Farm-LightSeek: An Edge-centric Multimodal Agricultural IoT Data Analytics Framework with Lightweight LLMs

2025-05-28

AI Summary

To address challenges in smart agriculture—including latency-sensitive edge decision-making, weak multimodal data fusion, poor dynamic adaptability, and heavy reliance on expert knowledge—this paper proposes an edge-first multimodal IoT analytics framework. We introduce a novel “perception–decision–execution” closed-loop architecture, featuring a cross-modal adaptive monitoring mechanism and a lightweight large language model (LLM) deployment strategy optimized for resource-constrained edge devices. By fusing field imagery, meteorological, and geospatial data directly at the edge, our framework enables low-latency crop disease detection and closed-loop control, while supporting cloud-edge collaborative model updates. Evaluated on two real-world agricultural datasets, our approach reduces inference latency by 42%, compresses the LLM to 8.3% of its original size, and maintains high stability and decision accuracy under stringent resource constraints.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Amid the challenges posed by global population growth and climate change, traditional agricultural Internet of Things (IoT) systems is currently undergoing a significant digital transformation to facilitate efficient big data processing. While smart agriculture utilizes artificial intelligence (AI) technologies to enable precise control, it still encounters significant challenges, including excessive reliance on agricultural expert knowledge, difficulties in fusing multimodal data, poor adaptability to dynamic environments, and bottlenecks in real-time decision-making at the edge. Large language models (LLMs), with their exceptional capabilities in knowledge acquisition and semantic understanding, provide a promising solution to address these challenges. To this end, we propose Farm-LightSeek, an edge-centric multimodal agricultural IoT data analytics framework that integrates LLMs with edge computing. This framework collects real-time farmland multi-source data (images, weather, geographic information) via sensors, performs cross-modal reasoning and disease detection at edge nodes, conducts low-latency management decisions, and enables cloud collaboration for model updates. The main innovations of Farm-LightSeek include: (1) an agricultural"perception-decision-action"closed-loop architecture; (2) cross-modal adaptive monitoring; and (3)a lightweight LLM deployment strategy balancing performance and efficiency. Experiments conducted on two real-world datasets demonstrate that Farm-LightSeek consistently achieves reliable performance in mission-critical tasks, even under the limitations of edge computing resources. This work advances intelligent real-time agricultural solutions and highlights the potential for deeper integration of agricultural IoT with LLMs.

Problem

• Addresses reliance on expert knowledge in smart agriculture
• Solves multimodal data fusion challenges in farming IoT
• Improves edge-based real-time decision-making for agriculture

Innovation

• Edge-centric multimodal data analytics framework
• Lightweight LLMs for agricultural IoT
• Closed-loop perception-decision-action architecture