{"id":"W4406070271","doi":"10.1016/j.ecoinf.2025.102995","title":"Improving daily reference evapotranspiration forecasts: Designing AI-enabled recurrent neural networks based long short-term memory","year":2025,"lang":"en","type":"article","venue":"Ecological Informatics","topic":"Plant Water Relations and Carbon Dynamics","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Prince Edward Island","funders":"King Saud University","keywords":"Long short term memory; Term (time); Evapotranspiration; Computer science; Artificial neural network; Recurrent neural network; Artificial intelligence; Ecology; Biology","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":[0.000418319,0.0001906381,0.0001953546,0.00006112012,0.0002646878,0.000140618,0.000278241,0.0002022364,0.0002968492],"category_scores_gemma":[0.0000482379,0.0001519449,0.00006501321,0.0002855795,0.00009442508,0.0005606093,0.0001408902,0.0004151922,0.00003064307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002589899,"about_ca_system_score_gemma":0.00002229536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001336815,"about_ca_topic_score_gemma":0.0001290801,"domain_scores_codex":[0.9985824,0.00006405206,0.0005908493,0.0001674162,0.0002099092,0.0003853723],"domain_scores_gemma":[0.9994361,0.0001221017,0.0001219678,0.0002095393,0.00001985968,0.00009042631],"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":[0.00002836249,0.00007723189,0.04375013,0.00003864563,0.000009738914,0.000007836803,0.0001306011,0.9064584,0.0001786953,0.0001135614,0.0001435781,0.04906322],"study_design_scores_gemma":[0.0002603477,0.0001129468,0.02710987,0.00002692935,0.00002996877,0.000003278297,0.0000250481,0.9719909,0.00009530073,0.00008713674,0.00007610099,0.0001821731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6617169,0.00001213474,0.3291859,0.00007267767,0.0002189217,0.0003953566,0.000007438779,0.0000973202,0.008293303],"genre_scores_gemma":[0.9946012,0.000009203134,0.004175327,0.0008741324,0.00001513731,0.00004804,0.0001381669,0.000005745987,0.0001329942],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3328843,"threshold_uncertainty_score":0.6196135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01842519740138154,"score_gpt":0.2336475806728057,"score_spread":0.2152223832714242,"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."}}