GRAIL: AI translation for scientists application workflow on satellite data
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917528570167296 |
|---|---|
| author | Shang, Zhuocheng Eldawy, Ahmed |
| author_facet | Shang, Zhuocheng Eldawy, Ahmed |
| contents | Domain scientists increasingly develop Python scripts to analyze satellite imagery but they lack scalability to large-scale data. This paper demonstrates GRAIL, an agentic translation system that converts Python geospatial workflows into executable Spark-based programs without requiring scientists to learn a new framework. Rather than fine-tuning a specialized LLM model, GRAIL adapts RDPro, a Scala library for satellite data analysis, to make it LLM-ready using structured documentation, API alias functions, and repair-oriented error logs. Translation is structured as a LangGraph pipeline that decomposes code generation into explicit sections with guided inputs and outputs, enabling targeted repair without regenerating the full program. We demonstrate GRAIL on real-world geospatial workflows and showcase the correctness and scalability of the translated code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_24784 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GRAIL: AI translation for scientists application workflow on satellite data Shang, Zhuocheng Eldawy, Ahmed Artificial Intelligence Domain scientists increasingly develop Python scripts to analyze satellite imagery but they lack scalability to large-scale data. This paper demonstrates GRAIL, an agentic translation system that converts Python geospatial workflows into executable Spark-based programs without requiring scientists to learn a new framework. Rather than fine-tuning a specialized LLM model, GRAIL adapts RDPro, a Scala library for satellite data analysis, to make it LLM-ready using structured documentation, API alias functions, and repair-oriented error logs. Translation is structured as a LangGraph pipeline that decomposes code generation into explicit sections with guided inputs and outputs, enabling targeted repair without regenerating the full program. We demonstrate GRAIL on real-world geospatial workflows and showcase the correctness and scalability of the translated code. |
| title | GRAIL: AI translation for scientists application workflow on satellite data |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.24784 |