{"id":"W4401043857","doi":"10.1016/j.gsd.2024.101296","title":"A meta-ensemble machine learning strategy to assess groundwater holistic vulnerability in coastal aquifers","year":2024,"lang":"en","type":"article","venue":"Groundwater for Sustainable Development","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Aquifer; Groundwater; Vulnerability (computing); Environmental science; Water resource management; Hydrology (agriculture); Petroleum engineering; Geology; Computer science; 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":[0.002156846,0.000751697,0.001035322,0.001357109,0.0005500168,0.0008835248,0.001181127,0.001005497,0.001286492],"category_scores_gemma":[0.003968828,0.0003381913,0.000987463,0.001005381,0.0003459512,0.001392753,0.0009539688,0.0007769724,0.0001755972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006448298,"about_ca_system_score_gemma":0.0008666822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007913855,"about_ca_topic_score_gemma":0.007996028,"domain_scores_codex":[0.9995794,0.0001769447,0.00002980681,0.00008317934,0.00006943528,0.00006119688],"domain_scores_gemma":[0.998458,0.0008169336,0.0001087012,0.0001533603,0.000393919,0.00006908494],"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":[0.0000720875,0.00007104044,0.005228771,0.00001834358,0.0002555475,0.00003727181,0.00003256097,0.937768,0.0007510314,0.002430578,0.0007955549,0.05253913],"study_design_scores_gemma":[0.000001710927,0.00001147998,0.0002656095,0.000001723856,0.00001256225,0.00000328643,0.000005397066,0.9986494,0.0001033126,0.0009051543,0.00003823031,0.000002259637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3121696,0.0005137178,0.6815546,0.0007319885,0.00009800036,0.00006905986,0.0004051127,0.0005434201,0.003914556],"genre_scores_gemma":[0.9530564,0.00008128524,0.04539994,0.00008983463,0.00004760246,0.00005888359,0.0002685468,0.00002509366,0.000972415],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007913855,"threshold_uncertainty_score":0.01573557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09444486748809207,"score_gpt":0.3014054524312475,"score_spread":0.2069605849431554,"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."}}