{"id":"W3200802708","doi":"10.1109/jstars.2021.3112623","title":"Spatial Gap-Filling of SMAP Soil Moisture Pixels Over Tibetan Plateau via Machine Learning Versus Geostatistics","year":2021,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Soil Moisture and Remote Sensing","field":"Environmental Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Environmental science; Geostatistics; Water content; Brightness temperature; Mean squared error; Remote sensing; Plateau (mathematics); Moisture; Soil science; Satellite; Kriging; Spatial variability; Atmospheric sciences; Brightness; Meteorology; Mathematics; Geology; Computer science; Machine learning; Geography; Statistics","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":[0.0003095077,0.0001892188,0.0003747473,0.0001021801,0.0001989197,0.00004448609,0.00007389559,0.0001701111,0.00001607406],"category_scores_gemma":[0.0001863419,0.0001749082,0.00006199128,0.0006118696,0.0001124855,0.00008174742,0.00004907716,0.0007515615,0.000001200072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000945763,"about_ca_system_score_gemma":0.00008827885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001467968,"about_ca_topic_score_gemma":0.01169756,"domain_scores_codex":[0.9983252,0.00008877015,0.0006440539,0.0002238101,0.0004469556,0.0002712665],"domain_scores_gemma":[0.9989511,0.0001986722,0.0004397147,0.0001425823,0.0001739093,0.00009404837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002186222,0.00006672076,0.01095189,0.00006224235,0.0001279335,0.0002298566,0.001475914,0.04920525,0.3507445,0.00005732986,0.0000548128,0.586805],"study_design_scores_gemma":[0.004311371,0.0002794382,0.5128542,0.000441268,0.0002495838,0.0005174796,0.000430728,0.3970414,0.07516536,0.002691098,0.00529481,0.0007232296],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9472029,0.0001982232,0.04938922,0.0002090926,0.000558587,0.00008775051,0.000002676863,0.0000139582,0.00233764],"genre_scores_gemma":[0.9191221,0.0002891767,0.08007504,0.00008554611,0.0002767409,9.496592e-9,0.00001308793,0.000021794,0.0001165006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5860817,"threshold_uncertainty_score":0.7132551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01901509840177703,"score_gpt":0.2270484720265092,"score_spread":0.2080333736247321,"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."}}