{"id":"W4303649320","doi":"10.1038/s41598-022-19437-5","title":"RaVÆn: unsupervised change detection of extreme events using ML on-board satellites","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"Minnow Environmental (Canada); Research Canada","funders":"European Social Fund; European Regional Development Fund; University of Oxford; European Space Agency; Ministerio de Ciencia e Innovación; Institut national de recherche en informatique et en automatique (INRIA)","keywords":"Computer science; Satellite; Software deployment; Telecommunications link; Real-time computing; Event (particle physics); Change detection; Encoder; Data mining; Remote sensing; Artificial intelligence; Telecommunications","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001046033,0.0001566191,0.0001732482,0.0001052749,0.0006248583,0.00004928718,0.0001897074,0.00004772805,0.001064534],"category_scores_gemma":[0.00005567675,0.0001344515,0.0001150805,0.001120324,0.0001890202,0.0001805378,0.0002995207,0.0001676272,0.00004607127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003613699,"about_ca_system_score_gemma":0.00001604259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000375914,"about_ca_topic_score_gemma":0.00007004893,"domain_scores_codex":[0.9971839,0.0001339622,0.000412432,0.0007549821,0.001207831,0.0003069146],"domain_scores_gemma":[0.9987905,0.00002226237,0.0003552042,0.000713946,0.00002521141,0.00009288878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001171484,0.0001074895,0.01413031,0.000007966943,0.000007151311,0.0001025685,0.0008719201,0.003102635,0.9692376,0.00000114983,0.0005674404,0.01185202],"study_design_scores_gemma":[0.0004554695,0.0002965418,0.2434664,0.0000937807,0.00007778359,0.001084327,0.0009830579,0.008217315,0.625422,0.003583023,0.115368,0.0009523024],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9925318,0.00006001428,0.00003440105,0.00005589269,0.005402821,0.0004143805,0.000002822533,0.00005202685,0.001445807],"genre_scores_gemma":[0.9973266,0.000002224964,0.0008102769,0.00004964273,0.00005658218,0.000006133742,0.00001763638,0.00001624647,0.001714718],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3438157,"threshold_uncertainty_score":0.9998486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04491109908469114,"score_gpt":0.230356763147478,"score_spread":0.1854456640627868,"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."}}