{"id":"W4362703713","doi":"10.1016/j.jag.2023.103287","title":"Towards transparent deep learning for surface water detection from SAR imagery","year":2023,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Flood Risk Assessment and Management","field":"Environmental Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"TD Bank Group","funders":"Shaanxi Key Science and Technology Innovation Team Project; Fundamental Research Funds for the Central Universities; National University's Basic Research Foundation of China; National Natural Science Foundation of China","keywords":"Computer science; Deep learning; Artificial intelligence; Visualization; Artificial neural network; Analytics; Domain (mathematical analysis); Pattern recognition (psychology); Remote sensing; Machine learning; Data mining; Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.000366821,0.00008356948,0.00009478847,0.00008045362,0.00009393581,0.00009727198,0.0001139456,0.00003809037,0.0001898824],"category_scores_gemma":[0.000009448174,0.00006635532,0.00005110198,0.00008472488,0.00001986415,0.0007754065,0.00004477943,0.00008847892,0.00009454605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004875789,"about_ca_system_score_gemma":0.00000499186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006669171,"about_ca_topic_score_gemma":0.00006113004,"domain_scores_codex":[0.9990209,0.00001037895,0.0003744115,0.00008394451,0.0003915885,0.0001187999],"domain_scores_gemma":[0.9996205,0.00003329986,0.0002008959,0.00004155437,0.0000622533,0.00004152314],"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":[0.0003692601,0.00003308917,0.004790866,0.0000171942,0.0001272413,0.000002059272,0.003336504,0.4949386,0.03027376,0.0002204688,0.0004577377,0.4654333],"study_design_scores_gemma":[0.002364814,0.0001530857,0.2769329,0.00002486362,0.00006518251,0.000003981245,0.001855431,0.5734544,0.05064295,0.003818206,0.09042425,0.000259922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8957955,0.000005228674,0.101848,0.0007576143,0.0004110083,0.000171452,0.000003535326,0.00003374359,0.0009739567],"genre_scores_gemma":[0.9945023,0.00015757,0.004698686,0.0002102891,0.00009969389,0.00000492111,0.0001817468,0.000006696748,0.0001380784],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4651734,"threshold_uncertainty_score":0.2705891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01799462991705344,"score_gpt":0.2410436007383657,"score_spread":0.2230489708213122,"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."}}