EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ICDL-Agent: A Tool-Augmented LLM Agent for Automatic Instrument Workflows in Incoherent Doppler LiDAR Analysis

Jiawei Li, Yuli Han, Chong Chen, Tingdi Chen, Xianghui Xue, Liangyu Pu, Zhaowang Su, Hengjia Liu, Shuhua Zhang, Jing Yang, Dongsong Sun

ISPRS International Journal of Geo-Information · 26.05.2026 · 15 (6) · 238

DOI: 10.3390/ijgi15060238 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ISPRS International Journal of Geo-Information, online erschienen am 26.05.2026. Verfasst von Jiawei Li und 10 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Innovation Program for Quantum Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) offer new possibilities for natural-language interaction with geospatial analysis systems, but their use in remote sensing instrument data analysis remains limited by weak execution control, poor reproducibility, and limited integration with domain-specific computation. The paper presents an agent for Incoherent Doppler wind LiDAR (ICDL) data analysis, named ICDL-Agent, a tool-augmented LLM framework for remote sensing instrument workflows. The system maps conversational user requests to executable analysis pipelines for wind retrieval, uncertainty estimation, visualization, and higher-level diagnostics through structured planning over a registry of domain-specific tools. To improve execution reliability, the system combines schema-constrained workflow generation, shared-state reuse of intermediate scientific products, and validation with bounded repair. In addition to supporting routine LiDAR processing, the framework can generate new tools when required and adapt to related analytical tasks through domain-aware guidance and procedural documentation. We evaluate the system on multiple atmospheric wind-observation datasets in China and show that it faithfully reproduces the refined Doppler wind-retrieval pipeline, achieving representative R2/MAE values of 0.52/3.73 m/s against ERA5 and 0.80/2.31 m/s against radiosonde observations, while supporting downstream analyses such as profile comparison, climatological interpretation, and gravity-wave diagnostics. More broadly, this study demonstrates how constrained LLM orchestration can support LiDAR researchers, remote-sensing instrument teams, and geospatial analysts seeking transparent, reproducible, and automated scientific data-processing workflows.

Förderung

  • National Natural Science Foundation of China
  • Innovation Program for Quantum Science and Technology

Zitieren

APA

Li, J., Han, Y., Chen, C., Chen, T., Xue, X., Pu, L., Su, Z., Liu, H., Zhang, S., Yang, J., & Sun, D. (2026). ICDL-Agent: A Tool-Augmented LLM Agent for Automatic Instrument Workflows in Incoherent Doppler LiDAR Analysis. ISPRS International Journal of Geo-Information, 15(6), 238. https://doi.org/10.3390/ijgi15060238

Vancouver

Li J, Han Y, Chen C, Chen T, Xue X, Pu L, et al. ICDL-Agent: A Tool-Augmented LLM Agent for Automatic Instrument Workflows in Incoherent Doppler LiDAR Analysis. ISPRS International Journal of Geo-Information. 2026;15(6):238. doi:10.3390/ijgi15060238

BibTeX
@article{Li2026,
  author = {Li, Jiawei and Han, Yuli and Chen, Chong and Chen, Tingdi and Xue, Xianghui and Pu, Liangyu and Su, Zhaowang and Liu, Hengjia and Zhang, Shuhua and Yang, Jing and Sun, Dongsong},
  title = {ICDL-Agent: A Tool-Augmented LLM Agent for Automatic Instrument Workflows in Incoherent Doppler LiDAR Analysis},
  journal = {ISPRS International Journal of Geo-Information},
  year = {2026},
  volume = {15},
  number = {6},
  pages = {238},
  doi = {10.3390/ijgi15060238}
}
Kostenlos starten →