A Flexible Sensor-Enabled Multi-Parameter Collaborative Monitoring System for Precision Agriculture with Field Validation

Abstract

Real-time and accurate monitoring of farmland environmental parameters and crop growth status is essential for precision agriculture and intelligent irrigation management. However, conventional agricultural monitoring approaches remain limited in spatial coverage, sensor adaptability, and intelligent data analysis. To address these limitations, this study proposes a multi-parameter collaborative monitoring system for precision agriculture that integrates flexible sensing, LoRa-based wireless communication, and deep learning-based data analysis. Specifically, a flexible capacitive humidity sensor based on graphene-PDMS composites was designed and fabricated for farmland environmental monitoring, and a distributed LoRa sensor network was developed to enable large-scale multi-parameter data acquisition and remote transmission. In addition, a convolutional neural network (CNN) was established for feature extraction and crop disease identification using multimodal sensor data. Experimental results showed that the flexible sensor exhibited a response time of 2.3 s and good mechanical stability, while the proposed model achieved an accuracy of 97.1% for crop disease identification on the test set. Field experiments conducted in 12 test fields across Hebei, Shandong, and Henan provinces showed that the proposed system achieved an average water-saving rate of 32.8% and an average crop yield increase of 10.6%. These results demonstrate that the proposed system can effectively improve farmland monitoring accuracy and support intelligent irrigation decision-making, highlighting its application potential in smart agriculture.

Plant phenotyping relevance

作物病害識別を含むマルチモーダルセンサ計測・CNN解析システムの開発と実証が中心で、植物の病害状態を推定するフェノタイピング手法に該当する。

Code and data availability

公開論文であることは確認できましたが、現在の公式API・許可済み取得経路では本文を自動取得できませんでした。

No evidence-backed public reproduction asset is currently recorded.