cs.AIAug 22, 2026

Effectiveness of IoT and Deep Learning for Detection and Severity Assessment of Postelectrotermes militaris in Tea Plantations

Authors: D. K. C. Senevirathna, A. A. E. Nanayakkara, H. M. C. K. Kulathunga, J. K. D. P. Nadula, R. M. Mapatuna, Malithi Nawarathne, Jaliya L. Wijayaraja, P. D. Senanayake, 

Organizations: Sri Lanka Institute of Information Technology, New Kandy Road, Malabe, Sri Lanka · University of Kelaniya, Kandy Road, Dalugama, Kelaniya, Sri Lanka · Tea Research Institute of Sri Lanka, Talawakelle, Sri Lanka · Murdoch University, 90 South St, Murdoch, Perth, Western Australia, Australia

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

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.

Figures & tables

Figure 1: (A) Concealed ULWT infestation in a visually healthy tea bush. (B) Internal trunk and root damage caused by heartwood galleries.
Figure 2: ULWT-affected plantation area following removal of infested tea bushes, showing Mana grass ( Glyceria ) cultivation implemented to reduce termite activity before replanting.
Ref.CropDetection taskMethodPerformance
Kadethankar et al. (2021)CoconutPest detectionCNN, Faster R-CNN84.64%
Kong et al. (2022)Multi-cropPest detectionDeep learning, Fe-Net85.29%
Hewawitharana et al. (2023)TeaDisease detectionCNN, YOLOv8, Mask R-CNN98% recall
Wanninayake et al. (2023)RiceDisease & pest detectionYOLOv5, CNN, ML89–99%
Chen et al. (2024)TeaPest detectionMAM-IncNet81.44% recall
He et al. (2024)TeaPest detectionYOLOv7, SSD, R-CNN+2.58% mAP
Table 1: Representative vision-based deep learning systems relevant to pest and disease detection.
Ref.Target crop/materialDetection taskMethodReported accuracy
Nanda et al. (2019)WoodSubterranean termite detectionLSTM-based deep learning97.16%
Escola et al. (2020)CoffeeCicadid pest detectionSVM96.91%
Ali et al. (2023)Agricultural cropsClassification of 10 pest speciesCNN–BiLSTM98.91%
Ekramirad et al. (2023)ApplesCodling moth detectionAdaBoost94.00%
Torky et al. (2023)Agricultural cropsRed palm weevil detectionVGGish, SVM, DT, NB, LR, and DL models94.50%
Shetty and Kumar (2025)Agricultural cropsCicada, beetle, termite, and cricket classificationXGBoost, Random Forest, KNN97.00%
Table 2: Representative acoustic and sensor-based approaches for pest infestation detection.
Figure 3: Overview of the proposed AI–IoT framework for acoustic-based ULWT infestation detection in tea plantations, integrating trunk-level acoustic data acquisition and preprocessing, deep learning-based infestation classification, severity estimation, user notification, and geospatial visualization for spread monitoring.
ConditionLocationClassTypeTotalTrainValTest
Infested & HealthyPundaluoyaHealthyCollected2001602020
   Segmented8006408080
  InfestedCollected2001602020
   Segmented8006408080
Table 3: Audio dataset composition for ULWT detection.
Figure 4: Architecture of the IoT-based audio acquisition device used for capturing acoustic signals from tea trunks.
Figure 5: Internal components (A) and assembled prototype (B) of the proposed IoT device for acoustic data acquisition.
Figure 6: Training and validation performance curves of the CNN-based ULWT infestation classification model using Fourier-derived spectrogram representations: (A) accuracy and (B) loss.
Figure 7: Performance evaluation of the CNN-based ULWT infestation classification model on the held-out test set: (A) ROC curve and (B) confusion matrix.
More in this topic

Passive Acoustic Monitoring

Passive acoustic monitoring uses unattended microphones and hydrophones to detect, classify, and track wildlife and other sounds over time.

See all 38 papers

Explore similar work

CardsList
Apr 9, 2026

DeepForestSound: a multi-species automatic detector for passive acoustic monitoring in African tropical forests, a case study in Kibale National Park

Passive Acoustic Monitoring (PAM) is widely used for biodiversity assessment. Its application in African tropical forests is limited by scarce annotated data, reducing the performance of general-purpose ecoacoustic models on underrepresented taxa. In this study, we introduce DeepForestSound (DFS), a multi-species automatic detection model designed for PAM in African tropical forests. DFS relies on a semi-supervised pipeline combining clustering of unannotated recordings with manual validation, followed by supervised fine-tuning of an Audio Spectrogram Transformer (AST) using low-rank adaptation, which is compared to a frozen-backbone linear baseline (DFS-Linear). The framework supports the detection of multiple taxonomic groups, including birds, primates, and elephants, from long-term acoustic recordings. DFS was trained on acoustic data collected in the Sebitoli area, in Kibale National Park, Uganda, and evaluated on an independent dataset recorded two years later at different locations within the same forest. This evaluation therefore assesses generalization across time and recording sites within a single tropical forest ecosystem. Across 8 out of 12 taxons, DFS outperforms existing automatic detection tools, particularly for non-avian taxa, achieving average AP values of 0.964 for primates and 0.961 for elephants. Results further show that LoRA-based fine-tuning substantially outperforms linear probing across taxa. Overall, these results demonstrate that task-oriented, region-specific training substantially improves detection performance in acoustically complex tropical environments, and highlight the potential of DFS as a practical tool for biodiversity monitoring and conservation in African rainforests.

Gabriel Dubus, Théau d'Audiffret, Claire Auger +10

Eco-Anthropologie, Muséum National d’Histoire Naturelle, UMR7206, Paris, France · Sebitoli Chimpanzee Project, Great Ape Conservation Project, Sebitoli, Kibale National Park, Fort Portal, Uganda · N’lab, Nitidae Association, Montpellier, France +3

Passive Acoustic MonitoringSound Event DetectionBioacousticsBiodiversity Monitoring
AskPDF
Aug 14, 2026

LightTeaNet: A Weakly Supervised Lightweight CNN for Multi-Label Tea Leaf Disease Detection and Localization

Tea is known as an important crop in many parts of South and Southeast Asia, yet the production of tea is still hampered by the multiple diseases that decrease the quantity and quality. Traditional methods of inspection, which are manual, are not consistent, labor-intensive, and depend on extensive monitoring. This paper introduces a lightweight convolutional neural network (CNN) designed for weakly supervised multi-label classification and disease localization in tea leaves called LightTeaNet. LightTeaNet learns directly from image-level labels and employs Class Activation Mapping (CAM) to localize disease-affected regions automatically, unlike conventional object detection models such as YOLO, which require extensive bounding box annotations. For Parameter efficiency, the network integrates Depthwise Separable Convolutions, and for enhanced feature discrimination, it integrates Channel Attention. LightTeaNet has achieved a Precision of 0.9615, a Recall of 0.8772, and an F1-score of 0.9179, while it shows [email protected]=0.1810 without any manual annotations, which delivers a competitive localization performance in the experimental results. These results validate the model as an interpretable as well as a resource-efficient framework for intelligent disease monitoring in agriculture.

Naif Haider Chowdhury, Md Rahim, Syed Farhan Hasan +2

Department of Computer Science & Engineering, Leading University, Kamal Bazar, Sylhet, 3112, Sylhet, Bangladesh.

Plant Disease ClassificationMulti-Label ClassificationLightweight CNNsWeakly Supervised Learning
AskPDF
Apr 8, 2026

TeaLeafVision: An Explainable and Robust Deep Learning Framework for Tea Leaf Disease Classification

As the worlds second most consumed beverage after water, tea is not just a cultural staple but a global economic force of profound scale and influence. More than a mere drink, it represents a quiet negotiation between nature, culture, and the human desire for a moment of reflection. So, the precise identification and detection of tea leaf disease is crucial. With this goal, we have evaluated several Convolutional Neural Networks (CNN) models, among them three shows noticeable performance including DenseNet201, MobileNetV2, InceptionV3 on the teaLeafBD dataset. teaLeafBD dataset contains seven classes, six disease classes and one healthy class, collected under various field conditions reflecting real world challenges. Among the CNN models, DenseNet201 has achieved the highest test accuracy of 99%. In order to enhance the model reliability and interpretability, we have implemented Gradient weighted Class Activation Mapping (Grad CAM), occlusion sensitivity analysis and adversarial training techniques to increase the noise resistance of the model. Finally, we have developed a prototype in order to leverage the models capabilities on real life agriculture. This paper illustrates the deep learning models capabilities to classify the disease in real life tea leaf disease detection and management.

Rafi Ahamed, Sidratul Moon Nafsin, Md Abir Rahman +3

Dept. of CSE, East West University, Dhaka, Bangladesh · Dept. of BBA, East West University, Dhaka, Bangladesh

Plant Disease ClassificationConvolutional Neural NetworksExplainable Image Classification
AskPDF