Impact of photometric redshifts on the galaxy power spectrum and BAO scale in the LSST survey

Ansari, R.; Choyer, Adeline; Habibi, Farhang; Magneville, C.; Moniez, M.; Plaszczynski, S.; Renault, C.; Ricol, Jean-Stéphane; Souchard, Julien

doi:10.1051/0004-6361/201833732

Cited by 7 publications

(3 citation statements)

References 54 publications

(61 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…QSO, redshifts (e.g. Ball et al 2008;Laurino et al 2011;Brescia et al 2014;D'Isanto & Polsterer 2018;Ansari et al 2019).…”

Section: Comparison With Previous Deep Learning Resultsmentioning

confidence: 99%

QSO photometric redshifts using machine learning and neural networks

Curran,

Moss,

Perrott

2021

Preprint

View full text Add to dashboard Cite

The scientific value of the next generation of large continuum surveys would be greatly increased if the redshifts of the newly detected sources could be rapidly and reliably estimated. Given the observational expense of obtaining spectroscopic redshifts for the large number of new detections expected, there has been substantial recent work on using machine learning techniques to obtain photometric redshifts. Here we compare the accuracy of the predicted photometric redshifts obtained from Deep Learning (DL) with the k-Nearest Neighbour (kNN) and the Decision Tree Regression (DTR) algorithms. We find using a combination of near-infrared, visible and ultraviolet magnitudes, trained upon a sample of SDSS QSOs, that the kNN and DL algorithms produce the best self-validation result with a standard deviation of σ ∆z = 0.24 (σ ∆z(norm) = 0.11). Testing on various sub-samples, we find that the DL algorithm generally has lower values of σ ∆z , in addition to exhibiting a better performance in other measures. Our DL method, which uses an easy to implement off-the-shelf algorithm with no filtering nor removal of outliers, performs similarly to other, more complex, algorithms, resulting in an accuracy of ∆z < 0.1 up to z ∼ 2.5. Applying the DL algorithm trained on our 70 000 strong sample to other independent (radio-selected) datasets, we find σ ∆z 0.36 (σ ∆z(norm) 0.17) over a wide range of radio flux densities. This indicates much potential in using this method to determine photometric redshifts of quasars detected with the Square Kilometre Array.

show abstract

“…QSO, redshifts (e.g. Ball et al 2008;Laurino et al 2011;Brescia et al 2014;D'Isanto & Polsterer 2018;Ansari et al 2019).…”

Section: Comparison With Previous Deep Learning Resultsmentioning

confidence: 99%

QSO photometric redshifts using machine learning and neural networks

Curran,

Moss,

Perrott

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The template-fitting methods, first developped by (Loh & Spillar 1986), have been used for instance in the references (Arnouts et al 1999;Benítez 2000;Feldmann et al 2006;Brammer et al 2008) and recently in (Gorecki et al 2014;Ansari et al 2019). For a given galaxy, the algorithm matches the magnitude distributions in the different filter wide bands (e.g.…”

Section: Introductionmentioning

confidence: 99%

“…The feature based machine learning methods use different types of tools as Decision Trees (DT; Quinlan (1986)), Random Forests (RF; Breiman (2001)), Support Vector Machine (SVM; Boser et al (1992)), k-nearest neighbors (KNN; Altman (1992)) as well as Muti-Perceptron Layers (nicknamed either MLP or ANN; Werbos (1974); Rumelhart et al (1986)). They have been used for instance in the references (Collister & Lahav 2004;Wadadekar 2005;Carrasco Kind & Brunner 2013;Sadeh et al 2016;Beck et al 2016;Ansari et al 2019). These methods use as input for a given galaxy the different magnitudes (or colors) measured in the different filters augmented eventually by other user driven information, and give as output a single photo-z value or a probability density distribution (p.d.f).…”

Section: Introductionmentioning

confidence: 99%

Adversarial training applied to Convolutional Neural Network for photometric redshift predictions

Campagne

2020

Preprint

View full text Add to dashboard Cite

The use of Convolutional Neural Networks (CNN) to estimate the galaxy photometric redshift probability distribution by analysing the images in different wavelength bands has been developed in the recent years thanks to the rapid development of the Machine Learning (ML) ecosystem. Authors have set-up CNN architectures and studied their performances and some sources of systematics using standard methods of training and testing to ensure the generalisation power of their models. So far so good, but one piece was missing : does the model generalisation power is well measured? The present article shows clearly that very small image perturbations can fool the model completely and opens the Pandora's box of adversarial attack. Among the different techniques and scenarios, we have chosen to use the Fast Sign Gradient one-step Method and its Projected Gradient Descent iterative extension as adversarial generator tool kit. However, as unlikely as it may seem these adversarial samples which fool not only a single model, reveal a weakness both of the model and the classical training. A revisited algorithm is shown and applied by injecting a fraction of adversarial samples during the training phase. Numerical experiments have been conducted using a specific CNN model for illustration although our study could be applied to other models -not only CNN ones -and in other contexts -not only redshift measurements -as it deals with the complexity of the boundary decision surface.

show abstract

QSO photometric redshifts using machine learning and neural networks

Curran

Moss

Perrott

2021

Monthly Notices of the Royal Astronomical Society

View full text Add to dashboard Cite

The scientific value of the next generation of large continuum surveys would be greatly increased if the redshifts of the newly detected sources could be rapidly and reliably estimated. Given the observational expense of obtaining spectroscopic redshifts for the large number of new detections expected, there has been substantial recent work on using machine learning techniques to obtain photometric redshifts. Here we compare the accuracy of the predicted photometric redshifts obtained from Deep Learning (DL) with the k-Nearest Neighbour (kNN) and the Decision Tree Regression (DTR) algorithms. We find using a combination of near-infrared, visible and ultraviolet magnitudes, trained upon a sample of SDSS QSOs, that the kNN and DL algorithms produce the best self-validation result with a standard deviation of σΔz = 0.24 (σΔz(norm) = 0.11). Testing on various sub-samples, we find that the DL algorithm generally has lower values of σΔz, in addition to exhibiting a better performance in other measures. Our DL method, which uses an easy to implement off-the-shelf algorithm with no filtering nor removal of outliers, performs similarly to other, more complex, algorithms, resulting in an accuracy of Δz < 0.1 up to z ∼ 2.5. Applying the DL algorithm trained on our 70 000 strong sample to other independent (radio-selected) datasets, we find σΔz ≤ 0.36 (σΔz(norm) ≤ 0.17) over a wide range of radio flux densities. This indicates much potential in using this method to determine photometric redshifts of quasars detected with the Square Kilometre Array.

show abstract

Impact of photometric redshifts on the galaxy power spectrum and BAO scale in the LSST survey

Cited by 7 publications

References 54 publications

QSO photometric redshifts using machine learning and neural networks

QSO photometric redshifts using machine learning and neural networks

Adversarial training applied to Convolutional Neural Network for photometric redshift predictions

QSO photometric redshifts using machine learning and neural networks

Contact Info

Product

Resources

About