{"id":"W3005510284","doi":"10.3390/rs12030500","title":"Deep Learning in Archaeological Remote Sensing: Automated Qanat Detection in the Kurdistan Region of Iraq","year":2020,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Archaeological Research and Protection","field":"Earth and Planetary Sciences","cited_by":107,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institutes of Health; National Geographic Society; National Science Foundation","keywords":"Satellite imagery; Remote sensing; Convolutional neural network; Deep learning; Spectral signature; Geology; Computer science; Archaeology; Artificial intelligence; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009248258,0.0001442351,0.000242952,0.0001527646,0.0001632814,0.00002056132,0.0001375854,0.0001531349,0.00002373556],"category_scores_gemma":[0.001566961,0.0001009257,0.00006921878,0.0008997527,0.0002600074,0.0000884343,0.00003906709,0.0008375685,0.00002081114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002005541,"about_ca_system_score_gemma":0.00002726341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006459075,"about_ca_topic_score_gemma":0.01205757,"domain_scores_codex":[0.9973749,0.001121653,0.0003418222,0.0003390067,0.0003804188,0.000442228],"domain_scores_gemma":[0.999063,0.0005260333,0.0001151852,0.0001338446,0.00004497366,0.0001170158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003009739,0.000001371967,0.001011887,0.00002584335,0.000003766972,0.0004478938,0.001723105,0.0148017,0.001208417,0.00000262391,0.000002123784,0.9804703],"study_design_scores_gemma":[0.0002377152,0.0003768633,0.04339341,0.00005235114,0.000003193047,0.0001638586,0.0007541064,0.9502842,0.0005521856,0.003800645,0.0002683701,0.0001131209],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.867135,0.0001857203,0.128618,0.002192884,0.00004994794,0.0003165156,5.016498e-7,0.0001562223,0.001345111],"genre_scores_gemma":[0.9909941,0.0001238716,0.008524138,0.0002597308,0.00007481494,2.630049e-9,0.00001156551,0.00000444128,0.000007316894],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9803572,"threshold_uncertainty_score":0.9764231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04034062495677643,"score_gpt":0.2628124957324371,"score_spread":0.2224718707756607,"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."}}