{"id":"W6959540597","doi":"10.1109/jstars.2025.3590461","title":"Chlorophyll-a Prediction Based on Machine Learning and Satellite Data in the South Sea of Korea","year":2025,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Marine and coastal ecosystems","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Gradient boosting; Algal bloom; Satellite; Ensemble learning; Random forest; Boosting (machine learning); Scalability; Satellite imagery; Scope (computer science)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008830943,0.0006865489,0.0004391751,0.0007659285,0.0002016424,0.0004634086,0.0003707367,0.0004581517,0.0002745094],"category_scores_gemma":[0.0011194,0.0002488687,0.0007734789,0.0007534641,0.0001826713,0.0007684098,0.0003589593,0.0003523971,0.0001497224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006265127,"about_ca_system_score_gemma":0.0006714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04920042,"about_ca_topic_score_gemma":0.02979706,"domain_scores_codex":[0.9998191,0.00004471322,0.00001728365,0.00006113094,0.00002867355,0.00002911637],"domain_scores_gemma":[0.9995527,0.0001716072,0.00006417232,0.000042162,0.0001291397,0.00004019545],"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":[0.0003221541,0.0003070374,0.1783269,0.00008430833,0.0002056123,0.0003351458,0.00009474648,0.755707,0.007190586,0.0002024897,0.001094552,0.05612953],"study_design_scores_gemma":[0.000007781232,0.00002307381,0.02337845,0.000003758942,0.00001819295,0.000008449984,0.00003528033,0.9756918,0.0006849167,0.00005954173,0.00007855079,0.00001021675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9973424,0.00009398543,0.001986091,0.00007612159,0.00001002835,0.000006981543,0.0001697744,0.00008997965,0.0002247192],"genre_scores_gemma":[0.9965827,0.00006987309,0.002526747,0.00002124655,0.000004539343,0.000007337341,0.0005909838,0.00000855598,0.0001881178],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04920042,"threshold_uncertainty_score":0.09782809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02190394040972021,"score_gpt":0.2178082635506563,"score_spread":0.1959043231409361,"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."}}