EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AdaRisk-Agent: LLM-Orchestrated Adaptive Risk Calibration for Cost-Sensitive Active Learning in UAV Weed Detection

Ali Güneş

Drones · 17.07.2026 · 10 (7) · 547

DOI: 10.3390/drones10070547 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Drones, online erschienen am 17.07.2026. Verfasst von Ali Güneş. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

UAV-based weed detection in precision agriculture is constrained by asymmetric error costs: a missed weed patch causes herbicide under-treatment and yield loss, whereas a false alarm only prompts an unnecessary spot treatment. Cost-sensitive active learning (cAL) addresses this through an asymmetric misclassification penalty r+, but the optimal value is scene-dependent and cannot be determined without domain expertise or advance knowledge of scene difficulty—a fundamental barrier to autonomous UAV monitoring workflows. We propose AdaRisk-Agent, the first LLM-orchestrated framework for adaptive r+ calibration in cAL-based UAV weed detection. We validate the framework on four UAV multispectral scenes from two public datasets—WeedsGalore (Germany, five-band maize) and WeedyRice (Vietnam, four-band paddy)—spanning two crop types, two sensor configurations, and weed prevalence from 3.1% to 30.5%. Adaptive calibration reduces the false-negative rate (FNR) by up to 80% relative to symmetric-cost baselines across all scenes. The deterministic surrogate (AdaRisk-Rule) surpasses the fixed-policy oracle (cAL r+=7) on two of four scenes without advance scene knowledge, achieving a 50% FNR reduction on the most spectrally challenging scene. A context-feature ablation confirms that budget urgency is the primary calibration signal and that test-set-independent deployment is feasible. Each calibration decision is accompanied by a natural-language justification, enabling auditable deployment in operational precision agriculture workflows. Future work will extend AdaRisk-Agent to multi-class weed species detection and multi-scene meta-learning for compact offline surrogate policies.

Zitieren

APA

Güneş, A. (2026). AdaRisk-Agent: LLM-Orchestrated Adaptive Risk Calibration for Cost-Sensitive Active Learning in UAV Weed Detection. Drones, 10(7), 547. https://doi.org/10.3390/drones10070547

Vancouver

Güneş A. AdaRisk-Agent: LLM-Orchestrated Adaptive Risk Calibration for Cost-Sensitive Active Learning in UAV Weed Detection. Drones. 2026;10(7):547. doi:10.3390/drones10070547

BibTeX
@article{Gne2026,
  author = {Güneş, Ali},
  title = {AdaRisk-Agent: LLM-Orchestrated Adaptive Risk Calibration for Cost-Sensitive Active Learning in UAV Weed Detection},
  journal = {Drones},
  year = {2026},
  volume = {10},
  number = {7},
  pages = {547},
  doi = {10.3390/drones10070547}
}
Kostenlos starten →