{"id":"W4412592452","doi":"10.1016/b978-0-443-33631-7.00003-2","title":"A combination of satellite observations and machine learning technique for terrestrial water storage anomaly estimation (case study: St. Lawrence watershed, Quebec, Canada)","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Geophysics and Gravity Measurements","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Watershed; Anomaly (physics); Satellite; Estimation; Environmental science; Remote sensing; Hydrology (agriculture); Geography; Geology; Computer science; Engineering; 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":[0.0005069582,0.0004661382,0.0002424436,0.0009483836,0.0003798729,0.0008948752,0.0006372164,0.0004102894,0.003325322],"category_scores_gemma":[0.0007169446,0.0001926411,0.0002638718,0.002774582,0.0002251227,0.0005054537,0.0002198781,0.0002650561,0.0008122277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002954833,"about_ca_system_score_gemma":0.003462543,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.8451174,"about_ca_topic_score_gemma":0.9391785,"domain_scores_codex":[0.9998544,0.00001872526,0.000006600278,0.00002745255,0.00007191927,0.00002092942],"domain_scores_gemma":[0.9997968,0.00006209216,0.00001203459,0.00001251679,0.0001077352,0.000008836743],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00005353285,0.00004385689,0.02153989,0.0001696415,0.00008384196,0.0002767992,0.0001554927,0.0558973,0.007416915,0.003018549,0.03113874,0.8802054],"study_design_scores_gemma":[0.0000278537,0.0001341338,0.09961571,0.0001630828,0.0001848918,0.0005995216,0.0006051536,0.7857311,0.01310513,0.003331457,0.09641529,0.00008659525],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2848781,0.01520829,0.4667227,0.003867403,0.0004873933,0.000297128,0.009298885,0.006669661,0.2125705],"genre_scores_gemma":[0.6601436,0.005232948,0.2426722,0.0003312748,0.0001070196,0.0000664268,0.00293128,0.0002514319,0.08826379],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1548826,"threshold_uncertainty_score":0.3115893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03050127520324348,"score_gpt":0.2214924631408122,"score_spread":0.1909911879375687,"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."}}