{"id":"W4286559726","doi":"10.31223/x57p9w","title":"A scalable framework for soil property mapping tested across a highly diverse tropical data-scarce region","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Ministério da Ciência, Tecnologia, Inovações e Comunicações; Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Ministério da Ciência, Tecnologia e Inovação; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Empresa Brasileira de Pesquisa Agropecuária; Natural Environment Research Council; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Environmental science; Soil texture; Soil map; Digital soil mapping; Soil science; Vegetation (pathology); Remote sensing; Feature selection; Flexibility (engineering); Soil water; Computer science; Machine learning; Geology; Mathematics","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":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003666795,0.0003575928,0.0004195037,0.00003558274,0.0006277242,0.0002232952,0.001525439,0.0002943605,0.001335215],"category_scores_gemma":[0.0005461134,0.0002733979,0.0001196311,0.0002310449,0.0002293838,0.0001587605,0.01268974,0.0008210818,0.0001110596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003824076,"about_ca_system_score_gemma":0.0000662575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004579895,"about_ca_topic_score_gemma":0.0004584736,"domain_scores_codex":[0.9968185,0.00008680211,0.0004295406,0.001413258,0.0005482365,0.000703697],"domain_scores_gemma":[0.9976183,0.0002901756,0.0002387849,0.001643346,0.00002316152,0.0001862691],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007022095,0.001946976,0.2501971,0.002158396,0.0006687488,0.0004965236,0.01009254,0.02806381,0.001329114,0.01013787,0.4685083,0.2256984],"study_design_scores_gemma":[0.001404842,0.0002404465,0.0724243,0.0004129741,0.0001615208,0.00003474443,0.003521753,0.1849267,0.00009449488,0.03482047,0.7000382,0.001919591],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1125918,0.000105153,0.8654341,0.003331487,0.002174398,0.003464807,0.002122205,0.0005402972,0.01023575],"genre_scores_gemma":[0.468091,0.0002872453,0.4765328,0.00313622,0.000752955,0.001733058,0.002829581,0.0002097064,0.04642738],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3889012,"threshold_uncertainty_score":0.9999718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08803003029658314,"score_gpt":0.306401706047937,"score_spread":0.2183716757513539,"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."}}