{"id":"W2951229719","doi":"10.5194/bg-2019-202","title":"Improving non-representative-sample prediction of forestaboveground biomass maps: A combined machinelearning and spatial statistical approach","year":2019,"lang":"en","type":"article","venue":"","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"National Office for Philosophy and Social Sciences; National Natural Science Foundation of China; Chinese Academy of Sciences; National Science Foundation","keywords":"Sample (material); Scale (ratio); Sampling (signal processing); Biomass (ecology); Longitude; Computer science; Geographic coordinate system; Spatial ecology; Latitude; Spatial analysis; Covariate; Environmental science; Data mining; Remote sensing; Cartography; Machine learning; Geography; Ecology","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":[0.001898454,0.0008772965,0.001125092,0.001209432,0.0003498714,0.0006812565,0.001022045,0.0007257513,0.0005790888],"category_scores_gemma":[0.003668408,0.000312479,0.0007353685,0.00108231,0.0003716263,0.001235273,0.0008341558,0.000717352,0.0002442766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004680989,"about_ca_system_score_gemma":0.0007959711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007313772,"about_ca_topic_score_gemma":0.007290937,"domain_scores_codex":[0.9993346,0.0002466606,0.00003162397,0.0001946149,0.0001315135,0.00006097436],"domain_scores_gemma":[0.9975724,0.001426071,0.0002068986,0.0003020211,0.0004154216,0.00007724668],"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":[0.0001673688,0.0003312404,0.009644877,0.00005455595,0.0001342543,0.00008380453,0.00006105561,0.6982354,0.006346853,0.001161064,0.001203571,0.2825759],"study_design_scores_gemma":[0.000002056866,0.000006921958,0.000514066,9.24866e-7,0.000003234173,0.000003886397,0.000004221723,0.9987218,0.0003890799,0.0003029976,0.00004859783,0.000002164071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1473801,0.0003074052,0.8500016,0.0001876813,0.00003692616,0.00003506932,0.0001442227,0.00129737,0.0006096394],"genre_scores_gemma":[0.8156809,0.0001129473,0.1826402,0.0001194835,0.0000512426,0.00005728717,0.0005755314,0.00007476631,0.0006876779],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007313772,"threshold_uncertainty_score":0.0145424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009501941864075335,"score_gpt":0.2304402044661698,"score_spread":0.2209382626020945,"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."}}