The article develops automated algorithms for determining phenological and irrigation timing for cotton through an electronic system, optimizing fertilization, and determining yield increases.A comprehensive IoT-based monitoring system integrated with this algorithm is presented. Environmental and soil parameters are organized through a distributed network of IoT sensors (capacitive soil-moisture sensors, DHT22 temperature/humidity sensors, and BH1750 light-intensity sensors), equipped with ESP32 microcontrollers and wireless communication modules based on LoRa. The cotton field-oriented spectrum for real-time data transmission, storage in the SQL database, and preprocessing through peripheral computing mechanisms was implemented using the CCD protocol. For the calculation of vegetation indices, including the normalized differentiation vegetation index (NDVI), which allows for a quantitative assessment of the dynamics of plant development and growth, multi-spectral UUA images were used. Sensor data and spectral characteristics are developed in the Python programming language. The hybrid convolutional neural network (CNN), integrated with the long-term short-term memory (LSTM) model, was developed to classify phenological stages and predict temporary growth. The model was trained using the TensorFlow and Scikit-learn frameworks.
M. M. Talipov, “Computational Modeling and Analysis of Mechanical Power Consumption in Train Assemblers’ Work,” Proc. Int. Conf. on Applied Innovation in IT, vol. 13, no. 2, pp. 419-426, 2025, doi: 10.25673/120513.
J. Smith, A. Author, B. Author, et al., “IoT in Smart Agriculture,” Computers and Electronics in Agriculture, pp. 12-18, 2022.
L. Zhang, M. Li, X. Wang, et al., “Deep Learning for Crop Monitoring,” Remote Sensing, vol. 4, pp. 645-701, 2021, doi: 10.48550/arXiv.2112.11367.
R. Johnson, “NDVI Applications in Agriculture,” Agricultural Systems, vol. 8, pp. 114-122, 2020, [Online]. Available: https://doi.org/10.1016/j.compag.2021.106038.
M. Brown, S. Davis, L. Zhang, et al., “CNN-based Crop Classification,” IEEE Access, vol. 11, pp. 667-674, 2023, [Online]. Available: https://doi.org/10.3390/agriculture11080707.
A. Kumar, “LSTM for Agricultural Forecasting,” Sensors, vol. 3, pp. 122-131, 2022, doi: 10.3390/agriculture12020256.
S. Lee, H. Kim, Y. Park, et al., “IoT Sensor Networks in Farming,” IEEE Internet of Things Journal, vol. 10, pp. 25-33, 2023, [Online]. Available: https://doi.org/10.1016/j.jafr.2023.100776.
Y. Chen, J. Liu, X. Huang, et al., “Hybrid Deep Learning Models in Agriculture,” Applied Sciences, vol. 12, pp. 1-39, 2022, [Online]. Available: https://doi.org/10.48550/arXiv.2504.16141.
T. Wilson, “Water Optimization in Smart Farming,” Sustainability, vol. 13, pp. 241-238, 2021, [Online]. Available: https://doi.org/10.1016/j.agwat.2023.107824.
P. Garcia, M. Torres, S. Lopez, et al., “UAV-based Crop Monitoring,” Remote Sensing of Environment, vol. 238, pp. 1-21, 2020, [Online]. Available: https://doi.org/10.1016/j.atech.2025.101406.
M. Ubaydullayev, H. Asqarov, R. Nazirova, O. Sulaymonov, N. Usmonov, and D. Abdukarimova, “Research of the scientific basis of leaf surface formation indicators in medium fiber cotton varieties,” in Proc. XVI Int. Scientific-Practical Conf. “Actual Problems of Improving Farming Productivity and Agroecology” (IPFA 2024), E3S Web Conf., vol. 538, Art. no. 04010, 2024, [Online]. Available: https://doi.org/10.1051/e3sconf/202453804010.
