{"id":"W4401845558","doi":"10.1016/j.scitotenv.2024.175764","title":"From data to harvest: Leveraging ensemble machine learning for enhanced crop yield predictions across Canada amidst climate change","year":2024,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Climate change impacts on agriculture","field":"Agricultural and Biological Sciences","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Australian Research Council; Alliance de recherche numérique du Canada; Institut de Valorisation des Données; Mitacs","keywords":"Canola; Random forest; Gradient boosting; Boosting (machine learning); Ensemble learning; Mean squared error; Crop yield; Climate change; Mathematics; Machine learning; Ensemble forecasting; Statistics; AdaBoost; Vegetation (pathology); Environmental science; Agricultural engineering; Computer science; Agronomy; Support vector machine; Ecology; Engineering; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001047346,0.0004514735,0.0003533397,0.000724173,0.0007250168,0.001081695,0.0009556654,0.0003031101,0.000628548],"category_scores_gemma":[0.002986843,0.0001827933,0.0004771384,0.001345029,0.000225307,0.0007196746,0.0006280584,0.0005925956,0.0001560255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006850707,"about_ca_system_score_gemma":0.008638769,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9508316,"about_ca_topic_score_gemma":0.9632076,"domain_scores_codex":[0.9997255,0.00004426403,0.00001017363,0.00007625372,0.00007413042,0.00006966865],"domain_scores_gemma":[0.9990977,0.0001784341,0.00004947292,0.00007917582,0.0005218159,0.00007347854],"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":[0.0003686497,0.0002317288,0.3568588,0.0001178696,0.0004065811,0.0002590559,0.0005162571,0.3977942,0.002722668,0.001566127,0.009818398,0.2293396],"study_design_scores_gemma":[0.00001459875,0.00003002286,0.08977177,0.00002279039,0.0000746619,0.00001797621,0.0004041565,0.9042169,0.001155482,0.0006606851,0.003600649,0.00003023183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9638645,0.0009125454,0.02506011,0.0009388165,0.00005497498,0.00009152249,0.003782889,0.0008981903,0.004396592],"genre_scores_gemma":[0.9837556,0.0002854039,0.01119502,0.00006067507,0.0000103322,0.0000242516,0.00317828,0.0000476539,0.001442857],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04916841,"threshold_uncertainty_score":0.09891587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07368627747513497,"score_gpt":0.2628978307293238,"score_spread":0.1892115532541888,"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."}}