{"id":"W4408431097","doi":"10.5194/egusphere-egu25-13338","title":"Enhancing Soil Moisture Prediction with Data-Driven Models: A Global Perspective","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Soil and Unsaturated Flow","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nickel Institute","funders":"","keywords":"Perspective (graphical); Environmental science; Water content; Predictive modelling; Soil science; Econometrics; Computer science; Climatology; Mathematics; Geology; Machine learning; Artificial intelligence; 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":[0.0008163078,0.0008359482,0.0006201161,0.0004481751,0.0001793314,0.0009597369,0.0008953162,0.0007475406,0.0007132419],"category_scores_gemma":[0.001859376,0.0003363166,0.0006357448,0.0007354652,0.0003996855,0.001988624,0.0009541643,0.0008882365,0.0001807137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004792554,"about_ca_system_score_gemma":0.0006111577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01150629,"about_ca_topic_score_gemma":0.01082426,"domain_scores_codex":[0.9998446,0.00005224792,0.000007796236,0.00005075501,0.00002881909,0.00001577983],"domain_scores_gemma":[0.9995416,0.0001890838,0.00005443448,0.00008069822,0.0001013803,0.00003271283],"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":[0.00001727777,0.00002780129,0.004005586,0.00003407514,0.00005516081,0.00002944793,0.00001527324,0.9744095,0.001035605,0.001644895,0.0006480639,0.01807726],"study_design_scores_gemma":[0.000003414227,0.000007907549,0.000483897,0.000005993864,0.000007376933,0.00000344919,0.000007610695,0.9971635,0.0003170329,0.001364117,0.0006307765,0.000004989008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2638046,0.002450746,0.7144127,0.006287911,0.0003499851,0.00007023694,0.002779127,0.002619544,0.007225183],"genre_scores_gemma":[0.9312264,0.001093384,0.06460433,0.0003172708,0.0001571532,0.00005324702,0.00156666,0.0001511302,0.0008304596],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01150629,"threshold_uncertainty_score":0.02287865,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01945813897745125,"score_gpt":0.2423523618366419,"score_spread":0.2228942228591906,"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."}}