{"id":"W4415011750","doi":"10.1016/j.isprsjprs.2025.09.022","title":"Prior knowledge-informed semantic segmentation framework for precise glacial lake mapping from multimodal imagery","year":2025,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Cryospheric studies and observations","field":"Earth and Planetary Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council; National Natural Science Foundation of China; Medical Research Centre; Chinese Academy of Sciences; University of Alberta","keywords":"Glacial period; Segmentation; Feature (linguistics); Encoder; Dice; Deep learning; Pattern recognition (psychology); Glacial lake","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003198266,0.0001484195,0.000307316,0.0001250452,0.0004521494,0.000126921,0.00008262288,0.0001014932,0.00004715972],"category_scores_gemma":[0.0004986298,0.0001206059,0.0001516144,0.0004090762,0.00008482209,0.0001759382,0.00001661871,0.0002230176,0.000002085076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000121295,"about_ca_system_score_gemma":0.0001035427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009804456,"about_ca_topic_score_gemma":0.005518751,"domain_scores_codex":[0.9989171,0.0000437591,0.0004888234,0.0001585464,0.000145028,0.0002467212],"domain_scores_gemma":[0.998163,0.001190323,0.0002821882,0.00008904326,0.0001846324,0.00009076557],"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":[0.0001619708,0.00001273537,0.008842361,0.00007045626,0.0001268791,0.000009740461,0.001227844,0.0001383505,0.0003469974,0.000002866993,0.0001873214,0.9888725],"study_design_scores_gemma":[0.004099392,0.0003560965,0.5520445,0.002588464,0.0005612012,0.00009424384,0.01424826,0.3701951,0.004103345,0.01555591,0.03544071,0.0007128112],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5313222,0.001851414,0.4647492,0.0002117398,0.001416258,0.0002233115,0.0000242536,0.00001305757,0.0001885918],"genre_scores_gemma":[0.6540251,0.0004974336,0.3446644,0.0002633106,0.0004557069,4.231613e-8,0.0000255573,0.000004889709,0.00006356608],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9881597,"threshold_uncertainty_score":0.4918166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0204688143118309,"score_gpt":0.2833562501136419,"score_spread":0.262887435801811,"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."}}