Real-Time IoT-Integrated Ensemble LSTM–Bi-LSTM Framework for Greenhouse Microclimate Forecasting
Keywords:
Internet of Things (IoT), Ensemble Deep Learning, Greenhouse Microclimate Forecasting, Long Short-Term Memory (LSTM), Bidirectional LSTM, Time-Series Prediction, Precision Agriculture, Edge ComputingAbstract
Accurate prediction of greenhouse microclimates is essential for optimizing crop growth and resource utilization in precision agriculture. The research presents an IoT-integrated ensemble deep learning framework for real-time greenhouse microclimate forecasting using Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks. Environmental variables, including temperature, light intensity, soil moisture, and humidity, were acquired through IoT sensor nodes deployed in a controlled greenhouse environment. A benchmark greenhouse dataset was first used for model development and hyperparameter optimization, while an original IoT-based dataset collected during cucumber, tomato, and pepper cultivation at the Federal University Wukari, Nigeria, was used for validation and real-world deployment. The data were preprocessed through noise filtering, missing value imputation, Z-score-based outlier removal, and Min–Max normalization. A weighted ensemble strategy was then applied to combine LSTM and Bi-LSTM predictions for improved robustness. Experimental results show that the Bi-LSTM model outperformed the LSTM model, achieving R² = 0.9981, MAE = 0.0088, RMSE = 0.0110, and MSE = 0.0001, compared to LSTM results of R² = 0.9956, MAE = 0.0133, RMSE = 0.0167, and MSE = 0.0003. Statistical validation using paired t-test, Wilcoxon signed-rank test, confidence intervals, and multi-run analysis confirmed that the performance improvement is statistically significant and robust. The proposed framework enables accurate real-time microclimate forecasting and intelligent environmental monitoring, providing a scalable solution for precision greenhouse management, improved crop productivity, optimized energy utilization, and efficient irrigation scheduling.
References
1. Laplante, G., et al. (2021). Enhance domestic food security. [Publication details and page range needed].
2. Codeluppi, G., Cilfone, A., Davoli, L., & Ferrari, G. (2020). AI at the edge: A smart gateway for greenhouse air temperature forecasting. (pp. 348–353). [Conference or publication details needed].
3. Petrakis, T., Kavga, A., Thomopoulos, V., & Argiriou, A. A. (2022). Neural network model for greenhouse microclimate predictions. [Journal or publication details needed], 1–17.
4. Arunsandeep, G., & Chandramohan, V. P. (2026). [Article title and publication details needed]. [The supplied text contains Springer website navigation and subscription information rather than a complete reference.]
5. Rajendiran, G., & Rethnaraj, J. (2024). Optimizing lettuce crop yield prediction in an indoor aeroponic vertical farming system using IoT-integrated machine learning regression models. Revue d’Intelligence Artificielle, 38(3), 825–836.
6. Fasciolo, B., Grasso, N., Bruno, G., & Chiabert, P. (2025). Hybrid machine learning and physics-based model for estimating lettuce (Lactuca sativa) growth and resource consumption in aeroponic systems. [Journal or publication details needed], 1–16.
7. Ojo, M. O., & Zahid, A. (2022). Deep learning in controlled environment agriculture: A review of recent advancements, challenges and prospects. [Journal or publication details needed].
8. Cletus, F., & Emmanuel, A. (2024). Comparative analysis of machine learning models for greenhouse microclimate prediction. [Journal name needed], 4(1), 162–175.
9. Ansari, M. F., Dash, B., Sharma, P., & Yathiraju, N. (2022). The impact and limitations of artificial intelligence in cybersecurity: A literature review. International Journal of Advanced Research in Computer and Communication Engineering, 11(9), 81–90. doi.org
10. Rajeshwari, D., Manasa, K. B., & Shruthi, B. S. (2024). Automatic water pumping system for smart greenhouse using renewable energy resources. [Journal name needed], 13(4), 88–95.
11. Antonio, M., Benique, R., Enrique, L., Teves, F., Anibal, E., & Ortiz, V. (2025). Smart irrigation system with internet of things for rose cultivation in a basic greenhouse in Canchis, Cusco, 2025. International Journal of Reconfigurable and Embedded Systems, 14(3), 754–765. doi.org
12. Čisar, S. M., Molcer, P. S., & Pinter, R. (2025). Design and implementation of an IoT-based smart irrigation system for sustainable agriculture. [Journal name needed], 22(12), 315–328.
13. Venkataramanan, V., Pimpale, M., Kapure, V., Mishra, P., & Rokade, A. (2025). A hybrid IoT and machine learning framework for smart greenhouse automation in sustainable agriculture. [Journal name needed], 7(4), 58–69.
14. Benidis, K., et al. (2022). Deep learning for time series forecasting: Tutorial. [Journal name needed], 55(6). [Page range or article number needed].
15. Escamilla-García, A., Soto-Zarazúa, G. M., & Toledano-Ayala, M. (2020). Applications of artificial neural networks in greenhouse technology and overview for smart agriculture development. Applied Sciences. [Volume, issue, and article number needed].
16. Panda, B., & Mishra, S. (2025). An improved IoT-based hybrid predictive load forecasting model for a greenhouse integrated with demand-side management. [Journal name and publication details needed].
17. Jaiswal, N., Kumar, T. V., & Shukla, C. (2025). Smart drip irrigation systems using IoT: A review of architectures, machine learning models, and emerging trends. [Journal or publication details needed], 1–24.
18. Sahu, R., & Tripathi, P. (2025). An intelligent framework for monitoring and irrigation prediction for precision agriculture. Iranian Journal of Computer Science. doi.org
19. Royali, R. M., & Ariatmanto, D. (2026). Sistem kendali mikroklimat greenhouse cerdas berbasis hybrid GA-LSTM dan fuzzy logic controller. [Journal name needed], 7(2), 229–236.
20. Rahayu, A. U., Sastra, N. P., Bagus, I., & Manuaba, G. (2026). The evolution of weather-based deep learning in smart irrigation: A systematic review of sustainable approaches and perspectives. [Journal name needed], 8(2), 141–160.
21. Ahmed, N., & Farooqi, W. (n.d.). Pr rin t n ot pe er r iew Pr ep rin ot pe er ed.
22. Jagan, S., et al. (n.d.). AI-driven development of smart grid infrastructure with self-healing capabilities and edge and fog computing. [Publication details needed].
23. Benidis, K., Wang, Y., Bohlke-Schneider, M., Flunkert, V., Gasthaus, J., & Maddix, D. (n.d.). Deep learning for time series forecasting: Tutorial and literature survey. [Publication details needed].
24. Wu, Y., & Fu, X. (2026). Clean and smart energy technologies for agricultural energy internet systems: A comprehensive review and future perspectives. [Journal or publication details needed], 1–47.
25. Sharma, P., Malik, S., & Chand, M. (2026). Techno-ecological synergies: AI-IoT strategies for agrifood systems in sustainable eco-cities. [Journal or publication details needed], 1–24.
26. Li, S., Gong, X., Lin, W., Sun, Y., & Ma, Z. (2024). Review of transpired solar collectors: Heat and mass transfer mechanisms and enhancement, system integration, and performance assessment and optimisation. Journal of Cleaner Production, 450, Article 141967. doi.org
27. District, A., District, A., District, A., & Nadu, T. (2026). Synergistic impacts of drought, salinity, and temperature on wheat productivity. [Journal or publication details needed], 598–613.
Note: The author information appears corrupted and must be checked against the original publication.
28. Sarr, A., et al. (2026). Agroclimatic sensing, communication, and computational systems-based methods and technologies for precision irrigation management: Current state and prospects. [Full author list and publication details needed].
29. Xu, Y., Yazdinejad, A., Wang, H., & Kong, J. D. (2021). From detection to decision: A systematic literature review of AI and machine learning evolution in methane modelling. [Journal or publication details needed].
30. Jung, D., Lee, T. S., & Kim, K. (2022). A deep learning model to predict evapotranspiration and relative humidity for moisture control in tomato greenhouses. [Journal or publication details needed].
31. Esparza-Gómez, J. M., et al. (2023). Long short-term memory recurrent neural network and extreme gradient boosting algorithms applied in a greenhouse’s internal temperature prediction. Applied Sciences. [Full author list, volume, issue, article number, and DOI needed].
32. Wei, X., et al. (2024). Distribution characteristics and prediction of temperature and relative humidity in a South China greenhouse. [Full author list and publication details needed].
33. Lin, Y., Fang, S., Kang, L., Chen, C., Yao, M., & Kuo, B. (2024). Combining recurrent neural network and sigmoid growth models for short-term temperature forecasting and tomato growth prediction in a plastic greenhouse. [Journal or publication details needed].
34. Nocca, F. (2017). The role of cultural heritage in sustainable development: Multidimensional indicators as decision-making tool. Sustainability, 9(10), Article 1882. doi.org
35. El Ouaham, W., & Sadik, M. (2026). Smart greenhouses in the era of IoT and AI: A comprehensive review of AI applications, spectral sensing, multimodal data fusion, and intelligent systems. [Journal or publication details needed].
36. Ma, H., et al. (2026). IoT-based smart environmental control and air emission management in animal farming: A systematic review. Information Processing in Agriculture. doi.org
37. Prof, A., & Deniz, P. D. (2025). Advances in sensorics for ecological monitoring: Trends, challenges, and future perspectives. [Author names and publication details need verification].
38. Alawode, A., Blessing, A. O., & Chiamaka, O. T. (2024). Integrating IoT and AI in sustainable agriculture to mitigate environmental risk and financial misuse. International Journal of Research Publication and Reviews, 5(12), 2810–2828.
39. Ayorinde, A. S. (2025). Sustainable farming through AI-IoT synergy: Mitigating ecological damage and financial resource leakage. International Journal of Research Publication and Reviews, 6(6), 7845–7862.
40. Gund, R., Badgujar, C. M., Samiappan, S., & Jagadamma, S. (2025). Application of digital twin technology in smart agriculture: A bibliometric review. [Journal or publication details needed], 1–20.
41. Dimitriadis, P., Koutsoyiannis, D., & Iliopoulou, T. (2021). A global-scale investigation of stochastic similarities in marginal distribution and dependence structure of key hydrological-cycle processes. [Journal or publication details needed].
42. Jung, D., Seok, H., Jhin, C., Kim, H., & Hyun, S. (2020). Time-serial analysis of deep neural network models for prediction of climatic conditions inside a greenhouse. Computers and Electronics in Agriculture, 173, Article 105402. doi.org
43. Singh, R. D., & Tiwari, G. N. (2000). Thermal heating of controlled environment greenhouse: A transient analysis. [Journal name needed], 41, 505–522.
44. Wu, Q., Guan, F., Lv, C., & Huang, Y. (2021). Ultra-short-term multi-step wind power forecasting based on CNN-LSTM. doi: 10.1049/rpg2.12085.
