{"id":"W4389486544","doi":"10.5194/essd-15-5597-2023","title":"GTWS-MLrec: global terrestrial water storage reconstruction by machine learning from 1940 to present","year":2023,"lang":"en","type":"article","venue":"Earth system science data","topic":"Geophysics and Gravity Measurements","field":"Earth and Planetary Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; Natural Environment Research Council; U.S. Geological Survey; Wuhan University; National Natural Science Foundation of China; Centre for Ecology and Hydrology; UK Research and Innovation; Sight Research UK; Environment and Climate Change Canada; Agência Nacional de Águas","keywords":"Environmental science; Water cycle; Land cover; Streamflow; Climatology; Satellite; Vegetation (pathology); Meteorology; Drainage basin; Land use; Geology; Geography","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001656998,0.0001617081,0.0001977331,0.00009677044,0.0006795248,0.0004479975,0.001261995,0.00004358971,0.0002699598],"category_scores_gemma":[0.00009035192,0.000118294,0.00002995054,0.0008630937,0.0001336499,0.0008591967,0.0002367383,0.0001353104,0.004063544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001484193,"about_ca_system_score_gemma":0.00008688009,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02184084,"about_ca_topic_score_gemma":0.002856147,"domain_scores_codex":[0.9971142,0.0001484548,0.0002779139,0.0008021517,0.001060837,0.0005964721],"domain_scores_gemma":[0.998764,0.00003633437,0.00007674094,0.000766733,0.00004050451,0.0003156802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001506048,0.00003746055,0.764713,0.00004894499,0.00006016127,0.00007698134,0.000555541,0.01435366,0.011876,0.00001284266,0.01550859,0.1926061],"study_design_scores_gemma":[0.001045341,0.0002806377,0.5068348,0.0001867444,0.00003872247,0.0000438047,0.0009107821,0.4135444,0.002292608,0.0001186883,0.07395753,0.0007459492],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904906,0.00005456894,0.0001867759,0.0002347966,0.00335123,0.0003304258,0.004470767,0.0001444745,0.0007364203],"genre_scores_gemma":[0.9946321,0.000003519995,0.0002100969,0.00002601488,0.0003434713,0.000001536622,0.004552227,0.000003085884,0.0002279038],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3991907,"threshold_uncertainty_score":0.9967119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05094868466494022,"score_gpt":0.2470675212748152,"score_spread":0.196118836609875,"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."}}