{"id":"W4401687400","doi":"10.1109/tgrs.2024.3446042","title":"SSL-SoilNet: A Hybrid Transformer-Based Framework With Self-Supervised Learning for Large-Scale Soil Organic Carbon Prediction","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Deutsche Forschungsgemeinschaft","keywords":"Computer science; Soil carbon; Scale (ratio); Total organic carbon; Transformer; Remote sensing; Environmental science; Artificial intelligence; Machine learning; Soil science; Soil water; Geology; Environmental chemistry; Engineering; Electrical engineering; Cartography","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":[0.0003180765,0.0002100211,0.0001621729,0.0001163121,0.0007332464,0.0001489791,0.00007518377,0.00008661938,0.00003422255],"category_scores_gemma":[0.000008235668,0.0001777889,0.00006536229,0.00053805,0.0001403295,0.0001681018,0.00000156931,0.0003688725,0.00001036207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000113273,"about_ca_system_score_gemma":0.0000661154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003990329,"about_ca_topic_score_gemma":0.0004533102,"domain_scores_codex":[0.9983835,0.00003738579,0.0001974571,0.0005855276,0.0003370138,0.0004591548],"domain_scores_gemma":[0.999476,0.0001735918,0.00003279642,0.0001574933,0.00001964145,0.000140468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000135776,0.0001143649,0.00004180122,0.0002051373,0.00004965313,0.00004532706,0.004740556,0.04478019,0.02666375,0.000009925129,0.00002259695,0.9231909],"study_design_scores_gemma":[0.000396655,0.0003451683,0.0001807307,0.0002816274,0.00009005216,0.0000587068,0.0003999931,0.9867426,0.01011864,0.0002405055,0.0009085013,0.0002368017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3032849,0.00002238241,0.6954791,0.0002056809,0.0003451907,0.0002327874,0.00001834367,0.0001867718,0.0002248724],"genre_scores_gemma":[0.918927,0.00007502327,0.08053641,0.000154931,0.00004510739,0.000001576695,0.000003731069,0.00003418502,0.000222035],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9419624,"threshold_uncertainty_score":0.7250021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006663452912177755,"score_gpt":0.2103322946904334,"score_spread":0.2036688417782556,"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."}}