That cross-matching step is what addresses those projection effects and foreground stars directly because you are comparing the machine's output against known, verified human classifications. It’s a direct validation of the AI's output against reality.

Subrahmanyan: This whole improved system builds a bridge between automated classification and expert knowledge. It gives us not just a better catalogue, but a mechanism to learn *how* to classify galaxies more accurately by incorporating this visual feedback into the training loop (reference: <ref:2604.24471#pg3>).

Vera: The main improvement is building these homogeneous and visually verified catalogues for all those features—merging galaxies with six hundred twelve, irregular galaxies with nine thousand three hundred seventy-two edge-on ones with sixteen thousand eight hundred twenty-two barred ones with eight hundred eleven, ringed galaxies with two thousand one hundred fifty and dust lane galaxies with five hundred seventy-five.

Jocelyn: That’s a lot of verified data across different features. It shows the scale of the problem they are addressing here—they aren't just looking at a few examples; they are trying to cover all these distinct morphological categories systematically.

Subrahmanyan: Having such comprehensive, verified datasets will definitely enhance the robustness of morphological studies and provide reliable training samples for future machine learning models that aim to classify galaxies in even larger surveys (reference: <ref:2604.24471#pg3>).

The paper's improvements: Vera: So, wrapping up the whole thing, the main implication of this work is that we can achieve a much more reliable way to study galaxy morphology by combining CNN predictions with comprehensive visual expert validation. They’ve built these homogeneous catalogues that serve as benchmarks for future astrophysical analyses.

Jocelyn: This means when we look at these verified catalogues, we have a much stronger foundation for making claims about the underlying physics of those galaxies, whether it's how they evolve or what's happening in their centers.

Subrahmanyan: And they’ve managed to define a spectral type of nuclear activity for most studied SDSS galaxies at redshift less than zero point one specifically for edge-on galaxies and the ones with ring, bar, and dust lane morphologies, which is new information we should keep in mind <ref:2604.24471#pg1>.

Vera: They also identified five strong candidates for polar ring galaxies by systematically inspecting the CNN-classified ringed or irregular systems during their work, which shows how much detail you can extract when you look closely.

Jocelyn: It’s a good demonstration of how these combined approaches—AI for sorting and experts for validating—can lead to more detailed scientific understanding than either method could achieve alone.

Subrahmanyan: The full paper, "Machine learning technique for morphological classification of galaxies from SDSS. IV. CNN-Assisted Expert Validation of Morphological Catalogues for Merging, Irregular, Edge-on, Barred, Ringed, and Dust-lane Galaxies at zero point zero zero three < z < zero point one," provides a valuable blueprint for how to move toward more trustworthy automated classification tools in galaxy surveys.

Conclusion: Vera: So what we’ve seen here is how they took an existing CNN for classifying SDSS galaxies and put in this whole expert validation process, focusing on things like merging, irregular, edge-on, barred, ringed, and dust lane galaxies at redshifts between zero point zero zero three and zero point one.

Jocelyn: Exactly. It’s all about checking the completeness of those CNN classifications and figuring out where the machine messes up when it sees these specific shapes. They built these homogeneous catalogues that are visually verified, which is a big deal for making sure our data sets are solid.

Subrahmanyan: From a theoretical standpoint, this process helps us understand if our automated classification methods have hidden biases that could mess with the bigger picture of galaxy structure formation at those early cosmic times.

Vera: They also looked at nuclear activity, using BPT diagrams for most of these galaxies and even found some rare systems that were missed in the initial machine learning pass.

Jocelyn: That’s interesting because linking morphology to nuclear activity gives us another piece of information we can use to constrain what’s happening inside those galaxies.

Subrahmanyan: Yes, and the systematic differences they found in those BPT diagrams—for example, how many ringed galaxies were classified as LINERs—that tells us something about the energy sources driving activity in different galaxy shapes.

Vera: I mean that’s a lot of data being pulled from these observations. The authors showed that projection effects and things like foreground stars are the main reasons why the CNN made mistakes, especially when looking at merging galaxies or edge-on ones.

Jocelyn: It makes sense; you can easily get confused between a long silhouette of an edge-on galaxy and a merging system, which is why that visual cross-matching was so important to refine things.

Subrahmanyan: So the improvement they showed in the CNN model, using those adversarial validations and optimal image transformations to simulate changes in magnitude and size, did push its accuracy above ninety-three percent for some classes.

Vera: That's solid performance on three of them, but they noted that cigar-shaped galaxies and completely rounded ones were still a bit weaker at around seventy-five and eighty-three percent accuracy respectively.

Jocelyn: So the takeaway there is that the AI can get pretty good at identifying these features, but it’s still not perfect on all of them, which is why that human expert validation was necessary to build those trusted catalogues.

Subrahmanyan: These verified datasets will serve as reliable training samples for future machine learning models and give us a much better foundation for subsequent astrophysical analyses in cosmology.

Vera: So to wrap up, this paper, "Machine learning technique for morphological classification of galaxies from SDSS. IV. CNN-Assisted Expert Validation of Morphological Catalogues for Merging, Irregular, Edge-on, Barred, Ringed, and Dust-lane Galaxies at zero point zero zero three < z < zero point one," really shows how combining machine learning with human eyes can produce a much more robust result.

Jocelyn: It’s a good demonstration of how we can take automated classification and make it useful by grounding it in actual visual confirmation and adding that extra layer of physical data about the nuclear activity.

Subrahmanyan: This work sets up a benchmark for future studies, giving us high-quality, verified catalogues that we can rely on when we’re trying to model how galaxies evolve across cosmic time.

Vera: And it opens the door for building even better AI tools by feeding them these verified catalogues back in as training material.

Jocelyn: Next up, we’re looking at some work on dark matter winds and how they affect the distribution of baryons in galactic halos.

Main Astronomical Observatory of the NAS of Ukraine

astro-ph.GA

Submitted: 2026-04-27

Updated: 2026-11-05

Comments: 17 pages, 11 figures, 3 tables, 84 references, accepted to A&A

License: http://creativecommons.org/licenses/by/4.0/

Importance score: 90/100

The gist: Machine learning technique for morphological classification of galaxies from SDSS.

Key concepts

CNN-Assisted Expert Validation
This involves using a computer model (CNN) to initially sort galaxies by shape and then having human experts visually inspect those classifications. The goal is to see where the AI makes mistakes and create perfectly verified lists of galaxies with specific features.
Morphological Classification
This is the process of categorizing galaxies based on their visual structure, such as whether they are merging, spiral, or have a dust lane. The study aims to improve how accurately computers can perform this visual sorting task.
Failure Modes
These are the specific types of errors or mistakes that occur when the CNN misclassifies a galaxy. The researchers identified these errors, such as confusion caused by projection effects (like overlapping stars) or faint features, to improve the AI's performance.
Homogeneous Catalogues
These are final lists of galaxies that have been thoroughly checked by experts and verified visually. These catalogues are important because they provide high-quality, reliable data that can be used to train better machine learning models later.

Terminology

Summary

Machine learning technique for morphological classification of galaxies from SDSS. p. 0

Where the paper says it

Astronomy & Astrophysics manuscript no. Dobrycheva_et_al_2025 ©ESO 2026 April 28, 2026 Machine learning technique for morphological classification of galaxies from SDSS.

IV. CNN-Assisted Expert Validation of Morphological Catalogues for Merging, Irregular, Edge-on, Barred, Ringed, and Dust-lane Galaxies at 0. p. 0
Where the paper says it

Dobrycheva_et_al_2025 ©ESO 2026 April 28, 2026 Machine learning technique for morphological classification of galaxies from SDSS. Visual inspection vs CNN for merging, irregular, edge-on, barred, ringed, and with dust lanes galaxies at 0.

003 < z < 0.1 is a comprehensive visual inspection of SDSS galaxies to assess the completeness and typical failure modes of CNN-based classifications and to construct homogeneous, visually verified catalogues of galaxies with these morphological features. p. 0
Where the paper says it

1 previously classified by a CNN as merging, irregular and edge-on galaxies as well as galaxies with bar, ring, and dust lane; to assess the completeness and typical failure modes of CNN-based classifications; and to construct homogeneous, visually verified catalogues of galaxies with these morphological features. An additional goal is to determine the type of nuclear activity via BPT diagrams for most galaxies in these morphologically distinct subsamples and to identify rare systems revealed during the inspection.

Pruning redundant reasoning tokens

The aim of this work is to perform a comprehensive visual inspection of SDSS galaxies at 0.02 < z < 0.1 previously classified by a CNN as merging, irregular and edge-on galaxies as well as galaxies with bar, ring, and dust lane. p. 0

Where the paper says it

02 < z < 0. 1 previously classified by a CNN as merging, irregular and edge-on galaxies as well as galaxies with bar, ring, and dust lane; to assess the completeness and typical failure modes of CNN-based classifications; and to construct homogeneous, visually verified catalogues of galaxies with these morphological features.

The study sought to assess the completeness and typical failure modes of CNN-based classifications while constructing homogeneous, visually verified catalogues of these galaxies. p. 0
Where the paper says it

02 < z < 0. 1 previously classified by a CNN as merging, irregular and edge-on galaxies as well as galaxies with bar, ring, and dust lane; to assess the completeness and typical failure modes of CNN-based classifications; and to construct homogeneous, visually verified catalogues of galaxies with these morphological features.

An additional goal involved determining the type of nuclear activity via BPT diagrams for most galaxies in these morphologically distinct subsamples and identifying rare systems revealed during the inspection. p. 0
Where the paper says it

1 previously classified by a CNN as merging, irregular and edge-on galaxies as well as galaxies with bar, ring, and dust lane; to assess the completeness and typical failure modes of CNN-based classifications; and to construct homogeneous, visually verified catalogues of galaxies with these morphological features. An additional goal is to determine the type of nuclear activity via BPT diagrams for most galaxies in these morphologically distinct subsamples and to identify rare systems revealed during the inspection.

How the training signal is built

The research followed prior work dedicated to machine learning techniques for morphological classification of SDSS galaxies with absolute stellar magnitudes of −24m. Initial binary morphological classification was performed using classical machine learning methods, where Random Forest and Support Vector Machine classifiers achieved accuracies of 92. p. 0

Where the paper says it

(2015) and Masters (2025)). In this content, the photometry-based morphological classification is more developed, where machine learning methods like Random Forest, Support Vector Machine, k-NN, and others already have strong applications.

9% and 94.6%, respectively, for correctly classified galaxies<ref:2604. p. 1
Where the paper says it

The Random Forest and Support Vector Machine classifiers turned out to provide the highest accuracy of 92. 9% of correctly classified (96% for early and 84% for late morphological types) to 94.

24471#pg4>. The image-based approach involved classifying galaxies into five visual morphological types (completely rounded, rounded in-between, cigar-shaped, edgeon, and spiral) and 32 structural features<ref:2604. p. 1
Where the paper says it

Ring, CNNtotal probability 5 − 95. 2 % strong 360 343 17 good 1273 1190 83 thin 512 444 68 PRG 5 5 - no ring 11732 10554 1178 The image-based approach was applied for this catalogue of SDSS galaxies to classify into five visual morphological types (completely rounded, rounded in-between, cigar-shaped, edgeon, and spiral) and 32 structural features (Vavilova et al.

24471#pg4>. The voluntary Galaxy Zoo data (GZ2) was chosen as the training sample for this image-based approach<ref:2604. p. 1
Where the paper says it

The voluntary Galaxy Zoo data (GZ2) (Willett et al. 2013) was chosen as the training sample, consisting of 172,372 galaxies.

24471#pg4>.

Where the gains come from

The CNN model, based on DenseNet-201 with adversarial validation, train-test split, and optimal image transformation for simulation of a decrease in magnitude and size was used to improve human bias for those GZ2 galaxy images that had a poor vote classification<ref:2604.24471#pg4>. This approach showed promising performance, achieving more than 93% accuracy for three classes, except cigar-shaped galaxies (∼ 75%) and completely rounded galaxies (∼ 83%)<ref:2604. p. 2

Where the paper says it

This allowed us to improve the human bias for those GZ2 galaxy images that had a poor vote classification. This approach showed the promising performance of the morphological classification, achieving more than 93% accuracy for three classes, except cigar-shaped galaxies (∼ 75%) and completely rounded galaxies (∼ 83%) (Vavilova et al.

24471#pg4>. The CNN model had an accuracy in the range of 83. p. 2
Where the paper says it

This approach showed the promising performance of the morphological classification, achieving more than 93% accuracy for three classes, except cigar-shaped galaxies (∼ 75%) and completely rounded galaxies (∼ 83%) (Vavilova et al. Regarding the classification of galaxies by their detailed structural and morphological features, our CNN model had accuracy in the range of 83.

3 - 99.4% depending on features and image quality<ref:2604. p. 2
Where the paper says it

4 % depending on features (edgeon, bar, bulge, ring, irregular, merging, number of spiral arms, etc. ) and image quality.

24471#pg4>.

Visual inspection revealed that CNN misclassifications are primarily caused by projection effects, foreground stars, faint tidal features, and irregular star-forming structures. For merging galaxies, errors occurred when bright stars overlapped with galaxies or when a distant galaxy was superimposed over the background of a spiral arm<ref:2604. p. 2

Where the paper says it

Results and Discussion 3. Merging galaxies The most common errors, which occurred when CNN categorised these galaxies as merging, are as follows: 1) when the bright stars of our Galaxy overlap with galaxies, which is considered Figure 2 (a); 2) when a distant galaxy is superimposed over the background of a spiral arm, making the silhouette resemble merging galaxies Figure 2 (b); 3) spiral galaxies with arm’s shape like those in Figure 2 (b).

24471#pg4>. In edge-on galaxies, errors included irregular galaxies and merging galaxies forming a long silhouette that is easy to confuse with edge-on ones<ref:2604. p. 3
Where the paper says it

3% < CNN < 98. Among them, 68 are the irregular galaxies, which have an elongated shape; 66 are elliptical with a flattened shape; 22 are spiral galaxies with a shape between edgeon and face-on; 10 merging galaxies that form a long silhouette, which is easy to confuse with edge-on galaxies; 8 galaxies are no edge-on; 3 galaxies with artifacts of observation; and one galaxy has the polar ring presented in the catalogue by Moiseev et al.

24471#pg4>.

The visual inspection confirmed that all of the 9,372 galaxies marked as irregular by the CNN were indeed irregular, with 6,357 newly described systems<ref:2604.24471#pg4>. For galaxies with dust lanes, only 588 were initially marked by the CNN, and most of these had a probability of 5% for having a dust lane by CNN<ref:2604. p. 3

Where the paper says it

Results and Discussion 4. Galaxies with dust lane CNN marked 588 galaxies with dust lanes having probabilities 5% < CNN < 85, 59%.

24471#pg5>. The presence of dust lanes is also noted as a probe of disc stability and gas dynamics<ref:2604. p. 3
Where the paper says it

Distribution of apparent magnitude in the r-band of SDSS after visual inspection for dust lane galaxies, which you can see in the left histogram of Figure 3. Therefore, identifying dust lanes is not only a morphological task but also a probe of disc stability and gas dynamics.

24471#pg6>.

The analysis of available spectra for galaxies with ring, bar, dust lane, and edge-on galaxies revealed systematic differences in the relative weights of LINER-like and composite types across all four morphological subsamples. For ring galaxies, 1075 galaxies (53%) were classified as LINERs, suggesting a predominance of weak AGN activity or shocks. p. 6

Where the paper says it

Applying the aforementioned criteria, we obtained the following distribution for galaxies with ring (Figure 8): – 1075 galaxies (53%) are classified as LINERs, – 561 galaxies (27%) are classified as composites, – 218 galaxies (11%) are classified as Seyferts, – 183 galaxies (9%) are classified as star-forming galaxies. 8: The BPT diagram for galaxies with ring based on SDSS spectra This distribution indicates that most galaxies with rings in our catalog are dominated by low-ionization nuclear emission line (LINER) regions, suggesting either a predominance of weak AGN activity or the presence of shocks.

Similarly, for barred-galaxy subsamples, 333 galaxies (43%) were classified as LINERs. p. 6
Where the paper says it

Galaxies with bars. For the barred-galaxy subsample with available spectra in SDSS DR17 (N = 774), the application of the above criteria yields the following distribution of spectral classes (Figure 9): – 333 galaxies (43%) are classified as LINERs, – 229 galaxies (30%) are classified as composites galaxies, – 140 galaxies (18%) are classified as Seyfert, – 72 galaxies (9%) are classified as star-forming galaxies.

The resulting homogeneous and visually verified datasets improve the robustness of morphological studies and provide valuable training samples for future machine learning models. These catalogues serve as valuable benchmarks for subsequent astrophysical analyses and reliable, accurate datasets for future CNN training. p. 9

Where the paper says it

This information will be added into the relevant catalogues. Generally, these catalogues will serve as valuable benchmarks for subsequent astrophysical analyses and, importantly, as reliable, accurate datasets for future CNN training, thereby contributing to the gradual improvement of automated galaxy classification methods.

The work also identified five strong candidates for polar ring galaxies by visual inspection. p. 9
Where the paper says it

1: irregular, edgeon, and merging galaxies as well as galaxies with bar, dust lane, and ring. We discovered five strong candidates for galaxies with polar ring by visual inspection: SDSS J084058.

For the first time, a spectral type of nuclear activity was defined for most studied SDSS galaxies at z<0. p. 0
Where the paper says it

CNN misclassifications are primarily caused by projection effects, foreground stars, faint tidal features, and irregular star-forming structures. For the first time, we defined a spectral type of nuclear activity for most of studied SDSS galaxies at z<0.

1, namely for edge-on galaxies and galaxies with ring, bar, and dust lane. p. 0
Where the paper says it

For the first time, we defined a spectral type of nuclear activity for most of studied SDSS galaxies at z<0. 1, namely for edge-on galaxies and galaxies with ring, bar, and dust lane.

The catalogues will serve as valuable benchmarks for subsequent astrophysical analyses and reliable, accurate datasets for future CNN training. p. 9
Where the paper says it

This information will be added into the relevant catalogues. Generally, these catalogues will serve as valuable benchmarks for subsequent astrophysical analyses and, importantly, as reliable, accurate datasets for future CNN training, thereby contributing to the gradual improvement of automated galaxy classification methods.

Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.

Improvements for AI systems

  1. Improved AI system can perform visual validation by cross-matching CNN classifications with Galaxy Zoo 2 to refine results, addressing CNN misclassifications are primarily caused by projection effects, foreground stars, faint tidal features, and irregular star-forming structures.

  2. The improved system can define a spectral type of nuclear activity for most studied SDSS galaxies at z<0.1 for edge-on galaxies and galaxies with ring, bar, and dust lane subsamples to add this information to relevant catalogs.

  3. The system can systematically assess the completeness and typical failure modes of CNN-based classifications by performing comprehensive visual inspections on specific morphological features like merging, irregular, edge-on, bar, ring, and dust lane galaxies independently of CNN probability values.

  4. The improved system will enhance the robustness of morphological studies by constructing homogeneous and visually verified catalogues for various morphological features including merging galaxies (612), irregular galaxies (9372), edge-on galaxies (16822), bar galaxies (811), ringed galaxies (2150), and dust lane galaxies (575).

  5. The system can identify rare systems revealed during the inspection, such as five strong candidates for polar ring galaxies, by systematically inspecting all CNN-classified ringed or irregular systems.

  6. The system can provide a foundation for future machine learning models by generating highly verified catalogues of SDSS galaxies at z<0.1, which will serve as reliable training samples to contribute to the gradual improvement of automated galaxy classification methods.

Abstract

Convolutional neural networks (CNNs) classify galaxy morphology efficiently in large surveys, but complex features remain affected by projection effects, image artefacts, and intrinsic ambiguities, so expert visual validation is essential for reliable catalogues. We apply a CNN-assisted expert validation framework to SDSS galaxies at 0.003 < z < 0.1 previously classified by a CNN as merging, irregular, edge-on, barred, ringed, and dust-lane systems. We visually inspected all CNN-selected candidates in four categories - merging (2574), irregular (9432), ringed (13882), and dust-lane (588) - over their full catalogue feature-score range; for edge-on and barred galaxies we inspected the 17000 and 4323 highest-scoring candidates from larger CNN catalogues. Galaxies outside the Galaxy Zoo 2 (GZ2) selection domain, which carry no GZ2 label, were classified here. For the subset with SDSS spectroscopy we applied the BPT and WHAN diagnostics to MPA-JHU emission-line measurements. The verified catalogues contain 612 merging, 9372 irregular, 16822 edge-on, 811 barred, 2145 ringed, and 575 dust-lane galaxies. Comparison with GZ2 shows that this validation both refines existing classifications and extends reliable catalogues beyond the effective Galaxy Zoo selection domain. CNN misclassification is driven mainly by projection effects, foreground stars, faint tidal structures, and intrinsically ambiguous morphologies. Emission-line diagnostics show that 87.8% of the ringed galaxies with LINER-like line ratios have H-alpha equivalent widths consistent with ionisation by evolved stars rather than by an active nucleus. We also identify five strong new candidates for polar-ring galaxies. The catalogues provide benchmark samples for studies of galaxy morphology, secular evolution and nuclear activity, and for future machine-learning applications.

Sources

Related papers