{"id":"W2966350036","doi":"10.1016/j.isprsjprs.2019.07.010","title":"Mapping dead forest cover using a deep convolutional neural network and digital aerial photography","year":2019,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":109,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministère des Forêts, de la Faune et des Parcs","funders":"Ministère des Forêts, de la Faune et des Parcs","keywords":"Convolutional neural network; Computer science; Aerial photography; Artificial intelligence; Tree (set theory); Channel (broadcasting); Forest inventory; Pattern recognition (psychology); Remote sensing; Forest management; Geography; Forestry; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000340913,0.0002091423,0.0003218199,0.0001293028,0.0002757228,0.0002101382,0.00009028331,0.0001156001,0.00003125026],"category_scores_gemma":[0.00003710825,0.0001834916,0.0001530898,0.0004852624,0.0003338296,0.0002987124,0.0001105276,0.0003269994,0.00001043822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005751843,"about_ca_system_score_gemma":0.00001958641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005202707,"about_ca_topic_score_gemma":0.00004995483,"domain_scores_codex":[0.9985104,0.00006201443,0.0004379908,0.0002702399,0.0003293045,0.0003900272],"domain_scores_gemma":[0.9990981,0.0001366073,0.0003451819,0.0001555879,0.00004221662,0.0002223267],"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":[0.0004114002,0.00007916555,0.080327,0.00006071036,0.0002383172,0.0001298313,0.001169883,0.03724835,0.1081457,0.00002112392,0.0003055155,0.771863],"study_design_scores_gemma":[0.001791695,0.0002186326,0.02965464,0.0002667997,0.00009461111,0.0055647,0.0006809383,0.945873,0.0007132078,0.002095324,0.01247776,0.0005687157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.935096,0.0002767018,0.06303455,0.00005079017,0.0004195882,0.0001781197,0.000002375416,0.0000152883,0.0009266103],"genre_scores_gemma":[0.9715459,0.00004600858,0.02788093,0.0001713586,0.0003030831,9.070586e-9,0.000002832012,0.00002163857,0.00002827893],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9086246,"threshold_uncertainty_score":0.7482571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009656739092464488,"score_gpt":0.2205764960299295,"score_spread":0.2109197569374651,"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."}}