{"id":"W4411066004","doi":"10.1016/j.ecolind.2025.113709","title":"Automatic detection of Cyanobacterial blooms using multi-source optical satellite imagery: method development and application","year":2025,"lang":"en","type":"article","venue":"Ecological Indicators","topic":"Aquatic Ecosystems and Phytoplankton Dynamics","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Satellite imagery; Remote sensing; Environmental science; Satellite; Algal bloom; Computer science; Ecology; Phytoplankton; Geology; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005398617,0.0001227579,0.0002332155,0.00007158792,0.0001382371,0.0000192328,0.0001197139,0.0001565589,0.0001405383],"category_scores_gemma":[0.0000752301,0.0001008436,0.00003350272,0.0003010063,0.0001477967,0.00005604286,0.0001626589,0.0001053953,0.00002950314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001715649,"about_ca_system_score_gemma":0.00002013381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003940361,"about_ca_topic_score_gemma":0.00008731698,"domain_scores_codex":[0.9989038,0.0001009737,0.0003998415,0.0002822388,0.0001300733,0.0001831175],"domain_scores_gemma":[0.9994332,0.0001675969,0.0001828119,0.0001348503,0.000004651266,0.0000769378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002882573,0.000436911,0.3168935,0.0001165094,0.00006724719,0.000003148838,0.0005066842,0.00055285,0.1265092,0.0006756312,0.000003446565,0.5542061],"study_design_scores_gemma":[0.0003786704,0.00005208544,0.789266,0.00002240584,0.00004191306,0.000007716958,0.00008150967,0.1699865,0.03662037,0.000160628,0.003200207,0.0001819143],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7743592,0.0000117432,0.2249379,0.00001303653,0.00006935601,0.0002580251,0.00000139495,0.000032145,0.0003171852],"genre_scores_gemma":[0.9260433,0.000003631077,0.07381633,0.0000409916,0.00001061582,0.00002873579,0.000004165044,0.000005617112,0.00004665217],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5540242,"threshold_uncertainty_score":0.4112283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009319760631264625,"score_gpt":0.2612090463423186,"score_spread":0.251889285711054,"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."}}