ISW-Agent：LLM 对话驱动 n8n 工作流处理内孤立波遥感图像

ISW-Agent: Integrating LLM-Driven Dialogue with n8n Workflow for Internal Solitary Wave Remote Sensing Image Processing

AI 导读

ISW-Agent 将 LLM 对话解析与 n8n 工作流及独立科学模型结合，用于内孤立波遥感图像处理。在每后端 120 条中文指令测试中，GPT-5.6 Sol 和 DeepSeek 均达到 94.2% 的严格任务匹配率；50 个计时场景中 39 个完成检测、提取与预测，中位耗时 48.04 秒。3,408 次故障注入测试中，重试恢复 234 个瞬时故障，输出验证拒绝 234 个结构缺陷。

正文 · 原文

View PDF HTML (experimental)

Abstract:Internal solitary wave (ISW) remote sensing requires task parameters and spatial information to be transferred across image acquisition, detection, stripe extraction, and propagation prediction. Here, we present ISW-Agent, which integrates large language model (LLM) interpretation with n8n workflows and independent scientific models through structured task constraints, geospatial transformations, and stage-specific output validation. In tests of 120 Chinese instructions per backend, GPT-5.6 Sol and DeepSeek both achieved a strict task-match rate of 94.2%, with all intents and execution decisions matching the reference. Sentinel-1 cases demonstrated continuous processing from dialogue requests to wavefront prediction for the specified scene. Of 50 timed scenes, 39 completed detection, extraction, and prediction with a median turnaround time of 48.04 s; 11 stopped after empty extraction. Across 3,408 controlled fault-injection runs, retries recovered 234 transient-failure conditions and output validation rejected 234 structural defects, while 61 provenance or completeness errors indicated the need for content-consistency checks. Overall, ISW-Agent thus connects natural-language requests to traceable spatial processing chains for multimodel ISW analysis.

Subjects:	Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.21502 [cs.AI]
	(or arXiv:2610.21502v1 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2610.21502 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Hao Zhang [view email]
[v1] Thu, 15 Oct 2026 08:38:23 UTC (7,600 KB)

来源：arXiv cs.AI · arxiv.org