{"id":"W4311404507","doi":"10.5194/hess-2022-379","title":"Improving predictions of land-atmosphere interactions based on a hybrid data assimilation and machine learning method","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Plant Water Relations and Carbon Dynamics","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Chinese Academy of Sciences; Beijing Normal University; National Natural Science Foundation of China","keywords":"Environmental science; Evapotranspiration; Weather Research and Forecasting Model; Midstream; Precipitation; Data assimilation; Hydrology (agriculture); Vegetation (pathology); Atmospheric sciences; Meteorology; Geology; Geography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008958294,0.0006566385,0.0006259835,0.0004532274,0.0003835912,0.0006192385,0.0005785641,0.0008202357,0.0006028579],"category_scores_gemma":[0.001315967,0.0003486234,0.0006160514,0.000346278,0.0003209182,0.000668315,0.0005447314,0.0006355843,0.0001265292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006675117,"about_ca_system_score_gemma":0.0009246247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02356331,"about_ca_topic_score_gemma":0.01532616,"domain_scores_codex":[0.9998004,0.00006375276,0.00001399225,0.00005640796,0.00004040159,0.00002508474],"domain_scores_gemma":[0.9994954,0.0002454793,0.00004707379,0.00003637574,0.0001464461,0.00002923402],"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":[0.00004075273,0.00005090584,0.002524491,0.0000123117,0.00004914897,0.00001738587,0.00001391534,0.9762536,0.002189022,0.0003793668,0.0001709184,0.01829819],"study_design_scores_gemma":[0.000001370646,0.000002211172,0.00006659779,2.666131e-7,8.535298e-7,3.540275e-7,4.479452e-7,0.9998067,0.00008334852,0.00002551913,0.00001160611,7.201961e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5098025,0.0004083258,0.4842933,0.000379134,0.0001221166,0.00006625327,0.0001764686,0.001360505,0.003391457],"genre_scores_gemma":[0.954757,0.00003904058,0.04444495,0.0000594015,0.00002259439,0.00003930092,0.0000910469,0.00002514901,0.0005213862],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02356331,"threshold_uncertainty_score":0.04685229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02256181960589808,"score_gpt":0.2631303731484826,"score_spread":0.2405685535425846,"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."}}