{"id":"W4390450474","doi":"10.1016/j.jag.2023.103616","title":"Retrieving freeze-thaw states using deep learning with remote sensing data in permafrost landscapes","year":2023,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"China Scholarship Council; Ludwig-Maximilians-Universität München; Bundesministerium für Bildung und Forschung; European Space Agency","keywords":"Permafrost; Remote sensing; Transferability; Convolutional neural network; Cryosphere; Environmental science; Deep learning; Physical geography; Computer science; Machine learning; Geography; Ecology; Meteorology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.0004548079,0.0006694662,0.0003079925,0.001097662,0.0002796977,0.0004594272,0.0007729609,0.000532466,0.0003502314],"category_scores_gemma":[0.0009047622,0.0002389189,0.000480509,0.0009056368,0.0002830798,0.0006950675,0.0004173804,0.0004152491,0.0001071642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00101412,"about_ca_system_score_gemma":0.0006637691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07730786,"about_ca_topic_score_gemma":0.08895559,"domain_scores_codex":[0.9998498,0.00001974734,0.000009684512,0.00004993751,0.00002800373,0.00004277693],"domain_scores_gemma":[0.9997635,0.00006924855,0.00003702541,0.00002659442,0.00007583309,0.00002780652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0003906434,0.0004940388,0.1837825,0.0001496359,0.0002219473,0.0006041446,0.0002399697,0.6606678,0.01384878,0.0004442203,0.002506881,0.1366493],"study_design_scores_gemma":[0.00001492222,0.00001978819,0.03798186,0.00001413939,0.00002147955,0.00002006136,0.0001054626,0.9591005,0.002127097,0.0002979308,0.0002819714,0.00001478735],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9921688,0.0003456883,0.005686832,0.0001170569,0.0000200831,0.00001762854,0.0006786368,0.0003073453,0.0006578769],"genre_scores_gemma":[0.9937033,0.00008302945,0.004763406,0.00003238785,0.000009356666,0.000009186409,0.001190378,0.00001025987,0.0001988067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07730786,"threshold_uncertainty_score":0.1537157,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0483306476712165,"score_gpt":0.2602677084353187,"score_spread":0.2119370607641022,"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."}}