物联网与深度学习在茶园白蚁（Postelectrotermes militaris，俗称高地活木白蚁ULWT）检测及严重程度评估中的有效性
Effectiveness of IoT and Deep Learning for Detection and Severity Assessment of Postelectrotermes militaris in Tea Plantations
另 2 家 · 查看机构详情
- Sri Lanka Institute of Information Technology（斯里兰卡信息技术学院）
- School of Molecular and Life Sciences, Curtin University（科廷大学分子与生命科学学院）
- University of Kelaniya（凯拉尼亚大学）
- Tea Research Institute of Sri Lanka（斯里兰卡茶叶研究所）
- Murdoch University（默多克大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本研究提出集成深度学习的物联网声学监测框架，利用CNN结合多维度指标实现茶园高地活木白蚁的早期检测与严重程度评估，田间试验验证了其可行性，可辅助茶园虫害管理
中文摘要 AI 辅助
茶园易受Postelectrotermes militaris（俗称高地活木白蚁，ULWT）侵害，若未检测到虫害，会造成重大损失。本研究提出一种集成深度学习的物联网声学监测框架，用于茶园ULWT虫害的早期检测与严重程度评估。研究方法：使用连接于树莓派（Raspberry Pi）物联网设备的高灵敏度麦克风，从茶树干无创采集音频信号，同时记录地理坐标以实现空间追踪。经修剪、重采样和分割后，获得2000个10秒样本，其中健康样本与虫害样本各1000个，按1600、200、200的比例划分为训练集、验证集和测试集。本研究使用的数据集公开于Kaggle（Senevirathna等人，2026）。基于傅里叶变换生成的频谱图，训练卷积神经网络（CNN）用于虫害分类与概率估计。加权严重程度模型结合CNN概率、平均声振幅以及5米范围内的邻近虫害植株，利用地理空间制图可视化虫害分布。研究结果与价值：在Pundaluoya一处受ULWT侵害的茶园开展的田间试验，证明了该框架在实际环境噪声下的可行性。在保留的测试集上，CNN取得了81.5%的准确率、80.6%的精确率、83.0%的召回率、81.8%的F1值以及0.819的ROC-AUC。除二元虫害检测外，该框架还通过虫害概率、声振幅和邻近虫害植株引入了定量严重程度评估。生成的严重程度与地理空间输出可支持茶园管理者识别高风险区域、优先安排田间检查，并实施更及时、更具针对性的防治措施。
英文摘要
Tea plantations are vulnerable to Postelectrotermes militaris, commonly known as the Upcountry Live Wood Termite (ULWT), which can cause substantial damage when infestations remain undetected. This study proposes an IoT-enabled acoustic monitoring framework integrated with deep learning for early detection and severity assessment of ULWT infestations in tea plantations. Research Method: Audio signals were captured non-invasively from tea trunks using a high-sensitivity microphone connected to a Raspberry Pi-based IoT device, with geographic coordinates recorded for spatial tracking. After trimming, resampling, and segmentation, 2,000 ten-second samples were obtained, comprising 1,000 healthy and 1,000 infested samples, and divided into 1,600 training, 200 validation, and 200 test samples. The dataset used in this study is publicly available on Kaggle (Senevirathna et al. 2026). Fourier-derived spectrograms trained a CNN for infestation classification and probability estimation. A weighted severity model combined CNN probability, mean acoustic amplitude, and nearby infested plants within 5 m, with geospatial mapping used to visualize infestation distribution. Findings and Values: Field trials in a ULWT-affected tea plantation in Pundaluoya demonstrated feasibility under realistic environmental noise. On the held-out test set, the CNN achieved 81.5% accuracy, 80.6% precision, 83.0% recall, 81.8% F1-score, and 0.819 ROC-AUC. Beyond binary infestation detection, the framework introduced quantitative severity assessment using infestation probability, acoustic amplitude, and nearby infested plants. The resulting severity and geospatial outputs can support plantation managers in identifying high-risk areas, prioritizing field inspections, and implementing more timely and targeted control measures.
