- Pathi, Imdad Mahmud
- Soo, John Y. H.
- Wee, Mao Jie
- Zakaria, Sazatul Nadhilah
- Ismail, Nur Azwin
- Baugh, Carlton M.
- Manzoni, Giorgio
- Gaztañaga, Enrique
- Castander, Francisco J.
- Eriksen, Martin Borstad
- Carretero, Jorge
- Fernández, Enrique
- García-Bellido, Juan
- Miquel, Ramon
- Padilla, Cristóbal
- Renard, Pablo
- Sánchez, Eusebio
- Sevilla-Noarbe, I.
- Tallada-Crespí, Pau
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 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 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 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., IMP would like to thank Joseph Ooi Boon Han and Yoon Tiem Leong, for the fruitful discussions. JYHS acknowledges financial support via the Fundamental Research Grant Scheme(FRGS) by the Malaysian Ministry of Higher Education with code FRGS/1/2023/STG07/USM/02/14. JYHS and IMP acknowledge financial support from the Short Term Grant by Universiti Sains Malaysia with code 304/PFIZIK/6315395. IMP also acknowledges financial assistance under the Gra-Assist 2020 scheme provided by the Institute of Postgraduate Studies (IPS), Universiti Sains Malaysia. CMB acknowledges support from the Science Technology Facilities Council through ST/X001075/1. GM is supported by the Collaborative Research Fund under Grant No. C6017-20G which is issued by the Research Grants Council of Hong Kong S.A.R. EG acknowledges grants from Spain Plan Nacional (PGC2018-102021-B-100) and Maria de Maeztu (CEX2020-001058-M). FJC acknowledges grants from Spain Plan Nacional (PID2022-141079NB-C31) and Maria de Maeztu (CEX2020-001058-M). JC acknowledges support from the grant PID2021-123012NA-C44 funded by MCIN/AEI/ 10.13039/501100011033 and by “ERDF A way of making Europe”.
CP acknowledges support from the Spanish Plan Nacional project PID2021-123012NBC41. JGB acknowledges grants from Spain Plan Nacional (PID2021-123012NB-C43) and Centro de Excelencia Severo Ochoa (CEX2020-001007-S). RM acknowledges support from the Spanish Plan Nacional project PID2021-123012NB-C41. CP acknowledges support from the Spanish Plan Nacional project PID2019-111317GB-C32 and PID2022-141079NB-C32. PR acknowledges the support by the Tsinghua Shui Mu Scholarship, the funding of the National Key R&D Program of China (grant no. 2023YFA1605600), the National Science Foundation of China (grant no. 12073014 and 12350410365), the science research grants from the China Manned Space Project with No. CMS-CSST2021-A05, and the Tsinghua University Initiative Scientific Research Program (No. 20223080023). ES acknowledges grants from Spain Plan Nacional (PID2021-123012NB-C42). ISN acknowledges grants from Spain Plan Nacional (PID2021-123012NB-C42). ME acknowledges funding by MCIN with funding from European Union NextGenerationEU (PRTR-C17.I1) and by Generalitat de Catalunya. Funding for the SDSS-I/II/III has been provided by the Alfred P. Sloan Foundation, the Participating Institutions, the National Science Foundation, the U.S. Department of Energy, the National Aeronautics and Space Administration, the Japanese Monbukagakusho, the Max Planck Society, and the Higher Education Funding Council for England. The SDSS-I/II web site is http://www.sdss.org/, while the SDSS-III web site is http://www.sdss3.org/.
SDSS-I/II/III is managed by the Astrophysical Research Consortium for the Participating Institutions. The Participating Institutions include the American Museum of Natural History, Astrophysical Institute Potsdam, University of Basel, University of Cambridge, Case Western Reserve University, University of Chicago, Drexel University, Fermilab, the Institute for Advanced Study, the Japan Participation Group, Johns Hopkins University, the Joint Institute for Nuclear Astrophysics, the Kavli Institute for Particle Astrophysics and Cosmology, the Korean Scientist Group, the Chinese Academy of Sciences (LAMOST), Los Alamos National Laboratory, the Max-Planck-Institute for Astronomy (MPIA), the Max Planck-Institute for Astrophysics (MPA), New Mexico State University, Ohio State University, University of Pittsburgh, University of Portsmouth, Princeton University, the United States Naval Observatory, the University of Washington, University of Arizona, the Brazilian Participation Group, Brookhaven National Laboratory, Carnegie Mellon University, University of Florida, the French Participation Group, the German Participation Group, Harvard University, the Instituto de Astrofisica de Canarias, the Michigan State/Notre Dame/JINA Participation Group, Lawrence Berkeley National Laboratory, Max Planck Institute for Extraterrestrial Physics, New York University, Pennsylvania State University, the Spanish Participation Group, University of Tokyo, University of Utah, Vanderbilt University, University of Virginia, and Yale University. PAUS is partially supported by the Ministry of Economy and Competitiveness (MINECO, grants CSD2007-00060, AYA2015-71825, ESP2017-89838, PGC2018-094773, PGC2018-102021, SEV-2016-0588, SEV-2016-0597 and MDM-2015-0509). Funding for PAUS has also been provided by Durham University (ERC StG DEGAS259586), ETH Zurich, and Leiden University (ERC StG ADULT279396). The PAU data centre is hosted by the Port d’Informació Cienífica (PIC), maintained through a collaboration of CIEMAT and IFAE, with additional support from Universitat Autónoma de Barcelona and the European Research Development Fund (ERDF). This work has made use of CosmoHub, developed by PIC (maintained by IFAE and CIEMAT) in collaboration with ICE-CSIC. It received funding from the Spanish government (grant EQC2021-007479-P funded by MCIN/AEI/10.13039/501100011033), the EU NextGeneration/PRTR (PRTR-C17.I1), and the Generalitat de Catalunya., With funding from the Spanish government through the "María de Maeztu Unit of Excellence" accreditation (CEX2020-001058-M), With funding from the Spanish government through the "Severo Ochoa Centre of Excelence" accreditation (CEX2020-001007-S), Peer reviewed
Proyecto:
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 / PGC2018-102021-B-I00
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 / CEX2020-001058-M
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 / PID2021-123012NA-C44
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 / PID2021-123012NB-C41
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 / PID2021-123012NB-C43
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 / CEX2020-001007-S
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 / PID2019-111317GB-C32
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 / PID2022-141079NB-C32
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 / PID2021-123012NB-C42
,
MEC / Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 / CSD2007-00060
,
MINECO / Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 / AYA2015-71825-P
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 / ESP2017-89838-C3-1-R
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 / ESP2017-89838-C3-2-R
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 / ESP2017-89838-C3-3-R
,
AEI / Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 / PGC2018-094773-B-C31
,
AEI / PGC2018-094773-B-C32
,
AEI / PGC2018-094773-B-C33
,
MINECO / SEV-2016-0588
,
MINECO / SEV-2016-0597
,
MINECO / MDM-2015-0509