{"id":"W4313532989","doi":"10.5194/gmd-16-35-2023","title":"Prediction of algal blooms via data-driven machine learning models: an evaluation using data from a well-monitored mesotrophic lake","year":2023,"lang":"en","type":"article","venue":"Geoscientific model development","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"Uppsala Universitet; Vetenskapsrådet; Svenska Forskningsrådet Formas; Norges Forskningsråd; European Commission; Joint Programming Initiative Water challenges for a changing world","keywords":"Algal bloom; Chlorophyll a; Computer science; Bloom; Nutrient; Environmental science; Bathythermograph; Test data; Machine learning; Phytoplankton; Oceanography; Ecology; Chemistry; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003278428,0.0002496277,0.000259406,0.000155205,0.0005701506,0.00009650809,0.001494147,0.0001310337,0.0006089275],"category_scores_gemma":[0.0001365189,0.0002361939,0.00002832746,0.0007550223,0.0002244792,0.001005803,0.00264625,0.0002436728,0.0002790154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002186703,"about_ca_system_score_gemma":0.0001394864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008783686,"about_ca_topic_score_gemma":0.0006964946,"domain_scores_codex":[0.995483,0.0002565664,0.0006358536,0.001490906,0.00162618,0.000507498],"domain_scores_gemma":[0.9978778,0.00004145104,0.0002733244,0.001579593,0.00005088524,0.0001768876],"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":[0.0000196292,0.0001099472,0.00338774,0.000006893913,0.00002335665,0.000003557359,0.0007288143,0.9746496,0.012142,0.000001144814,0.0003723645,0.008554951],"study_design_scores_gemma":[0.0003704333,0.0000253724,0.003930818,0.00003498658,0.00007431626,0.000003039397,0.00002055487,0.9936199,0.0002368116,0.0006294245,0.0008352267,0.000219141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8687657,0.00001877778,0.1290243,0.00002633881,0.0004710326,0.0003681442,0.000966705,0.0002105009,0.0001485703],"genre_scores_gemma":[0.9135456,0.000008065993,0.06554696,0.0000159649,0.00004145074,0.00001709473,0.02049376,0.00003151959,0.0002995962],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0634773,"threshold_uncertainty_score":0.9631706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2868802441038442,"score_gpt":0.3066335108431824,"score_spread":0.01975326673933819,"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."}}