{"id":"W2964603971","doi":"10.1109/lgrs.2019.2926530","title":"Filling Voids in Elevation Models Using a Shadow-Constrained Convolutional Neural Network","year":2019,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Landslides and related hazards","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; Natural Science Foundation of Shandong Province","keywords":"Convolutional neural network; Shadow (psychology); Computer science; Digital elevation model; Artificial intelligence; Shadow mapping; Inference; Interpolation (computer graphics); Weighting; Elevation (ballistics); Inverse distance weighting; Computer vision; Key (lock); Pattern recognition (psychology); Image (mathematics); Bilinear interpolation; Mathematics; Multivariate interpolation; Remote sensing; Geometry; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003684312,0.0001337571,0.0001422976,0.00005509917,0.0002025496,0.00005949997,0.00009023006,0.00008205904,0.00002430913],"category_scores_gemma":[0.000007504612,0.0001100673,0.00003923666,0.0003803423,0.0002982762,0.000350753,0.00005176508,0.0002028469,0.00001554819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001052403,"about_ca_system_score_gemma":0.00001695495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001589177,"about_ca_topic_score_gemma":0.00008515667,"domain_scores_codex":[0.9986317,0.00004314482,0.0002099429,0.0003876966,0.0002806561,0.0004469243],"domain_scores_gemma":[0.9996793,0.00003968013,0.00007524987,0.0001270004,0.000007016721,0.00007171148],"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":[0.00001577574,0.000004527692,0.004783516,0.000005343789,0.000003283739,0.00002205036,0.0002990139,0.867297,0.1117405,0.00001310928,0.0000758927,0.01573997],"study_design_scores_gemma":[0.0002874065,0.00001533785,0.006431096,0.00007428615,0.000005851587,0.00008555816,0.00004010697,0.9921628,0.0000907189,0.0005781141,0.0000547428,0.0001739291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9628152,0.00002359139,0.03536741,0.0007411593,0.000572781,0.0001461644,0.000001214741,0.00002349839,0.0003089767],"genre_scores_gemma":[0.9819159,0.00001501625,0.0159962,0.00189367,0.00008157684,3.268682e-8,0.000002327516,0.000008583402,0.00008669669],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1248658,"threshold_uncertainty_score":0.4488415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01264248124707185,"score_gpt":0.2091243944320881,"score_spread":0.1964819131850162,"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."}}