Scholarlink

This study presents a systematic literature review on the use of Internet of Things (IoT) technologies in agricultural disaster early warning systems, with a focus on flood and landslide risks in upland farming regions. To enhance consistency and efficiency, ChatGPT-4 was employed to assist in thematically classifying 49 selected papers by key attributes, including IoT components, disaster types, alert methods, and agricultural contexts. The findings highlight the dominance of low-cost sensors, edge computing, and GSM/LoRa communication in rural deployments. A notable gap was identified in community-centered systems that link early warning with actionable decision-making. Based on these insights, the study proposes a conceptual framework tailored to highland farming communities in Thailand. The framework integrates real-time environmental sensing, edge AI for localized risk detection, multi-channel alerts, and post-disaster recovery planning. This research contributes methodologically by showcasing LLM-assisted analysis and practically by offering a scalable model for resilient, tech-enabled agriculture.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

ChatGPT-Assisted Review of IoT for Agricultural Disaster Early Warning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Chawis Boonmee,
  • Natthanan Promsuk,
  • Nopparuj Suetrong,
  • Nilubon Chonsawat,
  • Nuttapon Khongdee,
  • Rapeepan Pitakaso

摘要

This study presents a systematic literature review on the use of Internet of Things (IoT) technologies in agricultural disaster early warning systems, with a focus on flood and landslide risks in upland farming regions. To enhance consistency and efficiency, ChatGPT-4 was employed to assist in thematically classifying 49 selected papers by key attributes, including IoT components, disaster types, alert methods, and agricultural contexts. The findings highlight the dominance of low-cost sensors, edge computing, and GSM/LoRa communication in rural deployments. A notable gap was identified in community-centered systems that link early warning with actionable decision-making. Based on these insights, the study proposes a conceptual framework tailored to highland farming communities in Thailand. The framework integrates real-time environmental sensing, edge AI for localized risk detection, multi-channel alerts, and post-disaster recovery planning. This research contributes methodologically by showcasing LLM-assisted analysis and practically by offering a scalable model for resilient, tech-enabled agriculture.