{"id":"W4409814276","doi":"10.1016/j.procs.2025.03.118","title":"A Multimodal UAV-Based Pipeline for Precision Agriculture: Aerial Stress Detection with YOLO and High-Fidelity Disease Classification Using DeiT","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Pipeline (software); High fidelity; Artificial intelligence; Precision agriculture; Fidelity; Computer vision; Remote sensing; Agriculture; Operating system; Telecommunications; Geology","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":[0.0003266321,0.0001651852,0.0001405394,0.00003143289,0.0006059259,0.0002726607,0.0002886338,0.00005705545,0.00000206721],"category_scores_gemma":[0.00007864531,0.0000584099,0.00004111512,0.0008365854,0.00017094,0.000337816,0.00009229963,0.00007814918,8.644869e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005028035,"about_ca_system_score_gemma":0.00006084319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009234127,"about_ca_topic_score_gemma":0.0003397761,"domain_scores_codex":[0.9985945,0.00003627266,0.0001984933,0.0006198808,0.000277083,0.0002737964],"domain_scores_gemma":[0.9991456,0.0001359713,0.0001076965,0.00007133379,0.0003856213,0.0001537973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0003992704,0.0002670969,0.01506523,0.00007181187,0.000007758901,0.000001497632,0.00007250818,0.001285941,0.6382501,0.0001786209,0.0002262615,0.3441739],"study_design_scores_gemma":[0.0005500987,0.0001844465,0.617763,0.0001223156,0.00003995202,0.000002528144,0.00003405249,0.3469734,0.0332787,0.0002750874,0.0005253943,0.0002509806],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8630866,0.00004897475,0.1351856,0.0006283101,0.000337418,0.0005914913,0.00003026747,0.00008168496,0.0000096569],"genre_scores_gemma":[0.9901221,0.000003233589,0.008974529,0.0002255248,0.0005702484,0.00004885374,0.00004228661,7.627191e-7,0.00001243758],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6049713,"threshold_uncertainty_score":0.4660354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0160433067794123,"score_gpt":0.2346813115739796,"score_spread":0.2186380047945674,"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."}}