{"id":"W4412178037","doi":"10.5194/hess-29-2881-2025","title":"Benchmarking historical performance and future projections from a large-scale hydrologic model with a watershed hydrologic model","year":2025,"lang":"en","type":"article","venue":"Hydrology and earth system sciences","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Hydrological modelling; Benchmarking; Watershed; Hydrology (agriculture); Environmental science; Scale (ratio); Model validation; Geology; Computer science; Climatology; Data science; Cartography; Geography; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001563368,0.0007936331,0.0004076303,0.0004662072,0.0003510435,0.0008071167,0.0008312874,0.0007800761,0.001277392],"category_scores_gemma":[0.002595259,0.0002462155,0.0007753035,0.0006824223,0.0004124742,0.0008068375,0.0004965327,0.0009241306,0.0002065128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001160825,"about_ca_system_score_gemma":0.001735586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.08677111,"about_ca_topic_score_gemma":0.05120004,"domain_scores_codex":[0.9996803,0.0001013998,0.00002032648,0.00007816518,0.00006981281,0.00004990387],"domain_scores_gemma":[0.9989912,0.0003648151,0.00008233196,0.0001558738,0.0002921216,0.0001137415],"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":[0.00008997849,0.00007456584,0.01464211,0.00002391518,0.00007148892,0.00003733101,0.00001915678,0.9801198,0.0009212957,0.0004235584,0.0007199759,0.002856849],"study_design_scores_gemma":[0.00003293333,0.00004957301,0.004807252,0.000005336441,0.00001778046,0.000006902254,0.00002080166,0.9936551,0.0009265009,0.0001551464,0.0003111701,0.00001153508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9865685,0.00009271866,0.006991645,0.0002591282,0.00004140886,0.00003561883,0.002517814,0.0006145323,0.002878668],"genre_scores_gemma":[0.9914459,0.00004470066,0.004732905,0.00003002151,0.000009925426,0.00002443477,0.00340006,0.0000645886,0.0002474669],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08677111,"threshold_uncertainty_score":0.1725321,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009623042967625199,"score_gpt":0.1968110436432128,"score_spread":0.1871880006755876,"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."}}