{"id":"W4375928869","doi":"10.1109/tim.2023.3273689","title":"PEAMATL: A Strategy for Developing Near-Infrared Spectral Prediction Models Under Domain Shift Using Self-Supervised Transfer Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; National Key Research and Development Program of China; Higher Education Discipline Innovation Project; China Scholarship Council; National Natural Science Foundation of China","keywords":"Transfer of learning; Artificial intelligence; Computer science; Infrared; Machine learning; Pattern recognition (psychology); Physics; Optics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003595639,0.0002235786,0.0001672256,0.0002298288,0.0004360852,0.0001738659,0.00005098533,0.0001038616,0.000009170257],"category_scores_gemma":[0.000002103357,0.0002560416,0.00007958624,0.0003422275,0.00003222267,0.0004295612,5.235299e-7,0.0001935507,0.000007723607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005831849,"about_ca_system_score_gemma":0.0001061498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001394534,"about_ca_topic_score_gemma":0.0000302686,"domain_scores_codex":[0.9985591,0.00006333627,0.0003738758,0.0002880249,0.0004123946,0.0003033231],"domain_scores_gemma":[0.9996371,0.00002760697,0.00002835669,0.0001235467,0.00009852133,0.00008488427],"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":[0.00004599142,0.00002898261,0.000007464461,0.0001296539,0.0001211274,6.667628e-7,0.002250207,0.9143527,0.06800853,0.0001624908,0.00001383829,0.01487836],"study_design_scores_gemma":[0.001600734,0.00009247733,0.0006833258,0.0001035885,0.00008293553,0.000006795102,0.001646577,0.9625381,0.0320987,0.0008127654,0.0000814413,0.0002525294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3879654,0.000009166076,0.6104332,0.00007920185,0.000326601,0.0004719133,0.00001348924,0.0005842282,0.000116827],"genre_scores_gemma":[0.9826737,0.00008957988,0.01698394,0.00003067766,0.00003604783,0.00007067792,0.00002920293,0.0000620939,0.00002405203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5947083,"threshold_uncertainty_score":0.9999892,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09018907852131385,"score_gpt":0.2661405498034173,"score_spread":0.1759514712821034,"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."}}