Sazatul Nadhilah Zakaria

arXiv2026

Exploring the Viability of Fisher Discriminants in Galaxy Morphology Classification

One of the major challenges in astronomy involves accurately classifying galaxies, particularly distinguishing between different galaxy types. While many complex algorithms have shown strong performance in classification tasks, their complexity often results in longer processing times and increased difficulty in understanding. This study addresses this issue by exploring the viability of Fisher discriminants, a much simpler algorithm, in performing galaxy morphology classification. We tested four machine learning algorithms: the Fisher discriminant, Artificial Neural Networks (ANNs), Boosted Decision Trees (BDTs), and k-Nearest Neighbours (kNNs) to classify galaxies by the shape of their central bulges. Using data from the Sloan Digital Sky Survey (SDSS), we utilised five pre-processing transformations: normalisation, decorrelation, principal component analysis (PCA), uniformisation, and Gaussianisation, and classified the shape of central bulge into either rounded or no-bulge, based on the Galaxy Zoo Decision Tree. When compared to the Galaxy Zoo 2 (GZ2) labels, the Fisher discriminant with uniformisation obtained the highest accuracy score of 0.9310, outperforming ANN, BDT, and kNN by 1.93%, 0.42%, and 3.08%, respectively.

astro-ph.IM↗

arXiv2024

ANNZ+: an enhanced photometric redshift estimation algorithm with applications on the PAU Survey

ANNZ is a fast and simple algorithm which utilises artificial neural networks (ANNs), it was known as one of the pioneers of machine learning approaches to photometric redshift estimation decades ago. We enhanced the algorithm by introducing new activation functions like tanh, softplus, SiLU, Mish and ReLU variants; its new performance is then vigorously tested on legacy samples like the Luminous Red Galaxy (LRG) and Stripe-82 samples from SDSS, as well as modern galaxy samples like the Physics of the Accelerating Universe Survey (PAUS). This work focuses on testing the robustness of activation functions with respect to the choice of ANN architectures, particularly on its depth and width, in the context of galaxy photometric redshift estimation. Our upgraded algorithm, which we named ANNZ+, shows that the tanh and Leaky ReLU activation functions provide more consistent and stable results across deeper and wider architectures with > 1 per cent improvement in root-mean-square error ($σ_{\textrm{RMS}}$) and 68th percentile error ($σ_{68}$) when tested on SDSS data sets. While assessing its capabilities in handling high dimensional inputs, we achieved an improvement of 11 per cent in $σ_{\textrm{RMS}}$ and 6 per cent in $σ_{68}$ with the tanh activation function when tested on the 40-narrowband PAUS dataset; it even outperformed ANNZ2, its supposed successor, by 44 per cent in $σ_{\textrm{RMS}}$. This justifies the effort to upgrade the 20-year-old ANNZ, allowing it to remain viable and competitive within the photo-z community today. The updated algorithm ANNZ+ is publicly available at https://github.com/imdadmpt/ANNzPlus.

astro-ph.IM↗