{"id":"W2948149513","doi":"10.5194/isprs-archives-xlii-2-w13-79-2019","title":"MULTISPECTRAL AIRBORNE LASER SCANNING POINT-CLOUDS FOR LAND COVER CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORKS","year":2019,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Waterloo","funders":"","keywords":"Multispectral image; Convolutional neural network; Computer science; Artificial intelligence; Orthophoto; Deep learning; Pattern recognition (psychology); Land cover; Pixel; Ground truth; Point cloud; Laser scanning; Raster graphics; Artificial neural network; Remote sensing; Contextual image classification; Multispectral pattern recognition; Image (mathematics); Land use; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003895894,0.001178039,0.0003968821,0.001714143,0.0003457247,0.0006673822,0.0009205153,0.0006749922,0.002101622],"category_scores_gemma":[0.0006689784,0.0004689803,0.0009839254,0.001303088,0.0001990515,0.0008922325,0.0007329048,0.0007562332,0.001239045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009279215,"about_ca_system_score_gemma":0.0008970294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02102641,"about_ca_topic_score_gemma":0.02950211,"domain_scores_codex":[0.9996399,0.00003397783,0.00001917191,0.0001044205,0.0001443148,0.00005826044],"domain_scores_gemma":[0.999723,0.00004389915,0.0000431774,0.00005433626,0.0001210715,0.0000145586],"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":[0.0001868245,0.0002710672,0.01017621,0.0002038509,0.0003073337,0.0001670586,0.0001049501,0.2493349,0.04130749,0.001666933,0.008238687,0.6880347],"study_design_scores_gemma":[0.000004019531,0.00001809886,0.002236256,0.0000139396,0.00001620495,0.00002110656,0.00001832476,0.9880554,0.007971506,0.000578134,0.001058078,0.000009035394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1568645,0.00120286,0.8211768,0.0003662608,0.000169625,0.0002409306,0.002672008,0.01239578,0.004911304],"genre_scores_gemma":[0.6247151,0.0006036081,0.3634771,0.0001936356,0.00004603461,0.0002545243,0.005470615,0.0001677118,0.005071676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02102641,"threshold_uncertainty_score":0.04180801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01747414609594717,"score_gpt":0.2548519797808292,"score_spread":0.237377833684882,"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."}}