{"id":"W4399316221","doi":"10.1016/j.engappai.2024.108744","title":"Hybrid machine learning system based on multivariate data decomposition and feature selection for improved multitemporal evapotranspiration forecasting","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Prince Edward Island","funders":"Natural Resources Conservation Service; U.S. Department of Agriculture","keywords":"Computer science; Feature selection; Evapotranspiration; Multivariate statistics; Artificial intelligence; Machine learning; Selection (genetic algorithm); Decomposition; Data mining; Feature (linguistics); Pattern recognition (psychology)","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":[0.0004639855,0.000137595,0.0001208651,0.00008536814,0.0001707519,0.00006694735,0.0001737501,0.00006250563,0.00001140169],"category_scores_gemma":[0.0001291301,0.0001344722,0.00003354988,0.0002746779,0.00004338583,0.0001513938,0.000047673,0.0001992863,0.00001097955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009647024,"about_ca_system_score_gemma":0.000008687663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001487996,"about_ca_topic_score_gemma":0.00001832016,"domain_scores_codex":[0.9989985,0.0000219303,0.0002668628,0.0004382334,0.0001092775,0.000165207],"domain_scores_gemma":[0.9993904,0.0002672616,0.00006826048,0.0002027885,0.00002090599,0.00005041085],"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":[0.00002617744,0.00002918733,0.000047339,0.0001141201,0.00000669495,2.935146e-7,0.00003561424,0.8607421,0.06249299,0.0005645209,0.000006669145,0.07593428],"study_design_scores_gemma":[0.00002486391,0.0001192457,0.00002345796,0.0001019905,0.0000232199,0.000005695793,0.000003533542,0.9739357,0.02451669,0.0001263058,0.0009967594,0.0001226008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0461918,0.00003808894,0.9525845,0.000150961,0.00007482188,0.0005770942,0.00009010945,0.000266663,0.00002592784],"genre_scores_gemma":[0.9086423,0.000001247829,0.09092252,0.000008404691,0.00006522916,0.0001130018,0.000215372,0.00002208785,0.000009823737],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8624505,"threshold_uncertainty_score":0.5483619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03889269337246543,"score_gpt":0.2869871289383238,"score_spread":0.2480944355658584,"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."}}