{"id":"W4400262525","doi":"10.1038/s41598-024-65837-0","title":"Multi-step ahead forecasting of electrical conductivity in rivers by using a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model enhanced by Boruta-XGBoost feature selection algorithm","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Mean squared error; Artificial intelligence; Convolutional neural network; Computer science; Feature selection; Perceptron; Artificial neural network; Feature (linguistics); Multilayer perceptron; Pattern recognition (psychology); Machine learning; Algorithm; Mathematics; Statistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001710847,0.0003228409,0.0003927824,0.0001350286,0.0004525034,0.0001973863,0.0002001781,0.0001866935,0.0001277825],"category_scores_gemma":[0.0001814058,0.0003077638,0.000156783,0.001311434,0.0007815357,0.00059245,0.0002134336,0.0006171765,0.000007002187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007440685,"about_ca_system_score_gemma":0.0001258278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003077249,"about_ca_topic_score_gemma":0.0001076389,"domain_scores_codex":[0.9959494,0.0001576302,0.0006794689,0.001471473,0.0008732123,0.0008688426],"domain_scores_gemma":[0.999073,0.0000954727,0.000258086,0.0003252754,0.000050447,0.0001977015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000187699,0.0001647695,0.008189923,0.00002193129,0.00001979206,0.0002218786,0.0001102155,0.4692032,0.4895892,5.514293e-7,0.01231884,0.02014098],"study_design_scores_gemma":[0.0001359451,0.00005185323,0.0004430935,0.00007722856,0.00003177834,0.0004801475,0.000003939051,0.9634768,0.03471011,0.0001700338,0.0001208002,0.0002982194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9469765,0.0002662051,0.0501853,0.00003513732,0.001813327,0.0004424709,0.00003281569,0.0001256573,0.0001226231],"genre_scores_gemma":[0.9817297,0.000001563236,0.01698113,0.00002302768,0.00006260079,0.00001710574,0.0001541755,0.00003232751,0.0009983317],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4942737,"threshold_uncertainty_score":0.9999375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0336701325315195,"score_gpt":0.2682007268149353,"score_spread":0.2345305942834158,"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."}}