Rapid Agrichemical Inventory via Video Documentation and Large Language Model Identification

TL;DR

This paper introduces a method using video and AI to quickly identify agrichemicals in limited time, improving exposure assessments in field research.

Contribution

A novel approach using LLMs to identify agrichemicals from video footage in time-limited field settings.

Findings

LLM correctly identified 75% of agrichemicals from video screenshots.

The method supports rapid data collection when researcher access is limited.

Human validation improved accuracy and corrected LLM errors.

Abstract

Background: This technical note presents a methodological approach to agrichemical inventory documentation. It complements exposure assessments in field settings with time-restricted observational periods. Conducted in Michoacán, Mexico, this method leverages large language model (LLM) capabilities for categorizing agrichemicals from brief video footage. Method: Given time-limited access to a storage shed housing various agrichemicals, a short video was recorded and processed into 31 screenshots. Using OpenAI’s ChatGPT (model: GPT-4o®), agrichemicals in each image were identified and categorized as fertilizers, herbicides, insecticides, fungicides, or other substances. Results: Human validation revealed that the LLM accurately identified 75% of agrichemicals, with human verification correcting entries. Conclusions: This rapid identification method builds upon behavioral methods of exposure assessment, facilitating initial data collection in contexts where researcher access to hazardous materials may be time limited and would benefit from the efficiency and cross-validation offered by this method. Further refinement of this LLM-assisted approach could optimize accuracy in the identification of agrichemical products and expand its application to complement exposure assessments in field-based research, particularly as LLM technologies rapidly evolve. Most importantly, this Technical Note illustrates how field researchers can strategically harness LLMs under real-world time constraints, opening new possibilities for rapid observational approaches to exposure assessment.

Figures