{"id":"W4292258093","doi":"10.1109/jstars.2022.3199118","title":"A Deep Convolutional Neural Network With Multiscale Feature Dynamic Fusion for InSAR Phase Filtering","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Synthetic Aperture Radar (SAR) Applications and Techniques","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Key Science and Technology Foundation of Gansu Province; Lanzhou Jiaotong University; Natural Science Foundation of Gansu Province; Ministry of Natural Resources","keywords":"Computer science; Convolutional neural network; Interferometric synthetic aperture radar; Synthetic aperture radar; Artificial intelligence; Feature (linguistics); Noise (video); Pattern recognition (psychology); Noise reduction; Algorithm; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003608433,0.0005749733,0.0004708927,0.0004068862,0.0002594794,0.0004018264,0.0008075628,0.0007048565,0.0009413841],"category_scores_gemma":[0.0006095373,0.000268148,0.0005780259,0.0005804006,0.0002564814,0.0008079538,0.0006546913,0.0006952457,0.0002710437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006080809,"about_ca_system_score_gemma":0.0006610051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01089539,"about_ca_topic_score_gemma":0.01015765,"domain_scores_codex":[0.9998227,0.00001357228,0.00001030945,0.00005328655,0.00006817136,0.00003210103],"domain_scores_gemma":[0.9998803,0.00002414712,0.00001339228,0.00001669432,0.00005501772,0.00001042195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001751306,0.0001520065,0.002544468,0.0001065752,0.0001486454,0.0001679873,0.00007036259,0.3972697,0.05056741,0.005279584,0.004380561,0.5391375],"study_design_scores_gemma":[0.000003691047,0.00002296287,0.0003294703,0.000003622025,0.00001587994,0.00002591191,0.00000336671,0.9944682,0.003844324,0.000556975,0.0007186217,0.000006913042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04216498,0.0007176172,0.9529646,0.0001981782,0.0001322018,0.00003451817,0.0001534794,0.00114116,0.002493279],"genre_scores_gemma":[0.7603653,0.0006189798,0.231413,0.0002814193,0.00008512949,0.0000833966,0.0006236727,0.00006895161,0.00646022],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01089539,"threshold_uncertainty_score":0.02166396,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01139181695192074,"score_gpt":0.2238148172324356,"score_spread":0.2124230002805148,"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."}}