Abstract

Nigerian agriculture's fixed-schedule fertigation causes low efficiency and nutrient leaching. A stacked‑ensemble model is developed for precision fertigation that jointly predicts fertigation need, rate (kg/ha) and timing (Early/Optimal/Late). To train and evaluate the ensemble, a unified dataset was integrated, comprising 12,840 records and 42 variables from a Nigerian soil–weather–yield dataset, a locally sourced Nigerian IoT sensor series and historical weather/NDVI feeds. An LSTM soil‑dynamics model, an XGBoost rate regressor and Random Forest need/timing classifiers are fused through an XGBoost meta‑learner trained on out‑of‑fold predictions. On held‑out partitions, the ensemble reduced rate MAE from 0.55 to 0.49 kg/ha (−10.9%) and RMSE from 0.68 to 0.61 kg/ha (−10.3%; R² 0.88→0.92), raised need F1 from 0.83 to 0.86 (accuracy 0.87→0.89; AUC 0.89→0.93) and timing macro‑F1 from 0.84 to 0.86, with well‑calibrated probabilities (Brier 0.082). The trained ensemble was deployed through a RESTful API and responsive dashboard; under concurrent load, the system recorded 0% request errors with 1.88s median API latency, demonstrating practical deployability for Nigerian smallholder agriculture.

References

• Matthew, M. D., Timothy, E., & Olorunshola, E. O. (2025). Adaptation strategies to climate variability among maize farmers in Oyo State, Nigeria. Journal of Agricultural Extension, 29(3), 111–117. https://doi.org/10.4314/jae.v29i3.11
• Bamigboye, F. O., & Ademola, E. O. (2019). Internet of Things: The present status, future impacts and challenges in Nigerian agriculture. In J. A. Lozano, R. J. Howlett, & L. C. Jain (Eds.), Internet of things: Information processing in an increasingly connected world (pp. 211–217). Springer. https://doi.org/10.1007/978-3- 030-15651-0_17
• Wu, M., Xiong, J., Li, R., Dong, A., Lv, C., Sun, D., Abdelghany, A. E., Zhang, Q., Wang, Y., & Niu, W. (2023). Predicting fertiliser concentration for precision irrigation under mixed variable-rate fertigation using machine learning: A case study of combined fertilisation with dipotassium hydrogen phosphate and potassium chloride. Research Square. https://doi.org/10.21203/rs.3.rs-2996273/v1
• Masud Cheema, M. J., Iqbal, T., Daccache, A., Hussain, S., & Awais, M. (2023). Precision agriculture technologies. In Precision agriculture (pp. 231250). Elsevier. https://doi.org/10.1016/B97 8-0-443- 18953-1.00011-8
• Li, Z., Zhou, X., Cheng, Q., Fei, S., & Chen, Z. (2023). A machine-learning model based on the fusion of spectral and textural features from UAV multi-sensors to analyze the total nitrogencontent in winter wheat. Remote Sensing, 15(8), 2152. https://doi.org/10.3390/rs15082152
• Idris, F., Abdul Latiff, A., Buntat, M. A., Lecthmanan, Y., & Berahim, Z. (2024). IoT- based fertigation system for agriculture. Bulletin of Electrical Engineering and Informatics, 13(3), 1574–1581. https://doi.org/10.11591/eei.v13i3.6829
• Oguntoye, J. P., Olayiwola, A. A., Ogunkola, T. G., Fanibuyan, J. O., Ganiyu, R. A., & Olayiwola, D. S. (2024). Real-time IoT-based smart fertigation system for sustainable and precision agriculture. The Journal of Computer Science and Its Applications, 31(2).
• Nyakuri, J., Bizimana, J., Bigirabagabo, A., Gafirita, J., Munyaneza, M., & Nzemerimana, J. (2022). IoT and AI based smart soil quality assessment for data- driven irrigation and fertilisation. American Journal of Computing and Engineering, 5(2), 1–14. https://doi.org/10.47672/ajce.1232
• Adamo, T., Caivano, D., Colizzi, L., Dimauro, G., Guerriero, E., & Zhang, Q. (2025). Optimisation of irrigation and fertigation in smart agriculture: An IoT-based micro-services framework. Smart Agricultural Technology, 11, Article 100885. https://doi.org/10.1016/j.atech.2025.100885
• Biase, A. G., Albertini, T. Z., & de Mello, R. F. (2022). On supervised learning to model and predict cattle weight in precision livestock breeding. Computers and Electronics in Agriculture, 195, Article 106706. https://doi.org/10.1016/j.compag.2022.106706
• Hudaya, R., Margana, D. B., Hartono, R. W. T., & Magribi, A. N. (2020). Fertigation management system model using supervised machine learning and time-duration method on agricultural industrial land. In Proceedings of the International Seminar of Science and Applied Technology (ISSAT 2020). https://doi.org/10.2991/aer.k.201221.007
• Zhang, Q. (2023). Opinion paper: Precision agriculture, smart agriculture, or digital agriculture. Computers and Electronics in Agriculture, 211, Article 107982. https://doi.org/10.1016/j.compag.2 023.107982
• Wu, M., Xiong, J., Li, R., Dong, A., Lv, C., Sun, D., Abdelghany, A. E., Zhang, Q., Wang, Y., Siddique, K. H. M., & Niu, W. (2024). Precision forecasting of fertiliser components’ concentratio s in mixed variable-rate fertigation through machine learning.
• Mish, A. (n.d.). Crop yield data with soil and weather dataset [Data set]. Kaggle. Retrieved fromhttps://www.kaggle.com/datasets/anshumish/crop- yield-data-with-soil-and-weather-dataset
• Diarah, R. S., Osueke, C., Aderemi, A., George, I., & Emeng, E. (2026). Dataset on real-time IoT-based fertigation, irrigation, and hydroponics smart agriculture system for precision farming applications using STM32F401RE microcontroller architecture (Version 1) [Data set]. Mendeley Data. https://doi.org/10.17632/96nj4yyzkg.1
• OpenWeather Ltd. (2024). OpenWeather Current Weather and 5-Day Forecast API. Retrieved from https://openweathermap.org/api