{"id":"W4404878833","doi":"10.1016/j.envc.2024.101056","title":"Robust prediction of chlorophyll-A from nitrogen and phosphorus content in Philippine and global lakes using fine-tuned, explainable machine learning","year":2024,"lang":"en","type":"article","venue":"Environmental Challenges","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Philippine Council for Industry, Energy, and Emerging Technology Research and Development; Department of Science and Technology, Philippines; University of the Philippines","keywords":"Phosphorus; Nitrogen; Chlorophyll a; Content (measure theory); Computer science; Environmental science; Artificial intelligence; Mathematics; Chemistry; Materials science; Metallurgy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002044984,0.0002006266,0.0002264933,0.00002860113,0.00008823041,0.00002328407,0.00008211852,0.0001029968,0.0004957443],"category_scores_gemma":[0.00002263815,0.0001813244,0.00003500285,0.00007148468,0.0003284958,0.0001583693,0.0002923171,0.0001982326,0.00001622463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002336739,"about_ca_system_score_gemma":0.000002536644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001043181,"about_ca_topic_score_gemma":0.0001199088,"domain_scores_codex":[0.9986991,0.00006566726,0.0002474667,0.0005039152,0.0002312842,0.0002525849],"domain_scores_gemma":[0.9996825,0.00005855874,0.00005458427,0.0001142616,7.103987e-7,0.00008933684],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002324082,0.000442162,0.6966569,0.0001287317,0.0001100086,0.0002067838,0.003443334,0.1240059,0.07191832,0.00008586081,0.00001434002,0.1027552],"study_design_scores_gemma":[0.002203021,0.001308677,0.4302321,0.0004778751,0.0001506851,0.0001898675,0.00180032,0.5466478,0.006851196,0.004018487,0.005290316,0.0008295594],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9731972,0.02581611,0.00004579308,0.0002065196,0.00006299486,0.0001537326,0.0001093169,0.00004913312,0.0003592027],"genre_scores_gemma":[0.9960037,0.003044842,0.0007948745,0.00001848639,0.00003001113,0.00000853642,0.00002677596,0.0000181341,0.00005466052],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.422642,"threshold_uncertainty_score":0.7394195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05659747086337839,"score_gpt":0.2134944495560926,"score_spread":0.1568969786927142,"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."}}