Yerinde Problar Olmadan Etkili Toprak Nemi İzleme: LSTM Tabanlı Bluetooth Sinyal Gücü Analizi

Yıl 2024, Cilt: 25 Sayı: 1, 21 - 38

Selçuk Yazar , Deniz Taşkın , Erdem Bahar

https://doi.org/10.59314/tujes.1464575

Öz

Toprak yapısına zarar vermeden toprak nemi ölçümü tarımda önemlidir. Elektriksel iletkenlik ve mikrodalgalar bu amaçla yaygın olarak kullanılmaktadır. Son zamanlarda, toprak nem içeriğini belirlemek için yapay sinir ağları ve zaman serisi tahminlerinin kullanılmasına olan ilgi artmaktadır. Bu ölçümlerde mikrodalga cihazlara benzer şekilde Bluetooth sinyallerinden yararlanılmaktadır. Ancak Bluetooth sinyalleri, özel toprak nemi ölçüm cihazlarına kıyasla düşük iletim gücüne sahiptir. Bu çalışmada, Uzun Kısa Süreli Bellek (LSTM) sinir ağı mimarisi ve 0,001 Watt iletim gücüne sahip Bluetooth sinyal güçleri kullanılarak, özellikle farklı pH değerlerine sahip toprak örnekleri için toprak nem içeriğinin belirlenme olasılığı araştırılmaktadır. Amaç, toprak nem değişim durumunu yerinde bir prob olmadan doğrudan Bluetooth sinyal seviyelerini kullanarak değerlendirmekti. Deneysel bir çalışmada, alkali toprak örneklerinden elde edilen Bluetooth sinyal güçlerine dayalı bir yapay öğrenme modeli kullanılarak toprak nem içeriği değişimi %15'lik bir kök-ortalama-kare hata (RMSE) değeri ile tahmin edilmiştir. Bu yöntem, toprak nemi zaman içindeki sinyal seviyesi değişiklikleri izlenerek güvenilir bir şekilde ölçülebildiğinden, özel bir sensör ihtiyacını ortadan kaldırmaktadır.

Anahtar Kelimeler

Bluetooth Düşük Enerji, Derin öğrenme, Uzun-Kısa Süreli Bellek, Aktif mikrodalgalar, Toprak nemi

Efficient Soil Moisture Monitoring without In-Situ Probes: LSTM-Based Bluetooth Signal Strengths Analysis

Öz

Soil moisture measurement without damaging soil structure is important in agriculture. Electrical conductivity and microwaves are commonly used for this purpose. Recently, there has been growing interest in using artificial neural networks and time series forecasting to determine soil moisture content. Bluetooth signals, similar to microwave devices, are utilized in these measurements. However, Bluetooth signals have low transmission power compared to dedicated soil moisture measurement devices. This study investigates the possibility of determining soil moisture content using Long Short-Term Memory (LSTM) neural network architecture and Bluetooth signal strengths with 0.001 Watt transmission power, specifically for soil samples with varying pH values. The objective was to assess soil moisture change status directly using Bluetooth signal levels without an in-situ probe. In an experimental study, soil moisture content changing was predicted with a root-mean-square error (RMSE) value of 15% using an artificial learning model based on Bluetooth signal strengths obtained from alkali soil samples. This method eliminates the need for a dedicated sensor, as soil moisture can be reliably measured by tracking signal level changes over time.

Anahtar Kelimeler

Bluetooth Low Energy, Deep learning, Long Short-Term Memory, Active microwaves, Soil moisture

Kaynakça

• Abdel‐Wahab, W., Al‐Saedi, H., Ehsandar, A., Palizban, A., Raeis‐Zadeh, M., & Safavi‐Naeini, S. (2019). Efficient integration of scalable active‐ phased array antenna based on modular approach for MM‐wave applications. Microwave and Optical Technology Letters, 61(5), 1333–1336. https://doi.org/10.1002/mop.31744
• Adate, A., & Tripathy, B. K. (2019). S-LSTM-GAN: Shared Recurrent Neural Networks with Adversarial Training. In A. J. Kulkarni, S. C. Satapathy, T. Kang, & A. H. Kashan (Eds.), Proceedings of the 2nd International Conference on Data Engineering and Communication Technology (Vol. 828, pp. 107–115). Singapore: Springer Singapore. https://doi.org/10.1007/978-981-13- 1610-4_11
• Allen-Zhu, Z., Li, Y., & Song, Z. (2019). On the convergence rate of training recurrent neural networks. In Proceedings of the 33rd International Conference on Neural Information Processing Systems (pp. 6676–6688). Red Hook, NY, USA: Curran Associates Inc.
• Batchu, V., Nearing, G., & Gulshan, V. (2023). A Deep Learning Data Fusion Model Using Sentinel-1/2, SoilGrids, SMAP, and GLDAS for Soil Moisture Retrieval. Journal of Hydrometeorology, 24(10), 1789–1823. https://doi.org/10.1175/JHM-D-22- 0118.1
• Calla, O. P. N. (2002). Application of Microwave Remote Sensing In Ocean Studies. 2, 623–632. Kochi, India: Allied Publishers.
• Carbune, V., Gonnet, P., Deselaers, T., Rowley, H. A., Daryin, A., Calvo, M., … Gervais, P. (2020). Fast multi-language LSTM-based online handwriting recognition. International Journal on Document Analysis and Recognition (IJDAR), 23(2), 89–102. https://doi.org/10.1007/s10032-020-00350-4
• Carrière, S. D., Martin-StPaul, N. K., Doussan, C., Courbet, F., Davi, H., & Simioni, G. (2021). Electromagnetic Induction Is a Fast and NonDestructive Approach to Estimate the Influence of Subsurface Heterogeneity on Forest Canopy Structure. Water, 13(22), 3218. https://doi.org/10.3390/w13223218
• Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014, September 2). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. arXiv. Retrieved from http://arxiv.org/abs/1406.1078
• Darroudi, S., Caldera-Sànchez, R., & Gomez, C. (2019). Bluetooth Mesh Energy Consumption: A Model. Sensors, 19(5), 1238. https://doi.org/10.3390/s19051238
• Davis, J. L., & Chudobiak, W. J. (1975). In Situ Meter for Measuring Relative Permittivity of Soils. 75- 1A. https://doi.org/10.4095/104349
• De Jeu, R. A. M., Holmes, T. R. H., Parinussa, R. M., & Owe, M. (2014). A spatially coherent global soil moisture product with improved temporal resolution. Journal of Hydrology, 516, 284–296. https://doi.org/10.1016/j.jhydrol.2014.02.015
• Dong, J., Steele‐Dunne, S. C., Ochsner, T. E., & Van De Giesen, N. (2016). Determining soil moisture and soil properties in vegetated areas by assimilating soil temperatures. Water Resources Research, 52(6), 4280–4300. https://doi.org/10.1002/2015WR018425
• Ertam, F. (2019). An effective gender recognition approach using voice data via deeper LSTM networks. Applied Acoustics, 156, 351–358. https://doi.org/10.1016/j.apacoust.2019.07.033
• Gao, T., Gong, X., Zhang, K., Lin, F., Wang, J., Huang, T., & Zurada, J. M. (2020). A recalling-enhanced recurrent neural network: Conjugate gradient learning algorithm and its convergence analysis. Information Sciences, 519, 273–288. https://doi.org/10.1016/j.ins.2020.01.045
• Gardner, W., & Kirkham, D. (1952). DETERMINATION OF SOIL MOISTURE BY NEUTRON SCATTERING: Soil Science, 73(5), 391–402. https://doi.org/10.1097/00010694- 195205000-00007
• Gascho, G. J., Parker, M. B., & Gaines, T. P. (1996). Reevaluation of suspension solutions for soil pH. Communications in Soil Science and Plant Analysis, 27(3–4), 773–782. https://doi.org/10.1080/00103629609369594
• Ghori, M. R., Wan, T.-C., & Sodhy, G. C. (2020). Bluetooth Low Energy 5 Mesh Based Hospital Communication Network (B5MBHCN). In M. Anbar, N. Abdullah, & S. Manickam (Eds.), Advances in Cyber Security (Vol. 1132, pp. 247– 261). Singapore: Springer Singapore. https://doi.org/10.1007/978-981-15-2693-0_18
• H. Ali, M., & K. Ali, N. (2019). IoT based security system and intelligent home automation multi monitoring and control systems. IAES International Journal of Robotics and Automation (IJRA), 8(3), 205. https://doi.org/10.11591/ijra.v8i3.pp205-210
• Han, Q., Zeng, Y., Zhang, L., Cira, C.-I., Prikaziuk, E., Duan, T., … Su, B. (2023). Ensemble of optimised machine learning algorithms for predicting surface soil moisture content at global scale [Preprint]. Earth and space science informatics. https://doi.org/10.5194/gmd-2023-83
• Hanzlíček, Z., Vít, J., & Tihelka, D. (2019). LSTMBased Speech Segmentation for TTS Synthesis. In K. Ekštein (Ed.), Text, Speech, and Dialogue (Vol. 11697, pp. 361–372). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-030- 27947-9_31
• Haria, A. H., Johnson, A. C., Bell, J. P., & Batchelor, C. H. (1994). Water movement and isoproturon behaviour in a drained heavy clay soil: 1. Preferential flow processes. Journal of Hydrology, 163(3–4), 203–216. https://doi.org/10.1016/0022- 1694(94)90140-6
• Hochreiter, S., & Schmidhuber, J. (1997). Long ShortTerm Memory. Neural Computation, 9(8), 1735– 1780. https://doi.org/10.1162/neco.1997.9.8.1735
• Hu, H., Li, Z., Elofsson, A., & Xie, S. (2019). A BiLSTM Based Ensemble Algorithm for Prediction of Protein Secondary Structure. Applied Sciences, 9(17), 3538. https://doi.org/10.3390/app9173538
• Hussain, T., Muhammad, K., Ullah, A., Cao, Z., Baik, S. W., & De Albuquerque, V. H. C. (2020). CloudAssisted Multiview Video Summarization Using CNN and Bidirectional LSTM. IEEE Transactions on Industrial Informatics, 16(1), 77–86. https://doi.org/10.1109/TII.2019.2929228
• Lambot, S., Slob, E., Minet, J., Jadoon, K. Z., Vanclooster, M., & Vereecken, H. (2010). FullWaveform Modelling and Inversion of GroundPenetrating Radar Data for Non-invasive Characterisation of Soil Hydrogeophysical Properties. In R. A. Viscarra Rossel, A. B. McBratney, & B. Minasny (Eds.), Proximal Soil Sensing (pp. 299–311). Dordrecht: Springer Netherlands. https://doi.org/10.1007/978-90-481- 8859-8_25
• Luo, D., Wen, X., & He, P. (2023). Surface Soil Moisture Estimation Using a Neural Network Model in Bare Land and Vegetated Areas. Journal of Spectroscopy, 2023, 1–10. https://doi.org/10.1155/2023/5887177
• Ma, Z., Wu, B., Chang, S., Yan, N., & Zhu, W. (2023). Developing a physics-guided neural network to predict soil moisture with remote sensing evapotranspiration and weather forecasting [Other]. pico. https://doi.org/10.5194/egusphere-egu23- 10597
• Mamun, M. A. A., & Yuce, M. R. (2019). Sensors and Systems for Wearable Environmental Monitoring Toward IoT-Enabled Applications: A Review. IEEE Sensors Journal, 19(18), 7771–7788. https://doi.org/10.1109/JSEN.2019.2919352
• Martín, F., Vélez, P., Muñoz-Enano, J., & Su, L. (2023). Planar microwave sensors. Hoboken, New Jersey: Wiley-IEEE Press.
• Mu, T., Liu, G., Yang, X., & Yu, Y. (2022). SoilMoisture Estimation Based on Multiple-Source Remote-Sensing Images. Remote Sensing, 15(1), 139. https://doi.org/10.3390/rs15010139
• Nagarajan, B., Shanmugam, V., Ananthanarayanan, V., & Bagavathi Sivakumar, P. (2020). Localization and Indoor Navigation for Visually Impaired Using Bluetooth Low Energy. In A. K. Somani, R. S. Shekhawat, A. Mundra, S. Srivastava, & V. K. Verma (Eds.), Smart Systems and IoT: Innovations in Computing (Vol. 141, pp. 249–259). Singapore: Springer Singapore. https://doi.org/10.1007/978- 981-13-8406-6_25
• Newman, A. L. (1964). Soil Survey (Vol. 17). US Department of Agriculture, Soil Conservation Service.
• Nguyen, T. P., & Songsermpong, S. (2022). Microwave processing technology for food safety and quality: A review. Agriculture and Natural Resources, 56(1), 57–72. Retrieved from https://li01.tcithaijo.org/index.php/anres/article/view/253973
• Noborio, K. (2001). Measurement of soil water content and electrical conductivity by time domain reflectometry: a review. Computers and Electronics in Agriculture, 31(3), 213–237. https://doi.org/10.1016/S0168-1699(00)00184-8
• Panciera, R., Walker, J. P., Jackson, T. J., Gray, D. A., Tanase, M. A., Ryu, D., … Hacker, J. M. (2014). The Soil Moisture Active Passive Experiments (SMAPEx): Toward Soil Moisture Retrieval From the SMAP Mission. IEEE Transactions on Geoscience and Remote Sensing, 52(1), 490–507. https://doi.org/10.1109/TGRS.2013.2241774
• Paul, I. J. L., Sasirekha, S., Vishnu, D. R., & Surya, K. (2019). Recognition of handwritten text using long short term memory (LSTM) recurrent neural network (RNN). 030011. Kurdistan, Iraq. https://doi.org/10.1063/1.5097522
• Pekel, E. (2020). EVALUATION OF ESTIMATION PERFORMANCE FOR SOIL MOISTURE USING PARTICLE SWARM OPTIMIZATION AND ARTIFICIAL NEURAL NETWORK. Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi. https://doi.org/10.28948/ngumuh.529418
• Reginato, R. J., & Van Bavel, C. H. M. (1964). Soil Water Measurement with Gamma Attenuation. Soil Science Society of America Journal, 28(6), 721– 724. https://doi.org/10.2136/sssaj1964.0361599500280 0060014x
• Ren, G., & Ganapathy, V. (2019). Recognition of Online Handwriting with Variability on Smart Devices. ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 7605–7609. Brighton, United Kingdom: IEEE. https://doi.org/10.1109/ICASSP.2019.8682706 Scheberl, L., Scharenbroch, B. C., Werner, L. P.,
• Prater, J. R., & Fite, K. L. (2019). Evaluation of soil pH and soil moisture with different field sensors: Case study urban soil. Urban Forestry & Urban Greening, 38, 267–279. https://doi.org/10.1016/j.ufug.2019.01.001
• Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11), 2673–2681. https://doi.org/10.1109/78.650093
• Sengupta, D. L., & Liepa, V. V. (2005). Applied Electromagnetics and Electromagnetic Compatibility (1st ed.). Wiley. https://doi.org/10.1002/0471746231
• Singh, A., & Gaurav, K. (2023). Deep learning and data fusion to estimate surface soil moisture from multisensor satellite images. Scientific Reports, 13(1), 2251. https://doi.org/10.1038/s41598-023-28939-9
• Sun, H., Cai, C., Liu, H., & Yang, B. (2019). Microwave and Meteorological Fusion: A method of Spatial Downscaling of Remotely Sensed Soil Moisture. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(4), 1107–1119. https://doi.org/10.1109/JSTARS.2019.2901921
• Topp, G. C., Davis, J. L., & Annan, A. P. (1980). Electromagnetic determination of soil water content: Measurements in coaxial transmission lines. Water Resources Research, 16(3), 574–582. https://doi.org/10.1029/WR016i003p00574
• Wang, T., Zhou, J., Wang, W., Zhang, G., Huang, M., & Lai, Y. (2019). A personal local area information interaction system based on NFC and Bluetooth technology. International Journal of High Performance Computing and Networking, 13(4), 455. https://doi.org/10.1504/IJHPCN.2019.099268
• Wu, F., Wu, T., & Yuce, M. (2018). An Internet of Things (IoT) Network System for Connected Safety and Health Monitoring Applications. Sensors, 19(1), 21. https://doi.org/10.3390/s19010021
• Zárate-Valdez, J. L., Zasoski, R., & Läuchli, A. (2006). SHORT-TERM EFFECTS OF MOISTURE CONTENT ON SOIL SOLUTION pH AND SOIL EH. Soil Science. Retrieved from https://www.semanticscholar.org/paper/SHORTTERM-EFFECTS-OF-MOISTURE-CONTENTON-SOIL-pH-Z%C3%A1rate-Valdez38asoski/ba3aba909b76ba66b9be0cc8bfec3c897ae2 5f32
• Zhang, Y., Qu, C., & Wang, Y. (2020). An Indoor Positioning Method Based on CSI by Using Features Optimization Mechanism With LSTM. IEEE Sensors Journal, 20(9), 4868–4878. https://doi.org/10.1109/JSEN.2020.2965590
• Zia, T., & Zahid, U. (2019). Long short-term memory recurrent neural network architectures for Urdu acoustic modeling. International Journal of Speech Technology, 22(1), 21–30. https://doi.org/10.1007/s10772-018-09573-7