{"id":"W4395676539","doi":"10.2166/ws.2024.092","title":"Hybrid modeling of karstic springs: Error correction of conceptual reservoir models with machine learning","year":2024,"lang":"en","type":"article","venue":"Water Science & Technology Water Supply","topic":"Karst Systems and Hydrogeology","field":"Earth and Planetary Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Agence Nationale de la Recherche","keywords":"Karst; Conceptual model; Hydrology (agriculture); Computer science; Geology; Artificial intelligence; Environmental science; Machine learning; Geotechnical 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001104871,0.0005014901,0.0005437816,0.0004135287,0.0003231699,0.0008283557,0.0009865344,0.0006361,0.0006431877],"category_scores_gemma":[0.002205049,0.0003331971,0.0006360685,0.0004497395,0.0004485875,0.0009115973,0.0006147634,0.0006858096,0.00008604191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007925455,"about_ca_system_score_gemma":0.0008741103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02306249,"about_ca_topic_score_gemma":0.01425379,"domain_scores_codex":[0.9997011,0.0001301689,0.00002026183,0.00005960703,0.00005044778,0.00003838231],"domain_scores_gemma":[0.9988662,0.0006953595,0.0001281504,0.00007744031,0.0001911639,0.00004184242],"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":[0.00001345364,0.00001174824,0.0007128133,0.000005246223,0.00001038614,0.000007835882,0.000006570086,0.9962979,0.0001879918,0.000281126,0.00002902401,0.002435856],"study_design_scores_gemma":[0.000001239414,0.000004906233,0.00008512658,7.133569e-7,0.000001054173,8.206226e-7,0.000001279191,0.9997236,0.00006218427,0.0001007833,0.00001680602,0.000001411889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5985937,0.0002874247,0.3962638,0.000375863,0.00007637648,0.00007088091,0.0002153109,0.0006241957,0.003492518],"genre_scores_gemma":[0.9888099,0.00003041451,0.01069359,0.00001721689,0.000008267334,0.00002141831,0.00004175224,0.00001126996,0.0003662696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02306249,"threshold_uncertainty_score":0.04585654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01396783536508814,"score_gpt":0.2044343913365723,"score_spread":0.1904665559714842,"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."}}