{"id":"W4220683130","doi":"10.1139/cjss-2021-0133","title":"Predicting soil organic matter and soil moisture content from digital camera images: comparison of regression and machine learning approaches","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Soil Science","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Ministry of Agriculture, Food and Rural Affairs; Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Agriculture, Food and Rural Affairs; University of Guelph","keywords":"Mean squared error; Support vector machine; Artificial intelligence; Random forest; Soil organic matter; Artificial neural network; Water content; Machine learning; Multivariate statistics; Mathematics; Soil science; Pattern recognition (psychology); Computer science; Soil water; Statistics; Environmental science; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.0005052342,0.0001131679,0.0002095782,0.0001092804,0.0006539049,0.0001640715,0.0002941773,0.0000230874,0.0002685126],"category_scores_gemma":[0.0001865397,0.00009602479,0.00002538343,0.0002686518,0.0007799227,0.0003712978,0.0002260859,0.0003801239,0.000002377777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001933043,"about_ca_system_score_gemma":0.0001978009,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.04634833,"about_ca_topic_score_gemma":0.02058583,"domain_scores_codex":[0.9986938,0.0000414263,0.0003109338,0.0002338296,0.0004352282,0.0002848384],"domain_scores_gemma":[0.9990086,0.00006966339,0.0003523709,0.00009915246,0.00002809089,0.0004421115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000006894657,0.00001132135,0.9808868,0.000006280586,0.000006525746,0.00002165079,0.003014419,0.003508583,0.004068074,0.000005590155,0.0002644849,0.008199412],"study_design_scores_gemma":[0.0004990767,0.0002197457,0.9513316,0.00009462951,0.00002975882,0.0001938847,0.01242492,0.0326332,0.001502503,0.0002766023,0.0005656882,0.000228404],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9973839,0.0007531422,0.0002295471,0.0004163094,0.0001337877,0.00004858644,0.00006036355,0.0000030461,0.0009713068],"genre_scores_gemma":[0.9995114,0.00001303838,0.0002301921,0.0000949606,0.00002489839,0.000001134056,0.000004363339,0.000008744535,0.000111289],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02955517,"threshold_uncertainty_score":0.9972859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02785247229234753,"score_gpt":0.2090297903147053,"score_spread":0.1811773180223578,"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."}}