{"id":"W4411635855","doi":"10.1016/j.isprsjprs.2025.06.012","title":"STANet-TLA: leveraging deep learning and prior knowledge for large-scale soybean breeding plot segmentation and high-yielding variety screening from UAV time-series data","year":2025,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ministry of Agriculture","funders":"State Key Laboratory for Agrobiotechnology; Young Elite Scientists Sponsorship Program by Tianjin; Jiangsu Provincial Key Research and Development Program; Innovation and Technology Fund; Fundamental Research Funds for the Central Universities; China Association for Science and Technology; Natural Science Foundation of Jiangsu Province; Guangzhou University; National Natural Science Foundation of China","keywords":"Segmentation; Scale (ratio); Series (stratigraphy); Plot (graphics); Variety (cybernetics); Computer science; Artificial intelligence; Machine learning; Pattern recognition (psychology); Geography; Statistics; Cartography; Mathematics; Biology","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":[0.0007331787,0.0001905789,0.0003407959,0.00005198138,0.0008085581,0.0003254513,0.0001134846,0.000121666,0.000007599785],"category_scores_gemma":[0.0001446618,0.0000911793,0.00005884216,0.0002822162,0.00005918355,0.0004130055,0.000202654,0.0003107502,1.956398e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001687988,"about_ca_system_score_gemma":0.000009160794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003788935,"about_ca_topic_score_gemma":0.0006161332,"domain_scores_codex":[0.9987836,0.00009248913,0.0003661105,0.0003297114,0.0001401063,0.0002879776],"domain_scores_gemma":[0.9988597,0.0005929501,0.0002540257,0.0000464901,0.0001308345,0.0001159947],"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":[0.0001077867,0.00001478098,0.002328438,0.00003042198,0.00008778208,0.000007333889,0.0007684036,0.000003867557,0.2232882,0.000004283948,0.00008761662,0.773271],"study_design_scores_gemma":[0.01055036,0.003435124,0.1626794,0.007466879,0.002777646,0.001518748,0.1351395,0.3780064,0.1589035,0.004930825,0.1312479,0.0033438],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9444836,0.002939667,0.05156761,0.0004838294,0.0002360685,0.000177947,0.00002088332,0.00003073931,0.0000596827],"genre_scores_gemma":[0.9475475,0.0005296998,0.05105962,0.0001199971,0.0005687648,7.815737e-8,0.00007537138,0.000003458051,0.00009550031],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7699273,"threshold_uncertainty_score":0.6218857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01768406462357609,"score_gpt":0.2512873734908848,"score_spread":0.2336033088673087,"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."}}