{"id":"W4406805189","doi":"10.1038/s41598-025-85605-y","title":"Machine learning to identify environmental drivers of phytoplankton blooms in the Southern Baltic Sea","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Oceanographic and Atmospheric Processes","field":"Earth and Planetary Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Allison University","funders":"Carl von Ossietzky Universität Oldenburg","keywords":"Phytoplankton; Environmental science; Algal bloom; Nutrient; Brackish water; Bloom; Oceanography; Ecosystem; Ecology; Salinity; Marine ecosystem; Biology; Geology","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":[0.001377065,0.0005304423,0.0002843311,0.0006609163,0.0004233356,0.0005917484,0.0004009477,0.0004526659,0.0004676712],"category_scores_gemma":[0.003118275,0.0003718829,0.0005631373,0.0005168627,0.0002643419,0.0005396802,0.0005699407,0.0005261026,0.0001129467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008671737,"about_ca_system_score_gemma":0.0009376813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03693502,"about_ca_topic_score_gemma":0.05679026,"domain_scores_codex":[0.9997476,0.00009152892,0.00003021967,0.00008159031,0.0000176358,0.00003144099],"domain_scores_gemma":[0.9991406,0.0005134126,0.0001062896,0.00007053146,0.0001322423,0.00003693257],"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":[0.0001187533,0.0002537943,0.2273961,0.00006444626,0.0003267596,0.0001932283,0.0002740624,0.6858419,0.003577346,0.0004802272,0.0007754171,0.08069795],"study_design_scores_gemma":[0.0000081787,0.00002786392,0.03953467,0.000007375351,0.00002301736,0.00001474837,0.00005537409,0.959101,0.0005403713,0.0004389984,0.0002410223,0.000007524849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993086,0.000131879,0.005770178,0.0001258754,0.00001383544,0.00001513336,0.0002788357,0.0001132428,0.0004650067],"genre_scores_gemma":[0.994768,0.00003342029,0.003981954,0.00001960137,0.000006238859,0.00001598806,0.0008967048,0.000006550901,0.0002715725],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03693502,"threshold_uncertainty_score":0.07344007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005475497706118999,"score_gpt":0.2092159514689909,"score_spread":0.2037404537628719,"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."}}