A Robust Sensor-Failure-Tolerant Fuzzy Control Framework with Predictive Data Imputation for Sustainable Precision Irrigation
DOI:
https://doi.org/10.31436/iiumej.v27i2.3647Keywords:
Fuzzy Inference System (FIS), precission agriculture, Irrigation Management, Sensor Degradation, Linear Regression ModelAbstract
Effective irrigation management under uncertain conditions remains a major challenge in precision agriculture, particularly when sensor performance degrades or extreme environmental variations lead to unreliable data. This study presents a hybrid framework that combines a linear regression model with a Mamdani fuzzy inference system (FIS) to improve the robustness of soil moisture prediction and irrigation control. The proposed approach trains the regression model using synthetically generated data with controlled noise levels to estimate soil moisture conditions. These predictions are then integrated with real-time temperature and humidity data within the fuzzy inference system to generate appropriate irrigation decisions. To represent extreme sensor conditions, additional adaptive noise is introduced when soil moisture values exceed or fall below predefined thresholds, effectively simulating sensor malfunction scenarios. Time-series simulation results indicate that the proposed system can maintain stable, efficient irrigation performance despite significant sensor disturbances. Overall, this work improves irrigation efficiency and provides insights into how hybrid statistical and fuzzy-logic approaches can mitigate the adverse effects of sensor inaccuracies under highly variable environmental conditions.
ABSTRAK: Pengurusan pengairan cekap berkeadaan tidak menentu, kekal sebagai cabaran kritikal dalam pertanian, terutama apabila berlaku kerosakan pada sensor dan persekitaran turun naik yang melampau menyebabkan data yang diperolehi tidak boleh dipercayai. Kajian ini, mencadangkan pendekatan hibrid yang mengintegrasi model regresi linear dengan sistem inferens Mamdani kabur (FIS) bagi meramal kelembapan tanah dan mengawal pengairan. Kaedah ini melibatkan latihan model regresi menggunakan data sintetik yang terhasil melalui tahap bunyi yang dikawal dengan teliti bagi meramal kelembapan tanah, sementara sistem inferens kabur secara dinamik menterjemah ramalan tersebut bersama ukuran suhu dan kelembapan masa nyata kepada arahan pengairan yang tepat. Keadaan sensor yang melampau disimulasi dengan memperkenalkan bunyi tambahan secara adaptif apabila tahap kelembapan tanah jatuh di bawah atau melebihi had tertentu, seterusnya meniru senario kegagalan sensor. Melalui simulasi siri masa terperinci, dapatan kajian ini mengekalkan kawalan pengairan yang stabil dan cekap walaupun sensor gagal berfungsi. Kajian ini bukan sahaja meningkatkan kecekapan pengairan malah juga memberi pemahaman tentang bagaimana teknik hibrid statistik dan logik kabur boleh mengurangkan kesan ketidaktepatan sensor dalam keadaan persekitaran yang berubah.
Downloads
References
O. Kisi et al., “Modeling wetting front redistribution of drip irrigation systems using a new machine learning method: Adaptive neuro-fuzzy system improved by hybrid particle swarm optimization– gravity search algorithm,” Agric. Water Manag., vol. 256, p. 107067, 2021.
N. Mahmoudi et al., “Mutating fuzzy logic model with various rigorous meta-heuristic algorithms for soil moisture content estimation,” Agric. Water Manag., vol. 261, p. 107342, 2022.
M. Ehteram et al., “Performance improvement for infiltration rate prediction using hybridized Adaptive Neuro-Fuzzy Inference System (ANFIS) with optimization algorithms,” Ain Shams Eng. J., vol. 12, no. 2, pp. 1665–1676, 2021.
E. A. Abioye et al., “A review on monitoring and advanced control strategies for precision irrigation,” Comput. Electron. Agric., vol. 173, p. 105441, 2020.
M. F. Rahaman et al., “Wireless sensor networks in agriculture through machine learning: A survey,” Comput. Electron. Agric., vol. 197, p. 106933, 2022.
Z. Gu et al., “Neural network soil moisture model for irrigation scheduling,” Comput. Electron. Agric., vol. 180, p. 105801, 2021.
Y. Wang et al., “A comprehensive study of deep learning for soil moisture prediction,” Hydrol. Earth Syst. Sci., vol. 28, no. 2, pp. 917–943, 2024.
P. Datta and S. A. Faroughi, “A multihead LSTM technique for prognostic prediction of soil moisture,” Geoderma, vol. 433, p. 116452, 2023.
Q. Li et al., “An attention-aware LSTM model for soil moisture and soil temperature prediction,” Geoderma, vol. 409, p. 115651, 2022.
M. Yadav et al., “UAV-enabled approaches for irrigation scheduling and water body characterization,” Agric. Water Manag., vol. 304, p. 109091, 2024.
M. Benzaouia et al., “Fuzzy-IoT smart irrigation system for precision scheduling and monitoring,” Comput. Electron. Agric., vol. 215, p. 108407, 2023.
E. Pazouki, “A practical surface irrigation design based on fuzzy logic and meta-heuristic algorithms,” Agric. Water Manag., vol. 256, p. 107069, 2021.
S. Jaiswal and M. S. Ballal, “Fuzzy inference based irrigation controller for agricultural demand side management,” Comput. Electron. Agric., vol. 175, p. 105537, 2020.
R. S. Krishnan et al., “Fuzzy logic based smart irrigation system using Internet of Things,” J. Clean. Prod., vol. 252, p. 119902, 2020.
S. Jamroen et al., “An Intelligent irrigation scheduling system using low-cost wireless sensor network toward sustainable and precision agriculture,” IEEE Access, vol. 8, pp. 172756–172769, 2020.
W. R. Mendes et al., “Fuzzy control system for variable rate irrigation using remote sensing,” Expert Syst. Appl., vol. 124, pp. 13–24, 2019.
E. Bwambale et al., “Smart irrigation monitoring and control strategies for improving water use efficiency in precision agriculture: A review,” Agric. Water Manag., vol. 260, p. 107324, 2022.
O. Obaideen et al., “An overview of smart irrigation systems using IoT,” Energy Nexus, vol. 5, p. 100124, 2022.
G. Patrizi et al., “A Virtual Soil Moisture Sensor for Smart Farming Using Deep Learning,” IEEE Trans. Instrum. Meas., vol. 71, pp. 1–11, 2022.
N. Jihani et al., “Kalman filter based sensor fault detection in wireless sensor network for smart irrigation,” Results Eng., vol. 20, p. 101395, 2023.
H. Hamami et al., “Application of wireless sensor networks in the field of irrigation: a review,” Comput. Electron. Agric., vol. 179, p. 105782, 2020.
O. Friha et al., “Internet of Things for the future of smart agriculture: A comprehensive survey of emerging technologies,” IEEE/CAA J. Autom. Sinica, vol. 8, no. 2, pp. 718–740, 2021.
E. Giusti and S. Marsili-Libelli, “A Fuzzy Decision Support System for irrigation and water conservation in agriculture,” Environ. Model. Softw., vol. 63, pp. 73–86, 2015.
M. Li, R. Sui, Y. Meng, and H. Yan, “A real-time fuzzy decision support system for alfalfa irrigation,” Comput. Electron. Agric., vol. 163, p. 104870, 2019.
F. T. Teshome et al., “Improving soil moisture prediction with deep learning and machine learning models,” Comput. Electron. Agric., vol. 226, p. 109414, 2024.
F. Sadat Hashemi et al., “Integrating RS data with fuzzy decision systems for innovative crop water needs assessment,” Int. J. Appl. Earth Observ. Geoinf., vol. 136, p. 104338, 2025.
C. Catalano et al., “Anomaly detection in smart agriculture systems,” Comput. Ind., vol. 143, p. 103750, 2022.
M. Neethu et al., “Hybrid Transformer Network for Soil Moisture Estimation in Precision Irrigation,” IEEE Access, 2024.
S. Wu and J. Diao, “Outlier Detection in Wireless Sensor Networks: A Survey,” IEEE Commun. Surveys Tuts., vol. 18, no. 1, pp. 589–623, 2016.
M. Sami et al., “A deep learning-based sensor modeling for smart irrigation system,” Agric. Water Manag., vol. 250, p. 106841, 2021.
H. Hendra et al., “A smartphone-controlled, solar-powered automatic fertilizing and watering system for sustainable agriculture,” Renew. Energy, vol. 198, pp. 123–132, 2023
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 IIUM Press
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
