Deep Learning Models Achieve ~90% Accuracy in Galaxy Classification Task
Researchers tested two deep learning architectures, ResNet101 and InceptionV4, on the Galaxy10 DECals dataset and achieved approximately 90% accuracy in classifying galaxies into ten morphological categories. The study used a spatially augmented version of the dataset and found ResNet101 to be the superior performer across key metrics. The findings suggest both architectures could serve as reliable foundations for automated galaxy classification pipelines ahead of upcoming large-scale astronomical surveys.
A study published in the Proceedings of the 42nd Samahang Pisika ng Pilipinas Physics Conference (SPP 2024) evaluated the performance of ResNet101 and InceptionV4 convolutional neural networks (CNNs) on a spatially augmented Galaxy10 DECals dataset for ten-class galaxy morphology classification. Both architectures achieved accuracies of approximately 90%, consistent with results previously reported in the literature. ResNet101 outperformed InceptionV4 across performance metrics, though both were deemed sufficiently robust for practical use. The researchers modified the image count per class in the dataset as part of their augmentation strategy, aiming to address class imbalance or data scarcity issues common in astronomical imaging tasks. The work is motivated by the anticipated growth in galactic image data from upcoming surveys, underscoring the need for computationally efficient deep learning solutions. The authors highlight the architectural advantages of residual connections and parallelized inception modules, which allow deeper networks without proportionally increasing computational cost.
What's missing
The paper does not detail the specific class distribution before and after augmentation, making it difficult to assess whether class imbalance was fully addressed. It is also unclear how the models were validated against out-of-distribution data from surveys beyond Galaxy10 DECals, which limits generalizability claims. The study does not report training time or hardware requirements, which are relevant to the cost-effectiveness argument. As a short conference proceedings paper (4 pages), deeper ablation studies and uncertainty quantification are absent.
What different sources said
- arXiv astro-phCenter
Classifying galaxies in the Galaxy10 DECals dataset using Inception and Residual CNNs
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.