{"id":"W2985894533","doi":"10.1109/igarss.2019.8898418","title":"Soil Moisture Estimation From Smap Observations Using Long Short- Term Memory (LSTM)","year":2019,"lang":"en","type":"article","venue":"","topic":"Soil Moisture and Remote Sensing","field":"Environmental Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Long short term memory; Water content; Moderate-resolution imaging spectroradiometer; Environmental science; Artificial neural network; Term (time); Brightness temperature; Vegetation (pathology); Moisture; Estimation; Computer science; Soil science; Remote sensing; Recurrent neural network; Artificial intelligence; Meteorology; Geology; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008642546,0.0001473477,0.0001398263,0.00002417584,0.000142217,0.00005071252,0.0001368033,0.0001133905,0.0005380249],"category_scores_gemma":[0.00001626859,0.0001220078,0.0000624995,0.0001673563,0.0000629502,0.0003282704,0.0001101837,0.0001404354,0.0005503298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001553869,"about_ca_system_score_gemma":0.00001226366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006094465,"about_ca_topic_score_gemma":0.006414889,"domain_scores_codex":[0.9989573,0.00002954751,0.0001907298,0.000326926,0.0002849234,0.0002105564],"domain_scores_gemma":[0.9994789,0.00004865766,0.00004871072,0.000342493,0.000008882534,0.00007236373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000006393157,0.00004514114,0.7517568,0.000007097026,0.00002142473,0.00001012068,0.0005803233,0.0500756,0.148858,0.00001386794,0.0006012152,0.04802401],"study_design_scores_gemma":[0.0001276382,0.000009194056,0.9014191,0.00002469964,0.00002752601,0.000006440761,0.0001260818,0.09027357,0.007451571,0.0002561532,0.00009327092,0.0001847356],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9479458,0.00002793667,0.004321025,0.0001896319,0.000397133,0.0001806684,0.000001255749,0.00008364332,0.04685284],"genre_scores_gemma":[0.9828527,0.000002453007,0.01448681,0.0004668115,0.00009507356,4.025561e-7,0.00004045794,0.00001849061,0.002036781],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1496623,"threshold_uncertainty_score":0.9213048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02458732886630293,"score_gpt":0.2386951081321293,"score_spread":0.2141077792658264,"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."}}