{"id":"W4387735350","doi":"10.1109/ic3ina60834.2023.10285812","title":"Harmful Algal Blooms Prediction Model: Dealing With Limited Datasets","year":2023,"lang":"en","type":"article","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Transfer of learning; Computer science; Buoy; Process (computing); Artificial intelligence; Machine learning; Data modeling; Algal bloom; Artificial neural network; Water quality; Deep learning; Data mining; Ecology; Engineering","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001808807,0.0001018454,0.00007858915,0.00002929119,0.0001441046,0.0000277464,0.0001486667,0.0000534827,0.0009618382],"category_scores_gemma":[0.00004388695,0.00007215548,0.000017865,0.000341948,0.0001054025,0.000149402,0.0001740305,0.0001071683,0.001317575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003919698,"about_ca_system_score_gemma":0.000003416921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001833567,"about_ca_topic_score_gemma":0.00005122906,"domain_scores_codex":[0.9989772,0.00001751605,0.000124221,0.0003162062,0.0002849061,0.0002798817],"domain_scores_gemma":[0.9996158,0.00003096426,0.00003120983,0.0002167227,0.000003251339,0.0001019931],"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":[0.00001994873,0.00002512511,0.007229931,0.000001915373,0.000006501929,0.00002037435,0.00006566066,0.9774807,0.004120477,0.00006382408,0.008717109,0.002248449],"study_design_scores_gemma":[0.0001776491,0.00009027126,0.00376507,0.000007433089,0.00001183156,0.00001221979,0.000007021916,0.9929216,0.0007506795,0.0003021861,0.001851186,0.0001028618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9842163,0.000001045625,0.007693804,0.0004054994,0.00003880071,0.0001101545,0.00008703094,0.0006950579,0.006752329],"genre_scores_gemma":[0.9914469,0.000003310067,0.007309692,0.0003399922,0.00002013829,0.000008378584,0.0002899583,0.0000153998,0.0005662074],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01544091,"threshold_uncertainty_score":0.9999514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02794505423156136,"score_gpt":0.240157906524908,"score_spread":0.2122128522933466,"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."}}