{"id":"W4415376198","doi":"10.1038/s41598-025-20386-y","title":"An interpretable machine learning approach based on SHAP, Sobol and LIME values for precise estimation of daily soybean crop coefficients","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Plant Water Relations and Carbon Dynamics","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Sobol sequence; Interpretability; Mean squared error; Random forest; Irrigation scheduling; Gradient boosting; Consistency (knowledge bases); Coefficient of determination","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001919194,0.0006637776,0.0004295142,0.001414318,0.0002475499,0.000745111,0.000659681,0.0006891493,0.001266423],"category_scores_gemma":[0.006696872,0.0002066854,0.0006600749,0.0005164386,0.0003961254,0.0009122377,0.0006842584,0.0009960448,0.0001132681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005078572,"about_ca_system_score_gemma":0.0006450997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002437126,"about_ca_topic_score_gemma":0.003446441,"domain_scores_codex":[0.9995357,0.0002071656,0.00003242483,0.0001078573,0.0000809308,0.00003595258],"domain_scores_gemma":[0.9980145,0.001336255,0.0002412834,0.0001319787,0.0002337094,0.00004241128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001970282,0.000165854,0.05194798,0.0001893516,0.0002196315,0.0004251204,0.0003767215,0.7652394,0.004688298,0.02097948,0.002045754,0.1535254],"study_design_scores_gemma":[0.000007646597,0.00003416639,0.003774769,0.00001436943,0.0000187386,0.00003317658,0.00003594504,0.9861308,0.0005631788,0.009058028,0.0003175952,0.00001164659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3038796,0.0004625103,0.6909617,0.0006182205,0.00005094592,0.00008391677,0.0003523838,0.0007633386,0.002827493],"genre_scores_gemma":[0.9565422,0.0000703162,0.04264596,0.00006353242,0.00002188923,0.00004021062,0.0002332001,0.00001937803,0.000363365],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002437126,"threshold_uncertainty_score":0.01014978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006836643303415042,"score_gpt":0.2309670051120633,"score_spread":0.2241303618086483,"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."}}