{"id":"W4392433399","doi":"10.1016/j.jhydrol.2024.130950","title":"Machine learning facilitates connections between soil thermal conductivity, soil water content, and soil matric potential","year":2024,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Soil and Unsaturated Flow","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"Natural Science Foundation of Shaanxi Province; National Natural Science Foundation of China","keywords":"Mean squared error; Support vector machine; Soil science; Soil water; Machine learning; Water content; Pedotransfer function; Artificial neural network; Thermal conductivity; Artificial intelligence; Soil texture; Computer science; Random forest; Decision tree; Algorithm; Mathematics; Environmental science; Hydraulic conductivity; Materials science; Statistics; Geology; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003306495,0.0001843438,0.0003609011,0.0003031386,0.0001067171,0.00007549524,0.00009888943,0.0001725421,0.0001355005],"category_scores_gemma":[0.00002980635,0.000127212,0.000134505,0.0001076047,0.0000923606,0.0002752513,0.00004138664,0.0009234641,0.00005148792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003333705,"about_ca_system_score_gemma":0.00002043557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006314144,"about_ca_topic_score_gemma":0.00002070574,"domain_scores_codex":[0.9989231,0.0001033302,0.0003823295,0.0001411757,0.0001273046,0.0003227619],"domain_scores_gemma":[0.999572,0.0001430612,0.00004406664,0.00007085479,0.00006260958,0.0001074039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001435432,0.00005543396,0.01512964,0.0002676119,0.001822646,0.0009015943,0.001912632,0.4214965,0.5351724,0.0001004886,0.0008582069,0.02213935],"study_design_scores_gemma":[0.005766455,0.00261059,0.01682793,0.0002037437,0.001643471,0.01108981,0.0007141234,0.7975721,0.1245993,0.00524992,0.03218556,0.001537036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904878,0.00604489,0.000601778,0.001040448,0.001227754,0.0000394943,0.00001607694,0.0001322385,0.0004095116],"genre_scores_gemma":[0.9986274,0.0003345787,0.00002197656,0.00002857781,0.0005498946,0.000001978432,0.00001047091,0.00003217347,0.0003928965],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4105731,"threshold_uncertainty_score":0.5187553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01739251516377356,"score_gpt":0.2158816985321919,"score_spread":0.1984891833684184,"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."}}