{"id":"W2948344543","doi":"10.3390/geosciences9060254","title":"A Spatially Explicit Comparison of Quantitative and Categorical Modelling Approaches for Mapping Seabed Sediments Using Random Forest","year":2019,"lang":"en","type":"article","venue":"Geosciences","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan; Nova Scotia Community College; Memorial University of Newfoundland","funders":"ArcticNet; Government of Nunavut","keywords":"Categorical variable; Random forest; Seabed; Computer science; Sediment; Environmental science; Principal component analysis; Artificial intelligence; Machine learning; Geology; Oceanography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.005487182,0.0006623461,0.0004447041,0.00120632,0.0003197714,0.001003641,0.001093936,0.000517769,0.0005268915],"category_scores_gemma":[0.01023359,0.0003113199,0.000806884,0.0009258528,0.0003478223,0.001359379,0.0007344983,0.000494677,0.0001875655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007924602,"about_ca_system_score_gemma":0.0008581026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0198671,"about_ca_topic_score_gemma":0.0236428,"domain_scores_codex":[0.998316,0.0009696068,0.00008036196,0.0002352388,0.0003180715,0.00008062933],"domain_scores_gemma":[0.9936382,0.00395336,0.0003911011,0.0006979362,0.001231942,0.00008743556],"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":[0.0005615441,0.0001813396,0.02647209,0.0001467624,0.0002275591,0.00005866583,0.0002257348,0.8697926,0.005471047,0.002721323,0.0003623778,0.093779],"study_design_scores_gemma":[0.00001435935,0.00009742199,0.007325002,0.00001864191,0.00003245172,0.00003262969,0.0000622141,0.9897156,0.001430762,0.0009768895,0.0002526756,0.00004129161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5162132,0.000249732,0.4784083,0.0002084955,0.00003596274,0.0001056207,0.00057061,0.001403305,0.0028047],"genre_scores_gemma":[0.855548,0.000084923,0.1433699,0.00002423495,0.000006966863,0.00007170026,0.0004467162,0.00007035699,0.0003772114],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0198671,"threshold_uncertainty_score":0.03950292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1240170867072604,"score_gpt":0.2979414200993281,"score_spread":0.1739243333920677,"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."}}