{"id":"W3020943814","doi":"10.1016/j.advwatres.2020.103595","title":"Multiscale groundwater level forecasting: Coupling new machine learning approaches with wavelet transforms","year":2020,"lang":"en","type":"article","venue":"Advances in Water Resources","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":190,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Groundwater; Artificial neural network; Computer science; Environmental science; Irrigation scheduling; Gradient boosting; Water resource management; Artificial intelligence; Hydrology (agriculture); Random forest; Soil science; Geology; Geotechnical engineering","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":[0.0002465316,0.0002854884,0.0002937703,0.00003465754,0.0002048651,0.0000713191,0.0003470098,0.00008427235,0.000468967],"category_scores_gemma":[0.00004332474,0.0001625874,0.00005271981,0.0002248677,0.0002759266,0.0005237302,0.0001755573,0.0004510866,0.0001183473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006108759,"about_ca_system_score_gemma":0.000002555737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005518827,"about_ca_topic_score_gemma":0.0005931154,"domain_scores_codex":[0.9980276,0.00003994811,0.0003205329,0.0006210108,0.0003602946,0.0006306368],"domain_scores_gemma":[0.9995251,0.0000593948,0.00006758912,0.0001353922,0.00000350087,0.0002089805],"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":[0.0001920416,0.00004648128,0.1204221,0.00003109432,0.000007899637,0.00005001,0.01003773,0.8397548,0.0009506406,0.00000276793,0.000006960891,0.0284975],"study_design_scores_gemma":[0.001480616,0.0008257445,0.002299156,0.00008643907,0.00002096612,0.00005408645,0.0002116631,0.8568395,0.01079705,0.0004113756,0.1262926,0.0006808658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.985276,0.0001965843,0.01074343,0.001015317,0.00002756494,0.0002255085,0.000001709506,0.0001394563,0.002374417],"genre_scores_gemma":[0.9875913,0.00002087451,0.01145564,0.0002246173,0.0000814931,0.00001429659,0.00002006645,0.00004239267,0.0005493364],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1262856,"threshold_uncertainty_score":0.663012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07660228442083965,"score_gpt":0.223181709638159,"score_spread":0.1465794252173194,"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."}}