{"id":"W4379537355","doi":"10.1080/07038992.2023.2215333","title":"Comparative Analysis of Empirical and Machine Learning Models for Chl <i>a</i> Extraction Using Sentinel-2 and Landsat OLI Data: Opportunities, Limitations, and Challenges","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Marine and coastal ecosystems","field":"Earth and Planetary Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; Water Security Agency; University of Regina; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Geological Survey; Canada First Research Excellence Fund; National Aeronautics and Space Administration; Canada Research Chairs; Global Institute for Water Security, University of Saskatchewan; Global Water Futures; University of Regina; Canada Foundation for Innovation","keywords":"Remote sensing; Atmospheric correction; Environmental science; Support vector machine; Empirical modelling; Chlorophyll a; Earth observation; Satellite; Computer science; Geography; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004994062,0.00007535171,0.0002851225,0.0004522089,0.0001702584,0.00005937929,0.00003755138,0.0000352635,0.000003204896],"category_scores_gemma":[0.0000578387,0.00006798553,0.00002741953,0.0002071713,0.00004845048,0.0002841188,0.000009268594,0.0001008881,8.080543e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004503601,"about_ca_system_score_gemma":0.0001393244,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01737184,"about_ca_topic_score_gemma":0.2909759,"domain_scores_codex":[0.9993455,0.00007269949,0.0002357659,0.0001202462,0.00008545117,0.0001403419],"domain_scores_gemma":[0.9991593,0.0002513292,0.0001956156,0.00006519198,0.00009283976,0.0002357709],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006562438,0.000002464467,0.04050485,0.0001961441,0.000689602,0.0001646602,0.004215642,0.02462612,0.00005851953,0.00001951551,0.0001890191,0.9292678],"study_design_scores_gemma":[0.0001483833,0.00004117337,0.01374736,0.00004817126,0.0002436151,0.0001994166,0.003499563,0.9745088,0.000003799184,0.0001004062,0.007389736,0.00006956587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9882798,0.006417869,0.003677464,0.000807507,0.00008070942,0.00006571611,0.0001241241,0.000004272561,0.0005425597],"genre_scores_gemma":[0.9933146,0.003692069,0.002731094,0.00003340612,0.00005536973,3.095797e-9,0.0001393174,0.000002594816,0.00003150825],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9498827,"threshold_uncertainty_score":0.9891716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3895752542072285,"score_gpt":0.3135454720213864,"score_spread":0.07602978218584217,"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."}}