{"id":"W4390263283","doi":"10.1007/s11119-023-10099-5","title":"Comparing machine learning algorithms for predicting and digitally mapping surface soil available phosphorous: a case study from southwestern Iran","year":2023,"lang":"en","type":"article","venue":"Precision Agriculture","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"Iran National Science Foundation","keywords":"Mean squared error; Topsoil; Latin hypercube sampling; Random forest; Statistics; Algorithm; Mathematics; Support vector machine; Correlation coefficient; Artificial neural network; Coefficient of determination; Soil science; Digital elevation model; Digital soil mapping; Environmental science; Machine learning; Computer science; Remote sensing; Soil water; Soil map; Geography; Monte Carlo method","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":[0.0004927869,0.0002376028,0.0002737845,0.00002891971,0.0005719097,0.0002694181,0.000166255,0.00008000921,0.00009620542],"category_scores_gemma":[0.0001652722,0.0001781976,0.00005128952,0.0003672949,0.00003303152,0.0002301213,0.0004462169,0.0002430911,0.0001664338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005693017,"about_ca_system_score_gemma":0.000004324346,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007453419,"about_ca_topic_score_gemma":0.002607227,"domain_scores_codex":[0.9982664,0.00006268521,0.0003277375,0.0006230408,0.0003474251,0.0003727099],"domain_scores_gemma":[0.999065,0.0004478175,0.0001446976,0.0001690661,0.00002340568,0.0001499732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002240825,0.00009696306,0.9421753,0.00001643409,0.00005431936,0.000351778,0.01022634,0.03023563,0.002258357,4.605279e-7,0.002179479,0.01238249],"study_design_scores_gemma":[0.002789384,0.0002890557,0.2971347,0.0001608371,0.0001018068,0.0002922163,0.03228996,0.6576168,0.0001607414,0.00016345,0.008270779,0.0007302981],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9911008,0.0001516266,0.007007639,0.00002767287,0.0001605104,0.000696333,0.0001376789,0.000231218,0.0004865102],"genre_scores_gemma":[0.9955778,0.00003068232,0.002632743,0.00002551211,0.00006185041,0.00003689715,0.0001327445,0.00002410315,0.001477651],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6450407,"threshold_uncertainty_score":0.9991561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03831707533539234,"score_gpt":0.2451253900123978,"score_spread":0.2068083146770055,"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."}}