{"id":"W4407551986","doi":"10.5194/hess-29-785-2025","title":"A diversity-centric strategy for the selection of spatio-temporal training data for LSTM-based streamflow forecasting","year":2025,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; York University","keywords":"Training (meteorology); Streamflow; Selection (genetic algorithm); Diversity (politics); Computer science; Machine learning; Artificial intelligence; Meteorology; Geography; Cartography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.003883615,0.0006374606,0.0006985369,0.001019182,0.0007241277,0.0006630977,0.001374768,0.0009921895,0.0009162901],"category_scores_gemma":[0.01023185,0.0004508011,0.0007954752,0.0009419678,0.0008333323,0.001169731,0.00171622,0.001383497,0.0003168248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007403482,"about_ca_system_score_gemma":0.001229832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003852519,"about_ca_topic_score_gemma":0.007468193,"domain_scores_codex":[0.9989285,0.0005407502,0.00007601214,0.0001915287,0.0001665453,0.00009669893],"domain_scores_gemma":[0.9962807,0.001891898,0.0002370336,0.0004822706,0.0008957183,0.0002123036],"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":[0.0008027282,0.0003559178,0.01122598,0.00008944297,0.0002670994,0.0002856854,0.0003766393,0.6705675,0.02447651,0.007687613,0.004125651,0.2797392],"study_design_scores_gemma":[0.00002210791,0.0000539626,0.0006483709,0.000009496294,0.00001549222,0.00002414982,0.00002794896,0.9937595,0.003106301,0.001994767,0.0003308373,0.000007051658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1358442,0.0002245015,0.8613969,0.0004199258,0.00005377919,0.0001087123,0.0001750802,0.0005599058,0.001217029],"genre_scores_gemma":[0.820205,0.00008487164,0.1776006,0.000275283,0.00007648519,0.0002183893,0.000698292,0.00007617654,0.0007650375],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003883615,"threshold_uncertainty_score":0.02053875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08113463109503222,"score_gpt":0.2662262445812852,"score_spread":0.185091613486253,"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."}}