{"id":"W4408418184","doi":"10.5194/egusphere-2025-846-v1","title":"A novel hybrid fine-tuning method for supercharging deep learning model development for hydrological prediction","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Resources Canada","keywords":"Deep learning; Computer science; Artificial intelligence; Development (topology); Hybrid learning; Machine learning; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008030625,0.000928503,0.0006064479,0.0006628035,0.000396679,0.0006300597,0.001988652,0.0007411361,0.004103258],"category_scores_gemma":[0.001819849,0.0005205192,0.0007801809,0.0005028563,0.0003708113,0.00124058,0.001193954,0.001403762,0.001290063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007665502,"about_ca_system_score_gemma":0.001482222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009235067,"about_ca_topic_score_gemma":0.01717841,"domain_scores_codex":[0.9996074,0.00005234019,0.00002511777,0.0001350726,0.0001314034,0.00004859807],"domain_scores_gemma":[0.9994816,0.0001468654,0.00004109224,0.0001128423,0.0001780674,0.00003949508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001524557,0.0002158641,0.002293258,0.00009808875,0.0001273121,0.0001445644,0.0001296229,0.4717408,0.02675735,0.003760055,0.005756292,0.4888243],"study_design_scores_gemma":[0.000008311747,0.00001311808,0.00008439463,0.000002666582,0.000005682202,0.0000099921,0.000004418733,0.99558,0.002927185,0.0006561778,0.0007038736,0.000004157183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02799728,0.0002281536,0.9626091,0.0001201754,0.0000822117,0.00008344521,0.000123321,0.006763751,0.001992486],"genre_scores_gemma":[0.3999655,0.000127475,0.593354,0.0003334106,0.00005959461,0.0002655928,0.0007141696,0.0007446593,0.004435567],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009235067,"threshold_uncertainty_score":0.01836258,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0610815415135946,"score_gpt":0.3031462420867289,"score_spread":0.2420647005731343,"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."}}