{"id":"W7116877000","doi":"10.1016/j.fcr.2025.110311","title":"Utilizing soil characteristics and hybrid machine learning for interpretable potato yield prediction: A study with satin-bowerbird optimization and deep neural network","year":2025,"lang":"en","type":"article","venue":"Field Crops Research","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; University of Guelph; University of Prince Edward Island","funders":"Natural Sciences and Engineering Research Council of Canada; University of Prince Edward Island","keywords":"Interpretability; Artificial neural network; Feature selection; Support vector machine; Mean squared error; Regression; Selection (genetic algorithm); Correlation coefficient; Feature (linguistics); Predictive modelling","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003788694,0.0000993786,0.0001443139,0.00001812237,0.0006122032,0.0002214231,0.00009984419,0.00005291057,0.00006894615],"category_scores_gemma":[0.0002073347,0.00003926961,0.00001980639,0.0002730568,0.00004024188,0.00009304901,0.0001414843,0.0003177363,4.592443e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008640964,"about_ca_system_score_gemma":0.000006184306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003397671,"about_ca_topic_score_gemma":0.001007271,"domain_scores_codex":[0.9990452,0.00009282906,0.0001453198,0.0002763188,0.0001572724,0.0002830581],"domain_scores_gemma":[0.9990202,0.0007023182,0.00003156284,0.00004251986,0.0001429568,0.00006045135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007538086,0.0001713385,0.8613665,0.000075198,0.00007837846,0.00001862048,0.0006071752,0.001197851,0.003119358,0.00009746808,0.002925883,0.1295885],"study_design_scores_gemma":[0.001169352,0.009136076,0.6074519,0.0004086439,0.00009172201,0.00004573871,0.006462181,0.3590115,0.001203376,0.0002047166,0.01431545,0.0004993076],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961818,0.0003863059,0.0005556783,0.00154392,0.00008626651,0.0005456043,0.000008784574,0.00004499231,0.0006466014],"genre_scores_gemma":[0.9985059,0.00009636128,0.0001390067,0.0001518187,0.0002362477,0.00006601251,0.00003824663,0.000001215299,0.0007651998],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3578137,"threshold_uncertainty_score":0.4708634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02717889138502224,"score_gpt":0.2743822798026528,"score_spread":0.2472033884176306,"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."}}