{"id":"W4297094388","doi":"10.1109/jstars.2022.3206143","title":"3-D Hybrid CNN Combined With 3-D Generative Adversarial Network for Wetland Classification With Limited Training Data","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Wetland; Deep learning; Pattern recognition (psychology); Swamp; Contextual image classification; Training (meteorology); Machine learning; Remote sensing; Image (mathematics); Geography; Ecology; Meteorology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005197776,0.0001403988,0.0002399794,0.00007762075,0.0005903561,0.00005930692,0.000162777,0.00003870906,0.000007078317],"category_scores_gemma":[0.0000322715,0.000116539,0.00001877492,0.0006549063,0.0001034901,0.0001143377,0.00004933719,0.0003787368,2.753108e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009572302,"about_ca_system_score_gemma":0.0001414357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007232089,"about_ca_topic_score_gemma":0.0005445939,"domain_scores_codex":[0.9986885,0.0000741484,0.0003804742,0.0002823583,0.0003372571,0.0002372301],"domain_scores_gemma":[0.9990662,0.000138214,0.0003670543,0.0002701251,0.00009619457,0.00006226459],"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":[0.002426244,0.0001968603,0.002346959,0.00003076034,0.0002892741,0.00004664905,0.003614749,0.5176962,0.07206889,0.0008581353,0.004499752,0.3959255],"study_design_scores_gemma":[0.003675865,0.0006883182,0.03408895,0.0000709556,0.0001409758,0.0003371269,0.0008391117,0.9180512,0.000981236,0.001562936,0.03916306,0.0004002727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8081763,0.00001808672,0.1888732,0.001575553,0.0001479317,0.0005390944,0.00002234868,0.00002225962,0.0006251897],"genre_scores_gemma":[0.6660682,0.00002088772,0.3332034,0.0002182944,0.0002768871,4.4041e-7,0.0001076034,0.00002008822,0.00008414499],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.400355,"threshold_uncertainty_score":0.4752321,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05122278334762386,"score_gpt":0.2400173056607719,"score_spread":0.188794522313148,"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."}}