{"id":"W3144130411","doi":"10.1093/mnras/stab1513","title":"Benchmarking and scalability of machine-learning methods for photometric redshift estimation","year":2021,"lang":"en","type":"article","venue":"Monthly Notices of the Royal Astronomical Society","topic":"Galaxies: Formation, Evolution, Phenomena","field":"Physics and Astronomy","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Lawrence Berkeley National Laboratory; Brookhaven National Laboratory; European Research Council; All Souls College, University of Oxford; Engineering and Physical Sciences Research Council; York University; National Science Foundation; UK Research and Innovation; Alan Turing Institute; Science and Technology Facilities Council; Carnegie Mellon University; Office of Science; Princeton University; Alfred P. Sloan Foundation; University of Washington; Johns Hopkins University; College of Engineering, Michigan State University; Harvard University; Ohio State University; New Mexico State University; University of Portsmouth; Vanderbilt University; Yale University; University of Arizona; U.S. Department of Energy","keywords":"Random forest; Scalability; Machine learning; Photometric redshift; Benchmarking; Benchmark (surveying); Artificial intelligence; Virtual observatory; Computer science; Algorithm; Artificial neural network; Redshift; Physics; Galaxy; Astrophysics; Database; Astronomy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01452257,0.002304232,0.001436396,0.002975864,0.0008926959,0.002269496,0.004007786,0.002553862,0.001355769],"category_scores_gemma":[0.03236274,0.000550562,0.001385645,0.003173048,0.001334424,0.002759219,0.001674392,0.002338751,0.001101994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002079039,"about_ca_system_score_gemma":0.001979169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01543687,"about_ca_topic_score_gemma":0.006373404,"domain_scores_codex":[0.9885696,0.00454228,0.001053496,0.002047974,0.003054624,0.0007320062],"domain_scores_gemma":[0.974597,0.01421643,0.00126939,0.003847956,0.005392691,0.0006765556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00102085,0.0006791971,0.02230076,0.0007322381,0.0006852064,0.000151448,0.0001773649,0.8124223,0.004440728,0.004195413,0.01356003,0.1396344],"study_design_scores_gemma":[0.00009318132,0.0001420615,0.00491715,0.00006290447,0.0000380549,0.00004932261,0.00006862646,0.9844831,0.004993013,0.002943569,0.002178714,0.00003035029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7566205,0.01736005,0.1797396,0.002893452,0.001810914,0.0007086602,0.005589353,0.01935653,0.01592087],"genre_scores_gemma":[0.8359847,0.0009647999,0.1493931,0.0004095953,0.0002127644,0.0003092395,0.01057756,0.0007610046,0.001387278],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01543687,"threshold_uncertainty_score":0.07680362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00902234362389593,"score_gpt":0.2514044548007442,"score_spread":0.2423821111768483,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}