{"id":"W2751979613","doi":"10.1080/07038992.2017.1370367","title":"Mapping Arctic Coastal Ecosystems with High Resolution Optical Satellite Imagery Using a Hybrid Classification Approach","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Remote Sensing","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Tundra; Remote sensing; Land cover; Arctic; Satellite imagery; Pixel; Wetland; Random forest; Terrain; Geography; Cartography; Environmental science; Computer science; Land use; Geology; Artificial intelligence; Ecology; Oceanography","routes":{"ca_aff":true,"ca_fund":false,"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":[0.000552221,0.0005212469,0.0003511119,0.003219338,0.00030162,0.0008991302,0.0004161254,0.0003327721,0.0004390144],"category_scores_gemma":[0.0005254794,0.0002804392,0.0006922883,0.001528284,0.0001896977,0.0006654499,0.0004493163,0.0002067765,0.0002243404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003313365,"about_ca_system_score_gemma":0.0003798152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01136093,"about_ca_topic_score_gemma":0.02104861,"domain_scores_codex":[0.9996406,0.00006264987,0.00002299385,0.00008989049,0.000133822,0.00005002468],"domain_scores_gemma":[0.9996624,0.00006898311,0.00005256338,0.00004092999,0.0001546924,0.00002047713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002417887,0.0002650171,0.04391581,0.0001689485,0.0003370474,0.0002066466,0.000257434,0.07311153,0.09563603,0.0007152009,0.0009459939,0.7841986],"study_design_scores_gemma":[0.00002452665,0.0001294975,0.06137059,0.00002864034,0.0001743389,0.00024489,0.0002942851,0.9148563,0.02020449,0.0008036703,0.001812329,0.00005653869],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4470296,0.0005323771,0.5469158,0.0001146512,0.00004126041,0.000138028,0.0004240938,0.001561681,0.003242622],"genre_scores_gemma":[0.6719841,0.0002155582,0.3261111,0.00005893939,0.00002780947,0.00007989098,0.0004331494,0.00003990945,0.001049557],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01136093,"threshold_uncertainty_score":0.02258956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06699418352352655,"score_gpt":0.2326477009496956,"score_spread":0.1656535174261691,"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."}}