Field evaluation of an embedded acoustic sensing system for red palm weevil detection in date palms using deep learning

Document Type : Research Paper

Authors

Department of Agrotechnology, College of Aburaihan, University of Tehran, I. R. Iran

Abstract

The red palm weevil (RPW), Rhynchophorus ferrugineus, is a destructive pest of date palm whose concealed larval activity complicates non-destructive detection. This study evaluated an embedded acoustic sensing and deep-learning framework for distinguishing healthy and RPW-infested date palms under orchard conditions in Jahrom, Fars Province, Iran. Acoustic data were collected from 45 palms, comprising 23 healthy and 22 RPW-infested trees. A total of 5,355 raw recordings were acquired using a MAX9814-based microphone front end coupled to an STM32F103C8T6 microcontroller, of which 3,195 recordings passed recording-level quality control (2,255 healthy and 940 infested). The recordings were processed at 16 kHz, transformed into short-time Fourier transform spectrograms, and classified using DenseNet121. Performance was evaluated using stratified, tree-grouped five-fold cross-validation, with all recordings from an individual palm restricted to the same fold. Metrics were calculated independently for each validation fold and then averaged across the five folds. The model achieved a mean overall accuracy of 75.3% and mean balanced accuracy of 77.0%. Mean sensitivity and specificity were 81.2% and 72.8%, respectively, while infested-class precision and F1-score were 55.4% and 65.9%. The corresponding false-positive and false-negative rates were 27.2% and 18.8%. These findings support the potential of the proposed approach for field screening of RPW infestation, while the remaining classification errors indicate that acoustic predictions should complement rather than replace confirmatory inspection.

Graphical Abstract

Field evaluation of an embedded acoustic sensing system for red palm weevil detection in date palms using deep learning

Keywords

Main Subjects

References

Allen, J. B., & Rabiner, L. R. (1977). A unified approach to short-time Fourier analysis and synthesis. Proceedings of the IEEE, 65(11), 1558–1564. https://doi.org/10.1109/PROC.1977.10770
Alsanea, M., Habib, S., Khan, N. F., Alsharekh, M. F., Islam, M., & Khan, S. (2022). A deep-learning model for real-time red palm weevil detection and localization. Journal of Imaging, 8, 170. https://doi.org/10.3390/jimaging8060170
Analog Devices. (2022). MAX9814: Microphone amplifier with AGC and low-noise microphone bias (Rev. 4). Analog Devices, Inc.
Ashry, I., Mao, Y., Al-Fehaid, Y., Al-Shawaf, A., Al-Bagshi, M., Al-Brahim, S., Ng, T. K., & Ooi, B. S. (2020). Early detection of red palm weevil using distributed optical sensor. Scientific Reports, 10, 3155. https://doi.org/10.1038/s41598-020-60171-7
Ashry, I., Wang, B., Mao, Y., Sait, M., Guo, Y., Al-Fehaid, Y., Al-Shawaf, A., Ng, T. K., & Ooi, B. S. (2022). CNN-aided optical fiber distributed acoustic sensing for early detection of red palm weevil: A field experiment. Sensors, 22, 6491. https://doi.org/10.3390/s22176491
Boulila, W., Alzahem, A., Koubaa, A., Benjdira, B., & Ammar, A. (2023). Early detection of red palm weevil infestations using deep learning classification of acoustic signals. Computers and Electronics in Agriculture, 212, 108154. https://doi.org/10.1016/j.compag.2023.108154
Brodersen, K. H., Ong, C. S., Stephan, K. E., & Buhmann, J. M. (2010). The balanced accuracy and its posterior distribution. In 2010 20th International Conference on Pattern Recognition (pp. 3121–3124). IEEE. https://doi.org/10.1109/ICPR.2010.764
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
Gutiérrez, A., Ruiz, V., Moltó, E., Tapia, G., & Téllez, M. del M. (2010). Development of a bioacoustic sensor for the early detection of red palm weevil (Rhynchophorus ferrugineus Olivier). Crop Protection, 29, 671–676. https://doi.org/10.1016/j.cropro.2010.02.001
Hetzroni, A., Soroker, V., & Cohen, Y. (2016). Toward practical acoustic red palm weevil detection. Computers and Electronics in Agriculture, 124, 100-106. https://doi.org/10.1016/j.compag.2016.03.018
Huang, G., Liu, Z., van der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 4700–4708). https://doi.org/10.1109/CVPR.2017.243
Hussein, W. B., Hussein, M. A., & Becker, T. (2010). Detection of the red palm weevil Rhynchophorus ferrugineus using its bioacoustics features. Bioacoustics, 19, 177-194. https://doi.org/10.1080/09524622.2010.9753623
Jokar, P., Masoudi, M., & Pradhan, B. (2023). A new spatial model for ecological suitability assessment of irrigated farming in Jahrom County, Iran. Revista Caatinga, 36(1), 177-188. https://doi.org/10.1590/1983-21252023v36n119rc
Kang, C. H., Ashry, I., Marin, J. M., Ariff, T., Rjeb, A., Gunawan, W. H., Ng, T. K., & Ooi, B. S. (2024). On the large-scale field experiment of machine learning-aided fiber-optic distributed acoustic sensing for early detection of red palm weevils. In CLEO 2024, Technical Digest Series, Paper SF3A.5. Optica Publishing Group. https://doi.org/10.1364/CLEO_SI.2024.SF3A.5
Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations (ICLR), San Diego, CA, USA. https://doi.org/10.48550/arXiv.1412.6980
Pinhas, J., Soroker, V., Hetzroni, A., Mizrach, A., Teicher, M., & Goldberger, J. (2008). Automatic acoustic detection of the red palm weevil. Computers and Electronics in Agriculture, 63, 131-139. https://doi.org/10.1016/j.compag.2008.02.004
Rach, M. M., Gomis, H. M., Granado, O. L., Malumbres, M. P., Campoy, A. M., & Martín, J. J. S. (2013). On the design of a bioacoustic sensor for the early detection of the red palm weevil. Sensors, 13(2), 1706-1729. https://doi.org/10.3390/s130201706
Saranya, S., & Martin, B. (2025). Machine learning-enabled acoustic sensing for RPW infestation detection. Scientific Reports, 15, 38391. https://doi.org/10.1038/s41598-025-22306-6
Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4), 427-437. https://doi.org/10.1016/j.ipm.2009.03.002
STMicroelectronics. (2025). STM32F103x8, STM32F103xB: Medium-density performance line Arm®-based 32-bit MCU with 64 or 128 KB Flash, USB, CAN, 7 timers, 2 ADCs, 9 communication interfaces (DS5319 Rev. 20). Retrived from: https://www.st.com/resource/en/datasheet/stm32f103rb.pdf.
Torky, M., Dahy, G., & Hassanien, A. E. (2023). Recognizing sounds of red palm weevils (RPW) based on the VGGish model: Transfer learning methodology. Computers and Electronics in Agriculture, 212, 108079. https://doi.org/10.1016/j.compag.2023.108079
Tougui, I., Jilbab, A., & El Mhamdi, J. (2021). Impact of the choice of cross-validation techniques on the results of machine learning-based diagnostic applications. Healthcare Informatics Research, 27(3), 189-199. https://doi.org/10.4258/hir.2021.27.3.189
Wang, B., Mao, Y., Ashry, I., Al-Fehaid, Y., Al-Shawaf, A., Ng, T. K., Yu, C., & Ooi, B. S. (2021). Towards detecting red palm weevil using machine learning and fiber optic distributed acoustic sensing. Sensors, 21(5), 1592. https://doi.org/10.3390/s21051592

Files

Share

How to cite

Statistics