An IoT-driven predictive analytics framework for dynamic irrigation optimization in tomato cultivation

Maung Maung Htwe; Lachezar Filchev; Ekaterina Batchvarova; Sandra Jardim; Maung Maung Htwe; Lachezar Filchev; Ekaterina Batchvarova; Sandra Jardim

doi:10.3934/mbe.2026010

Mathematical Biosciences and Engineering

2026, Volume 23, Issue 1: 242-265. doi: 10.3934/mbe.2026010

Previous Article Next Article

Research article

An IoT-driven predictive analytics framework for dynamic irrigation optimization in tomato cultivation

1.
Climate, Atmosphere and Water Research Institute – Bulgarian Academy of Sciences
2.
Smart Cities Research Center, Polytechnic University of Tomar, Portugal

Received: 05 August 2025 Revised: 05 November 2025 Accepted: 18 November 2025 Published: 04 December 2025

Addressing the critical challenges of global food security and water scarcity, we introduced an Internet of Things (IoT)-driven predictive analytics framework for dynamic irrigation optimization in tomato cultivation. Our primary objective was to develop a robust model that accurately estimates daily water requirements, with the aim of minimizing water consumption while concurrently maintaining optimal soil health. This framework leverages a uniquely comprehensive, experimentally controlled dataset from multi-sensor IoT deployments, covering environmental conditions (air temperature, humidity, CO₂, pressure) and key soil parameters (humidity, temperature, electrical conductivity). Through a rigorous data preprocessing pipeline and a tailored feature engineering approach, critical temporal patterns, inter-variable relationships, and insights from agronomic indicators like Growing Degree Days (GDD), alongside other dynamically derived features, were extracted. A two-part eXtreme Gradient Boosting (XGBoost) regression model, combining classification and regression, was developed and validated to precisely predict the daily water volume needed per hectare. The innovation of this work lies in its ability to harness complex historical IoT data to build a sophisticated intelligence layer for irrigation scheduling. By demonstrating the model's accuracy in identifying optimal water levels under varying conditions and achieving significant water savings in a simulated dynamic optimization, this research provides foundational data-driven insights that can inform highly effective precision irrigation strategies. The model achieved a high R² of 0.9476 and yielded a potential water saving of 50.84% in a simulated dynamic optimization compared to the model's raw prediction. Such intelligence empowers farmers to significantly reduce water waste and prevent harmful over-irrigation, leading to more sustainable and efficient smart agriculture, which is critical for enhancing crop resilience and resource efficiency in a changing climate.
- Internet of Things (IoT),
- predictive analytics,
- irrigation optimization,
- water management,
- soil health,
- machine learning,
- XGBoost Model
Citation: Maung Maung Htwe, Lachezar Filchev, Ekaterina Batchvarova, Sandra Jardim. An IoT-driven predictive analytics framework for dynamic irrigation optimization in tomato cultivation[J]. Mathematical Biosciences and Engineering, 2026, 23(1): 242-265. doi: 10.3934/mbe.2026010

Related Papers:

Abstract

Addressing the critical challenges of global food security and water scarcity, we introduced an Internet of Things (IoT)-driven predictive analytics framework for dynamic irrigation optimization in tomato cultivation. Our primary objective was to develop a robust model that accurately estimates daily water requirements, with the aim of minimizing water consumption while concurrently maintaining optimal soil health. This framework leverages a uniquely comprehensive, experimentally controlled dataset from multi-sensor IoT deployments, covering environmental conditions (air temperature, humidity, CO₂, pressure) and key soil parameters (humidity, temperature, electrical conductivity). Through a rigorous data preprocessing pipeline and a tailored feature engineering approach, critical temporal patterns, inter-variable relationships, and insights from agronomic indicators like Growing Degree Days (GDD), alongside other dynamically derived features, were extracted. A two-part eXtreme Gradient Boosting (XGBoost) regression model, combining classification and regression, was developed and validated to precisely predict the daily water volume needed per hectare. The innovation of this work lies in its ability to harness complex historical IoT data to build a sophisticated intelligence layer for irrigation scheduling. By demonstrating the model's accuracy in identifying optimal water levels under varying conditions and achieving significant water savings in a simulated dynamic optimization, this research provides foundational data-driven insights that can inform highly effective precision irrigation strategies. The model achieved a high R² of 0.9476 and yielded a potential water saving of 50.84% in a simulated dynamic optimization compared to the model's raw prediction. Such intelligence empowers farmers to significantly reduce water waste and prevent harmful over-irrigation, leading to more sustainable and efficient smart agriculture, which is critical for enhancing crop resilience and resource efficiency in a changing climate.

References

[1]	E. Bwambale, G. Hu, X. Huang, Smart irrigation monitoring and control strategies for improving water use efficiency in precision agriculture: A review, Agric. Water Manag., 260 (2022), 107324. https://doi.org/10.1016/j.agwat.2021.107324 doi: 10.1016/j.agwat.2021.107324
[2]	A. Hadidi, A. Al-Khafaji, A. Al-Hamami, Smart irrigation system for smart agricultural using IoT: Concepts, architecture, and applications, in The Digital Agricultural Revolution, Wiley Online Library, (2022), 171–198. https://doi.org/10.1002/9781119823469.ch7
[3]	L. Belli, L. Davoli, G. Oddi, L. Preite, M. Galaverni, T. Ganino, et al., IoT-based data collection in a tomato cultivation under different irrigation regimes (V1), Mendeley Data, (2024). https://doi.org/10.17632/35wh56287y.1 doi: 10.17632/35wh56287y.1
[4]	S. Mansoor, S. Iqbal, S. M. Popescu, S. L. Kim, Y. S. Chung, J. H. Baek, et al., Integration of smart sensors and IoT in precision agriculture: Trends, challenges and future prospectives, Front. Plant Sci., 16 (2025), 1587869. https://doi.org/10.3389/fpls.2025.1587869 doi: 10.3389/fpls.2025.1587869
[5]	O. Khattach, O. Moussaoui, M. Hassine, End-to-end architecture for real-time IoT analytics and predictive maintenance using stream processing and ML pipelines, Sensors, 25 (2025), 2945. https://doi.org/10.3390/s25092945 doi: 10.3390/s25092945
[6]	Q. Zhu, X. Chen, Y. Liu, H. Wang, J. Li, S. Zhang, et al., A hybrid deep learning model for water quality prediction, IEEE Access, 13 (2025), 106406–106415. https://doi.org/10.1109/ACCESS.2025.3580741 doi: 10.1109/ACCESS.2025.3580741
[7]	G. K. Kumar, M. L. Bangare, P. M. Bangare, C. R. Raj, J. L. Arias-Gonzáles, B. Omarov, et al., IoT and SVM integrated intelligent irrigation system, Discover Sustain., 5 (2024), 6. https://doi.org/10.1007/s43621-024-00179-5 doi: 10.1007/s43621-024-00179-5
[8]	T. Miller, G. Mikiciuk, I. Durlik, M. Mikiciuk, A. Łobodzińska, M. Śnieg, The IoT and AI in agriculture: The time is now—A systematic review of smart sensing technologies, Sensors (Basel), 25 (2025), 3583. https://doi.org/10.3390/s25123583 doi: 10.3390/s25123583
[9]	M. Galaverni, G. Oddi, L. Preite, L. Belli, L. Davoli, T. Ganino, et al., An IoT-based data analysis system: A case study on tomato cultivation under different irrigation regimes, Comput. Electron. Agric., 229 (2025), 109660. https://doi.org/10.1016/j.compag.2024.109660 doi: 10.1016/j.compag.2024.109660
[10]	H. Zhang, L. He, F. Di Gioia, D. Choi, A. Elia, P. Heinemann, LoRaWAN based internet of things (IoT) system for precision irrigation in plasticulture fresh-market tomato, Smart Agric. Technol., 2 (2022), 100053. https://doi.org/10.1016/j.atech.2022.100053 doi: 10.1016/j.atech.2022.100053
[11]	V. H. U. Eze, E. C. Eze, G. U. Alaneme, P. E. Bubu, E. O. E. Nnadi, M. B. Okon, Integrating IoT sensors and machine learning for sustainable precision agroecology: Enhancing crop resilience and resource efficiency, Discover Agric., 3 (2025), 83. https://doi.org/10.1007/s44279-025-00247-y doi: 10.1007/s44279-025-00247-y
[12]	A. M. Zeyliger, O. S. Ermolaeva, V. V. Pchelkin, Assessment of irrigation efficiency by coupling remote sensing and ground-based data: Case study of sprinkler irrigation of Alfalfa in the Saratovskoye Zavolgie Region of Russia, Sensors, 23 (2023), 2601. https://doi.org/10.3390/s23052601 doi: 10.3390/s23052601
[13]	L. García, L. Parra, J. M. Jimenez, J. Lloret, P. Lorenz, IoT-based smart irrigation systems: An overview on the recent trends on sensors and IoT systems for irrigation in precision agriculture, Sensors, 20 (2020), 1042. https://doi.org/10.3390/s20041042 doi: 10.3390/s20041042
[14]	A. Bilal, X. Liu, H. Long, M. Shafiq, M. Waqar, Increasing Crop Quality and Yield with a Machine Learning-Based Crop Monitoring System, Comput. Mater. Contin., 76 (2023), 2401–2426. https://doi.org/10.32604/cmc.2023.037857 doi: 10.32604/cmc.2023.037857
[15]	Mazhar S, Sun G, Bilal A, Y. Li, M. Farhan, H. H. Awan, Digital and geographical feature detection by machine learning techniques using google earth engine for CPEC traffic management, Wirel. Commun. Mob. Comput., 2022 (2022), 9634032. https://doi.org/10.1155/2022/1192752 doi: 10.1155/2022/1192752
[16]	F. Mortazavizadeh, D. Bolonio, M. Mirzaei, J. L. Ng, S. V. Mortazavizadeh, A. Dehghani, et al., Advances in machine learning for agricultural water management: A review of techniques and applications, J. Hydroinform., 27 (2025), 474–492. https://doi.org/10.2166/hydro.2025.258 doi: 10.2166/hydro.2025.258
[17]	A. Elbeltagi, A. A. Alsumaiei, N. Elshaboury, Quantifying irrigation water demand through optimized daily vapor pressure deficit forecasting using LSTM and metaheuristic algorithms, J. Comput. Civ. Eng., 38 (2024), 04023035. https://doi.org/10.1061/JCCEE5.CPENG-7139 doi: 10.1061/JCCEE5.CPENG-7139
[18]	A. A. Esmail, M. A. Ibrahim, S. M. Abdallah, A. F. Hassan, Smart irrigation system using IoT and machine learning methods, in 2023 5th Novel Intelligent and Leading Emerging Sciences Conference (NILES), (2023), 225–230. https://doi.org/10.1109/NILES59815.2023.10296736
[19]	L. Benos, A. C. Tagarakis, G. Dolias, R. Berruto, D. Kateris, D. Bochtis, Machine learning in agriculture: A comprehensive updated review, Comput. Electron. Agric., 184 (2021), 106067. https://doi.org/10.3390/s21113758 doi: 10.3390/s21113758
[20]	B. Nsoh, A. Katimbo, H. Guo, D. M. Heeren, H. N. Nakabuye, X. Qiao, et al., Internet of Things-based automated solutions utilizing machine learning for smart and real-time irrigation management: A review, Sensors, 24 (2025), 7480. https://doi.org/10.3390/s24237480 doi: 10.3390/s24237480
[21]	E. Navarro, N. Costa, A. Pereira, A systematic review of IoT solutions for smart farming, Sensors, 20 (2020), 423. https://doi.org/10.3390/s20154231 doi: 10.3390/s20154231
[22]	P. P. Ray, Internet of things for smart agriculture: Technologies, practices and future direction, J. Ambient Intell. Humaniz. Comput., 8 (2017), 395–420. https://doi.org/10.3233/AIS-170440 doi: 10.3233/AIS-170440
[23]	P. Y. Chen, C. C. Chen, C. Kang, J. W. Liu, Y. H. Li, Soil water content prediction across seasons using random forest based on precipitation-related data, Comput. Electron. Agric., 230 (2025), 109802. https://doi.org/10.1016/j.compag.2024.109802 doi: 10.1016/j.compag.2024.109802
[24]	A. Vij, S. Vijendra, A. Jain, S. Bajaj, A. Bassi, A. Sharma, IoT and machine learning approaches for automation of farm irrigation, Proced. Comput. Sci., 167 (2020). https://doi.org/10.1016/j.procs.2020.03.440 doi: 10.1016/j.procs.2020.03.440
[25]	L. Pereira, R. Allen, M. Smith, Crop evapotranspiration estimation with FAO56: Past and future, Agric. Water Manag., 147 (2015), 4–20. https://doi.org/10.1016/j.agwat.2014.07.031 doi: 10.1016/j.agwat.2014.07.031
[26]	C. Pylianidis, S. Osinga, I. N. Athanasiadis, Introducing digital twins to agriculture, Comput. Electron. Agric., 184 (2021), 105942. https://doi.org/10.1016/j.compag.2020.105942 doi: 10.1016/j.compag.2020.105942
[27]	C. Verdouw, B. Tekinerdogan, A. Beulens, S. Wolfert, Digital twins in smart farming, Agric. Syst., 189 (2021), 103046. https://doi.org/10.1016/j.agsy.2020.103046 doi: 10.1016/j.agsy.2020.103046
[28]	G. Hu, C. Kubota, F. You, Cyber physical biological system in controlled environment agriculture for energy optimization: A comprehensive overview, key challenges, and future outlook, Energy, 280 (2025), 136153. https://doi.org/10.1016/j.energy.2025.136153 doi: 10.1016/j.energy.2025.136153
[29]	A. Bilal, J. A. Khan, A. Alzahrani, M. I. Pramanik, S. U. Islam, Fuzzy deep learning architecture for cucumber plant disease detection and classification, J. Big Data, 12 (2025), 117. https://doi.org/10.1186/s40537-025-01156-z doi: 10.1186/s40537-025-01156-z
[30]	X. Wang, The artificial intelligence-based agricultural field irrigation warning system using GA-BP neural network under smart agriculture, PLoS One, 20 (2025), e0317277. https://doi.org/10.1371/journal.pone.0317277 doi: 10.1371/journal.pone.0317277
[31]	U. Shafi, R. Mumtaz, J. García-Nieto, S. A. Hassan, S. A. R. Zaidi, N. Iqbal, Precision agriculture techniques and practices: From considerations to applications, Sensors, 19 (2019). https://doi.org/10.3390/s19173796 doi: 10.3390/s19173796
[32]	A. Kamilaris, F. X. Prenafeta-Boldú, Deep learning in agriculture: A survey, Comput. Electron. Agric., 147 (2018), 70–90. https://doi.org/10.1016/j.compag.2018.02.016 doi: 10.1016/j.compag.2018.02.016
[33]	J. Ge, L. Zhao, Z. Yu, H. Liu, L. Zhang, X. Gong, et al., Prediction of greenhouse tomato crop evapotranspiration using XGBoost machine learning model, Plants, 11 (2022), 1923. https://doi.org/10.3390/plants11151923 doi: 10.3390/plants11151923
[34]	J. K. G. Suarez, L. L. Lacatan, Yield prediction of maize using random forest algorithm, in Proceedings of Eighth International Congress on Information and Communication Technology, Springer, Singapore, 694 (2023), 481–490. https://doi.org/10.1007/978-981-99-3091-3_46
[35]	B. Mohammadi, M. Chen, M. R. Nikoo, A. Al-Alwani, R. Al-Waggad, An explainable hybrid framework for estimating daily reference evapotranspiration: Combining extreme gradient boosting with Nelder-Mead method, J. Hydrol., 626 (2024), 132130. https://doi.org/10.1016/j.jhydrol.2024.132130 doi: 10.1016/j.jhydrol.2024.132130
[36]	H. Yan, F. Xie, D. Long, Y. Yan, An accurate irrigation volume prediction method based on an optimized LSTM model, PeerJ Comput. Sci., 10 (2024), e2112. https://doi.org/10.7717/peerj-cs.2112 doi: 10.7717/peerj-cs.2112
[37]	N. Katta, N. Divya, S. Sahoo, S. K. Pani, Optimizing water irrigation in agriculture: Harnessing Bi-GRU networks for smart and sustainable crop management, in 2024 International Conference on Data Science and Network Security (ICDSNS), (2024), 1–6. https://doi.org/10.1109/ICDSNS62112.2024.10691309
[38]	A. Venkateshwar, V. C. Patil, Smart irrigation system based on spatial–temporal ConvLSTM for forecasting temperature and humidity, Int. J. Eng. Trends Technol., 70 (2022), 149–157. https://doi.org/10.14445/22315381/IJETT-V70I8P215 doi: 10.14445/22315381/IJETT-V70I8P215
[39]	S. O. Araújo, R. S. Peres, J. C. Ramalho, F. Lidon, J. Barata, Machine learning applications in agriculture: Current trends, challenges, and future perspectives, Agronomy, 13 (2024), 2976. https://doi.org/10.3390/agronomy13122976 doi: 10.3390/agronomy13122976
[40]	Y. Zheng, Z. Jiang, O. V. Kozlov, Y. P. Kondratenko, Fuzzy automatic control of the irrigation process for the IoT-based smart farming systems, J. Ambient Intell. Smart Environ., 16 (2024), 337–363. https://journals.sagepub.com/doi/abs/10.3233/AIS-230403
[41]	B. P. Roy, K. N. A. Sattar, A. A. Elngar, A Smart Irrigation System Using the IoT and Advanced Machine Learning Model, J. Smart Int. Things, 2024 (2024), 13–25. https://doi.org/10.2478/jsiot-2024-0009 doi: 10.2478/jsiot-2024-0009
[42]	Y. Tace, M. Tabaa, S. Elfilali, C. Leghris, H. Bensag, E. Renault, Smart irrigation system based on IoT and machine learning, Energy Rep., 8 (2024), 1025–1036. https://doi.org/10.1016/j.egyr.2022.07.088 doi: 10.1016/j.egyr.2022.07.088
[43]	K. Belouz, A. Nourani, S. Zereg, A. Bencheikh, Prediction of greenhouse tomato yield using artificial neural networks combined with sensitivity analysis, Sci. Hortic., 293 (2022), 110666. https://doi.org/10.1016/j.scienta.2021.110666 doi: 10.1016/j.scienta.2021.110666
[44]	N. G. A. El-Fattah, M. M. Ibrahim, S. Elsayed, M. S. Abd El-baki, Predicting tomato yield using RGB indices and artificial neural networks, Egypt. J. Soil Sci., 64 (2024), 123–134. https://doi.org/10.21203/rs.3.rs-4379462/v1 doi: 10.21203/rs.3.rs-4379462/v1
[45]	C. N. Kasimatis, E. Psomakelis, N. Katsenios, M. Papatheodorou, D. Apostolou, A. Efthimiadou, Industrial tomato yield prediction using machine learning models, Smart Agric. Technol., 11 (2025), 100920. https://doi.org/10.1016/j.atech.2025.100920 doi: 10.1016/j.atech.2025.100920

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)