AUTOMATION, ІОТ, ROBOTICS AND INFORMATION-MEASUREMENT SYSTEMS

Comparative Analysis of Short-Term Grain Temperature Forecasting Models in Grain Storages

Authors

A. R. Lishchuk ORCID 0009-0003-5519-456X
Vinnytsia National Technical University ROR
V. M. Dubovoy ORCID 0000-0003-0440-3643
Vinnytsia National Technical University ROR
DOI https://doi.org/10.31649/1997-9266-2026-186-3-117-134

Keywords

grain temperature forecasting grain storage facility short-term forecasting multiple linear regression LSTM ANFIS hybrid model time series

Abstract

Short-term forecasting of grain temperature is an important component of intelligent monitoring of grain storage facilities, since it enables the timely detection of dangerous temperature trends, assessment of the risk of local self-heating of the grain mass, and improvement of decision-making efficiency during storage. The temperature state of grain is formed under the influence of the thermal inertia of the grain mass, external meteorological conditions, moisture-related processes, crop type, sensor depth, and spatial heterogeneity of the temperature field. Therefore, it is relevant to study forecasting models that can take into account both the temporal dynamics of the process and nonlinear relationships between meteorological, technological, spatial, and regime-related parameters.

This paper investigates multiple linear regression, LSTM, Compact ANFIS, and hybrid LSTM-ANFIS architectures for short-term forecasting of grain temperature at prediction horizons of 1, 3, and 6 hours ahead. The study was carried out using a multi-series time dataset that includes two grain crops, four bins, 24 sensor suspensions, and 72 temperature sensors. The input data contained hourly measurements of grain temperature, external meteorological parameters, sensor location characteristics, and additional engineered features. During data preprocessing, lag, statistical, cyclic, spatial, and mode -related features were generated, as well as target variables for each prediction horizon. To prevent information leakage, the dataset was divided into training, validation, and test subsets according to the chronological principle.

The correlation analysis showed that the most informative features for grain temperature forecasting are the current grain temperature, its lagged values, rolling statistics, the difference between ambient air temperature and grain temperature, estimated grain moisture, crop type, sensor depth, and spatial-regime characteristics. It was shown that model performance depends significantly on the prediction horizon. For the 1-hour horizon, the best result was achieved by the multiple linear regression model, which provided MAE = 0.10266, RMSE = 0.16233, and R² = 0.99228. For the 3-hour horizon, the highest accuracy was demonstrated by the hybrid LSTMEncoder + Compact ANFIS model, with MAE = 0.29073, RMSE = 0.39682, and R² = 0.95375. For the 6-hour horizon, the best performance was achieved by the LSTMEncoder + Compact ANFIS Residual + Regime Features model, which reached MAE = 0.53045, RMSE = 0.73544, and R² = 0.84081.

The obtained results confirm that, for ultra-short-term grain temperature forecasting, tabular models with properly generated lag, statistical, and engineered features may be sufficiently effective. At the same time, as the prediction horizon increases, the use of hybrid architectures becomes more appropriate. Such models combine the ability of LSTM to capture temporal dependencies with the capability of Compact ANFIS to perform nonlinear forecast refinement based on physically meaningful and spatial-regime features. The practical significance of the proposed approach lies in its potential application in grain storage monitoring systems, early warning of dangerous temperature changes, and decision support for microclimate control in stored grain.

110 23

How to Cite

[1]
“Comparative Analysis of Short-Term Grain Temperature Forecasting Models in Grain Storages”, Вісник ВПІ, no. 3, pp. 117–134, Jul. 2026, doi: 10.31649/1997-9266-2026-186-3-117-134.

Author Biographies

A. R. Lishchuk, Vinnytsia National Technical University

Post-Graduate Student of the Chair of Computer Control Systems

V. M. Dubovoy, Vinnytsia National Technical University

Dr. Sc. (Eng.), Professor, Professor of the Chair of Computer Control Systems

References

Q. Wang, J. Feng, F. Han, W. Wu, and S. Gao, “Analysis and prediction of grain temperature from air temperature to ensure the safety of grain storage,” International Journal of Food Properties, vol. 23, no. 1, pp. 1200-1213, 2020. https://doi.org/10.1080/10942912.2020.1792922 .
S. Duan, W. Yang, X. Wang, S. Mao, and Y. Zhang, “Grain Pile Temperature Forecasting from Weather Factors: A Support Vector Regression Approach,” in 2019 IEEE/CIC International Conference on Communications in China (ICCC), Changchun, China, 2019, pp. 255-260. https://doi.org/10.1109/ICCChina.2019.8855910 .
L. Ge, C. Chen, Y. Li, T. Mo, and W. Li, “A CNN-based temperature prediction approach for grain storage,” International Journal of Internet Manufacturing and Services, vol. 7, no. 4, pp. 345-357, 2020. https://doi.org/10.1504/IJIMS.2020.110234 .
S. Duan, W. Yang, X. Wang, S. Mao, and Y. Zhang, “Deep Spatio-Temporal Attention Model for Grain Storage Temperature Forecasting,” in 2020 IEEE 26th International Conference on Parallel and Distributed Systems (ICPADS), 2020, pp. 593-600. https://doi.org/10.1109/ICPADS51040.2020.00082 .
S. Duan, W. Yang, X. Wang, S. Mao, and Y. Zhang, “Temperature Forecasting for Stored Grain: A Deep Spatiotemporal Attention Approach,” IEEE Internet of Things Journal, vol. 8, no. 23, pp. 17147-17160, Dec. 2021. https://doi.org/10.1109/JIOT.2021.3078332 .
Q. Wang, M. Hou, Y. Qin, and F. Lian, “Temperature Forecasting of Grain in Storage: An Improved Approach Based on Broad Learning Network,” IEEE Access, vol. 12, pp. 115112-115123, 2024. https://doi.org/10.1109/ACCESS.2024.3417533 .
Q. Zhang, W. Zhang, Q. Huang, C. Wan, and Z. Li, “AMSformer: A Transformer for Grain Storage Temperature Prediction Using Adaptive Multi-Scale Feature Fusion,” Agriculture, vol. 15, no. 1, p. 58, 2025. https://doi.org/10.3390/agriculture15010058 .
X. Li, W. Wu, H. Guo, X. Qiao, Y. Lu, Y. Wu, and G. Qiao, “An Interpretable Temperature Prediction Method for Grain in Storage Based on Improved Temporal Fusion Transformers,” SSRN, 2024. https://doi.org/10.2139/ssrn.4937130 .
H. Cui, Q. Zhang, W. Zhang, Z. Wu, and W. Wu, “Modeling and Application of Temporal Correlation of Grain Temperature during Grain Storage,” Agriculture, vol. 12, no. 11, p. 1883, 2022. https://doi.org/10.3390/agriculture12111883 .
H. Cui, Q. Zhang, J. Zhang, Z. Wu, and W. Wu, “Classification of Grain Storage Inventory Modes Based on Temperature Contour Map of Grain Bulk Using Back Propagation Neural Network,” Agriculture, vol. 11, no. 5, p. 451, 2021. https://doi.org/10.3390/agriculture11050451 .
Y. Jin, K. W. Wong, D. Yang, Z. Zhang, W. Wu, and J. Yin, “A neural network model used in continuous grain dryer control system,” Drying Technology, vol. 40, no. 9, pp. 1901-1922, 2022. https://doi.org/10.1080/07373937.2021.1891930 .
K. V. Shihabudheen and G. N. Pillai, “Recent advances in neuro-fuzzy system: A survey,” Knowledge-Based Systems, vol. 152, pp. 136-162, 2018. https://doi.org/10.1016/j.knosys.2018.04.014 .
M. N. M. Salleh, N. Talpur, and K. Hussain, “Adaptive Neuro-Fuzzy Inference System: Overview, Strengths, Limitations, and Solutions,” in Data Mining and Big Data, Y. Tan, H. Takagi, and Y. Shi, Eds. Cham, Switzerland: Springer, 2017, pp. 527-535. https://doi.org/10.1007/978-3-319-61845-6_52 .
A. R. Sadeghian, “Nonlinear neuro-fuzzy prediction: methodology, design and applications,” in Proc. 10th IEEE Int. Conf. Fuzzy Systems, Melbourne, VIC, Australia, 2001, vol. 3, pp. 1022-1026. https://doi.org/10.1109/FUZZ.2001.1009136 .
D. Kukolj, “Design of adaptive Takagi–Sugeno–Kang fuzzy models,” Applied Soft Computing, vol. 2, no. 2, pp. 89-103, 2002. https://doi.org/10.1016/S1568-4946(02)00032-7 .
X. Gu, F.-L. Chung, and S. Wang, “Bayesian Takagi–Sugeno–Kang fuzzy classifier,” IEEE Transactions on Fuzzy Systems, vol. 25, no. 6, pp. 1655-1671, Dec. 2017. https://doi.org/10.1109/TFUZZ.2016.2617377 .
О. В. Бондарчук, О. В. Мазурук, і В. Б. Мокін, «Системний аналіз та прогнозування температури зерна у силосі зернового елеватора за даними ІоТ-системи з використанням технологій штучного інтелекту,» у Матеріалах Всеукраїнської науково-практичної інтернет-конференції «Молодь в науці: дослідження, проблеми, перспективи (МН-2025)», 15–16 червня 2025 р. https://conferences.vntu.edu.ua/index.php/mn/mn2025/paper/view/25196
А. В. Святобатько, і І. О. Фурман, «Нейромережевий метод прогнозування параметрів зернової маси, що зберігається у бункерах елеваторів,» Енергетика та комп’ютерно-інтегровані технології в АПК, no. 1, pp. 68-70, 2014. [Електронний ресурс]. Режим доступу:
http://www.irbis-nbuv.gov.ua/cgi-bin/irbis_nbuv/cgiirbis_64.exe?Z21ID=&I21DBN=UJRN&P21DBN=UJRN&S21STN =1&S21REF=10&S21FMT=fullwebr&C21COM=S&S21CNR=20&S21P01=0&S21P02=0&S21P03=A=&S21COLORTERMS=1&S21STR=%D0%A4%D1%83%D1%80%D0%BC%D0%B0%D0%BD%20%D0%86$ .
А. В. Святобатько, А. Хоховські, П. Обставські, and І. О. Фурман, «Розробка архітектури програмно-апаратного комплексу засобів контролю та прогнозування параметрів зернової маси, що зберігається у бункерах на елеваторі,»Вісник ХНТУСГ ім. Петра Василенка. Технічні науки, no. 165, pp. 42-43, 2015.[Електронний ресурс]. Режим доступу: https://www.irbis-nbuv.gov.ua
A. Iguaz, C. Arroqui, A. Esnoz, and P. Vírseda, “Modelling and Simulation of Heat Transfer in Stored Rough Rice with Aeration,” Biosystems Engineering, vol. 89, no. 1, pp. 69-77, 2004. https://doi.org/10.1016/j.biosystemseng.2004.05.001
ASABE, “Moisture Relationships of Plant-Based Agricultural Products,” ASAE D245.7 JUN2021, St. Joseph, MI, USA: American Society of Agricultural and Biological Engineers, 2021.
F. I. Molina-Herrera, L. I. Quemada-Villagómez, M. Calderón-Ramírez, G. M. Martínez-González, and H. Jiménez-Islas, “Modeling Temperature and Moisture Dynamics in Corn Storage Silos: A Comparative 2D and 3D Approach,” Modelling, vol. 6, no. 1, art. 7, 2025. https://doi.org/10.3390/modelling6010007 .