Internet of Things (IoT) sensors designed for environmental and agricultural purposes can offer significant contributions to creating a sustainable and green environment. However, powering these sensors remains a challenge, and exploiting the temperature difference between air and soil appears to be a promising solution. For energy-harvesting technologies, accurate soil temperature profile data are needed. This study uses meteorological and soil temperature profile data collected in the Czech Republic to train machine learning models based on Polynomial Regression (PR), Support Vector Regression (SVR), and Long Short-Term Memory (LSTM) to predict the soil temperature profile. The results of the study indicate an error of 0.79 °C, which is approximately 10.9% lower than the temperature error reported in state-of-the-art studies. Beyond achieving a lower temperature prediction error, the proposed solution simplifies the input parameters of the model to only ambient temperature and solar irradiance. This improvement significantly reduces the computational costs associated with the regression model, offering a more efficient approach to predicting soil temperature for the purpose of optimizing energy harvesting in IoT sensors.

Department of Cybernetics and Biomedical Engineering VSB Technical University of Ostrava 17 Listopadu 2172 15 708 00 Ostrava Poruba Czech Republic

Department of Electronics Engineering Kaunas University of Technology K Donelaicio g 73 44249 Kaunas Lithuania

Department of Mechanical Engineering and Technology Management Norwegian University of Life Sciences Drøbakveien 31 1433 Ås Norway

Zobrazit více v PubMed

Pamula A.S.P., Ravilla A., Madiraju S.V.H. Applications of the Internet of Things (IoT) in Real-Time Monitoring of Contaminants in the Air, Water, and Soil. Eng. Proc. 2022;27:26. doi: 10.3390/ecsa-9-13335. DOI

Thi Kim Tuoi T., Van Toan N., Ono T. Thermal energy harvester using ambient temperature fluctuations for self-powered wireless IoT sensing systems: A review. Nano Energy. 2024;121:109186. doi: 10.1016/j.nanoen.2023.109186. DOI

Chatterjee A., Lobato C.N., Zhang H., Bergne A., Esposito V., Yun S., Insinga A.R., Christensen D.V., Imbaquingo C., Bjørk R., et al. Powering internet-of-things from ambient energy. J. Phys. Energy. 2023;5:022001. doi: 10.1088/2515-7655/acb5e6. DOI

Prauzek M., Konecny J., Paterova T. An Analysis of Double Q-Learning-Based Energy Management Strategies for TEG-Powered IoT Devices. IEEE Internet Things J. 2023;10:18919–18929. doi: 10.1109/JIOT.2023.3283599. DOI

Li C., Zhang Y., Ren X. Modeling Hourly Soil Temperature Using Deep BiLSTM Neural Network. Algorithms. 2020;13:173. doi: 10.3390/a13070173. DOI

Li X., Zhu Y., Li Q., Zhao H., Zhu J., Zhang C. Interpretable spatio-temporal modeling for soil temperature prediction. Front. For. Glob. Change. 2023;6:1295731. doi: 10.3389/ffgc.2023.1295731. DOI

Bancik K., Konecny J., Konecny J., Mikus M., Choutka J., Koziorek J., Andriukaitis D., Navikas D., Prauzek M. Powering IoT Sensors Using Natural Temperature Differences between Air and Soil: Measurement and Evaluation. Sensors. 2024;24:7687. doi: 10.3390/s24237687. PubMed DOI PMC

Pullwitt S., Kulau U., Hartung R., Wolf L.C. A Feasibility Study on Energy Harvesting from Soil Temperature Differences; Proceedings of the 7th International Workshop on Real-World Embedded Wireless Systems and Networks; Shenzhen, China. 4 November 2018; pp. 1–6. DOI

Cornu J.Y., Denaix L., Lacoste J., Sappin-Didier V., Nguyen C., Schneider A. Impact of temperature on the dynamics of organic matter and on the soil-to-plant transfer of Cd, Zn and Pb in a contaminated agricultural soil. Environ. Sci. Pollut. Res. 2016;23:2997–3007. doi: 10.1007/s11356-015-5432-4. PubMed DOI

Lee Y., Park N. Self-powered wireless sensor system utilizing a thermoelectric generator for photovoltaic module monitoring application. Sol. Energy. 2024;283:113026. doi: 10.1016/j.solener.2024.113026. DOI

Quan N.H., Van An N., Huy H.T., Tuoi T.T.K., Ono T., Nguyet N.P.M., Cuong M.T.T., Nhan N.C., Van Toan N., Van Hieu N. TEG-Self-Powered System for Wireless Sensing Node Operating in Aqua-Greenhouse. IEEJ Trans. Sens. Micromach. 2024;144:332–337. doi: 10.1541/ieejsmas.144.332. DOI

Xie H., Zhang Y., Gao P. Thermoelectric-Powered Sensors for Internet of Things. Micromachines. 2023;14:31. doi: 10.3390/mi14010031. PubMed DOI PMC

Cheng X., Khomtchouk B., Matlof N., Mohanty P. Polynomial Regression As an Alternative to Neural Nets. arXiv. 2019 doi: 10.48550/arXiv.1806.06850.1806.06850 DOI

Crone S.F., Pietsch S. A Naïve Support Vector Regression Benchmark for the NN3 Forecasting Competition; Proceedings of the 2007 International Joint Conference on Neural Networks; Orlando, FL, USA. 12–17 August 2007; pp. 2454–2459. DOI

Hua Y., Zhao Z., Li R., Chen X., Liu Z., Zhang H. Deep Learning with Long Short-Term Memory for Time Series Prediction. IEEE Commun. Mag. 2019;57:114–119. doi: 10.1109/MCOM.2019.1800155. DOI

Shiri F., Perumal T., Mustapha N., Mohamed R. A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU. arXiv. 20232305.17473

Choon O.H., Hoong L.C., Huey T.S. A functional approximation comparison between neural networks and polynomial regression. WSEAS Trans. Math. Arch. 2008;7:353–363.

Müller K.R., Smola A.J., Rätsch G., Schölkopf B., Kohlmorgen J., Vapnik V. Predicting time series with support vector machines; Artificial Neural Networks—ICANN’97, Proceedings of the 7th International Conference Lausanne; Lausanne, Switzerland. 8–10 October 1997; Berlin/Heidelberg, Germany: Springer; 1997. pp. 999–1004. DOI

Smola A.J., Schölkopf B. A tutorial on support vector regression. Stat. Comput. 2004;14:199–222. doi: 10.1023/B:STCO.0000035301.49549.88. DOI

Hochreiter S., Schmidhuber J. Long Short-Term Memory. Neural Comput. 1997;9:1735–1780. doi: 10.1162/neco.1997.9.8.1735. PubMed DOI

Czech Hydrometeorological Institute Web Portal. [(accessed on 1 May 2025)]. Available online: https://www.chmi.cz/?l=en.