{"id":"W4380152165","doi":"10.1016/j.atmosres.2023.106856","title":"Deep learning for daily potential evapotranspiration using a HS-LSTM approach","year":2023,"lang":"en","type":"article","venue":"Atmospheric Research","topic":"Plant Water Relations and Carbon Dynamics","field":"Environmental Science","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Genetic programming; Evapotranspiration; Artificial intelligence; Computer science; Adaptive neuro fuzzy inference system; Machine learning; Inference; Artificial neural network; Deep learning; Ground truth; Fuzzy logic; Ecology; Fuzzy control system","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":[0.0003436633,0.0005608714,0.0004064981,0.0003040675,0.0002382262,0.0004925003,0.0008265053,0.0009873554,0.004814073],"category_scores_gemma":[0.0009093353,0.0003999119,0.0004386132,0.0005210713,0.0002635987,0.000970025,0.000640887,0.001383819,0.001098686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006475213,"about_ca_system_score_gemma":0.001216946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01722635,"about_ca_topic_score_gemma":0.02375881,"domain_scores_codex":[0.9999079,0.00001105868,0.000005631203,0.00003362379,0.00001858487,0.00002330421],"domain_scores_gemma":[0.9997762,0.00009739932,0.00001513343,0.00002549369,0.00006810069,0.0000176985],"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":[0.00009556,0.0000942118,0.0009249834,0.00006925133,0.00006124443,0.00005668268,0.00003369139,0.7351029,0.00739128,0.004921428,0.005168751,0.24608],"study_design_scores_gemma":[0.000001551995,0.000003934393,0.00006175952,0.000001671602,0.000001812262,0.000002419773,0.000001344067,0.9985013,0.0004119132,0.0008659567,0.0001450512,0.000001293817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0961348,0.0009115359,0.8932198,0.0007178594,0.0002776702,0.00003781077,0.001026009,0.003504336,0.004170178],"genre_scores_gemma":[0.8393946,0.0003862872,0.1463976,0.0002568272,0.0001364943,0.00007688449,0.001739426,0.0002140291,0.01139778],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01722635,"threshold_uncertainty_score":0.03425217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0492179328965802,"score_gpt":0.309652549387019,"score_spread":0.2604346164904388,"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."}}