{"id":"W2913828382","doi":"10.1080/07038992.2018.1540297","title":"Shelterbelt Agroforestry Systems Inventory and Removal Analyzed by Object-based Classification of Satellite Data in Saskatchewan, Canada","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Aeolian processes and effects","field":"Earth and Planetary Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Agriculture and Agri-Food Canada; University of Saskatchewan","keywords":"Windbreak; Land cover; Synthetic aperture radar; Remote sensing; Satellite imagery; Geography; Random forest; Vegetation (pathology); Environmental science; Forestry; Land use; Computer science; Agroforestry; Artificial intelligence; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":true,"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":[0.0004716228,0.0004062325,0.0002922771,0.002299323,0.000935155,0.00116983,0.0007367335,0.0002094064,0.001123334],"category_scores_gemma":[0.0008488023,0.0002472371,0.0002830572,0.004526962,0.0004843931,0.0003378235,0.000551709,0.0002830367,0.0003246806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01244219,"about_ca_system_score_gemma":0.01597838,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9896762,"about_ca_topic_score_gemma":0.9964144,"domain_scores_codex":[0.9996027,0.00002186149,0.00002071427,0.00007506717,0.0001686494,0.000110976],"domain_scores_gemma":[0.9985635,0.00008451677,0.000118775,0.00006187343,0.001045915,0.0001254779],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009344624,0.00005371224,0.9490044,0.00006073777,0.00009422335,0.0002138157,0.0006961694,0.003315871,0.004964409,0.0001900494,0.00166281,0.0396503],"study_design_scores_gemma":[0.000006686587,0.000008458097,0.9876084,0.00003148312,0.00002560536,0.00003791889,0.001317041,0.008261473,0.0009142174,0.00003415261,0.001738607,0.00001593543],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935742,0.0001647037,0.0006586341,0.0000522752,0.000004612982,0.00006425704,0.003418841,0.00004144306,0.002020943],"genre_scores_gemma":[0.9872512,0.0003785726,0.003162525,0.0000435818,0.000002565305,0.00005224423,0.006597041,0.00002147494,0.002490932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01244219,"threshold_uncertainty_score":0.09027481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01460348939989059,"score_gpt":0.2044508715302265,"score_spread":0.1898473821303359,"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."}}