kaz29Вестник Казахстанско-Британского технического университетаHerald of the Kazakh-British Technical University1998-66882959-8109Казахстанско-Британский Технический Университет10.55452/1998-6688-2025-22-3-134-148kaz29-2111Research ArticleКОМПЬЮТЕРНЫЕ НАУКИCOMPUTER SCIENCEРЕШЕНИЯ НА ОСНОВЕ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА В СЕЛЬСКОМ ХОЗЯЙСТВЕ: ПРОГНОЗИРОВАНИЕ УДОБРЕНИЙ И ОБНАРУЖЕНИЕ БОЛЕЗНЕЙ ТОМАТОВ С ИСПОЛЬЗОВАНИЕМ МАШИННОГО ОБУЧЕНИЯ И КОМПЬЮТЕРНОГО ЗРЕНИЯAI-BASED SOLUTIONS IN AGRICULTURE: FERTILIZER PREDICTION AND TOMATO DISEASE DETECTION USING MACHINE LEARNING AND COMPUTER VISIONhttps://orcid.org/0009-0007-1350-4020СвамбаеваА. С.SvambayevaA. S.

магистр

г. Алматы

Master's degree

Almaty

a.svambayeva@kbtu.kzhttps://orcid.org/0009-0006-3107-2412ЖабагинР. Н.ZhabaginR. N.

студент

г. Алматы

student 

Almaty 

r_zhabagin@kbtu.kzКазахстанско-Британский технический университетКазахстанKazakh-British Technical UniversityKazakhstan202527092025223134148Copyright © Свамбаева А.С., Жабагин Р.Н., 20252025Свамбаева А.С., Жабагин Р.Н.Svambayeva A.S., Zhabagin R.N.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.kbtu.edu.kz/jour/article/view/2111

Это исследование направлено на использование искусственного интеллекта для улучшения сельскохозяйственной практики в Казахстане. Оно сосредоточено на обнаружении болезней листьев томатов и оптимизации удобрений. Модели глубокого обучения, включая GoogleNet (InceptionV3), VGG16, ResNet50, MobileNetV2 и пользовательскую сверточную нейронную сеть (CNN), были оценены для обнаружения болезней. GoogleNet показала самую высокую точность – 99,72%, что показывает ее способность обнаруживать болезни листьев томатов. Для оптимизации удобрения были оценены различные модели на основе машинного обучения, а именно деревья решений, K-ближайшие соседи, CNN, дерево решений Gradient Boosting, LogitBoost с использованием различных функций PCA. Модель CNN, которая использовала шесть функций PCA, достигла наилучшей точности – 97,58%. Это показывает, как хорошие функции могут помочь в прогнозировании. Результаты показывают, что использование технологий ИИ может значительно повысить производительность сельского хозяйства и устойчивость Казахстана за счет точного обнаружения болезней и оптимизированного использования ресурсов. В будущих исследованиях модели следует внедрить в систему сельского хозяйства в режиме реального времени, а также расширить их на большее количество культур и условий.

This research is aimed at using artificial intelligence to improve agricultural practice in Kazakhstan. It focuses on tomato leaf disease detection and fertilizer optimization. Deep learning models – including GoogleNet (InceptionV3), VGG16, ResNet50, MobileNetV2, and a custom Convolutional Neural Network (CNN)–were evaluated for disease detection. GoogleNet had the highest accuracy of 99.72%, which shows its capability to detect tomato leaf diseases. For the optimization of the fertilizer, different machine learning-based models, namely Decision Trees, K-Nearest Neighbors, CNN, Gradient Boosting Decision Tree, LogitBoost were assessed using various PCA features. The CNN model that used six PCA features achieved the best accuracy at 97.58%. This shows how good features can help in prediction. The results show using AI technologies can significantly increase the agricultural productivity and sustainability of Kazakhstan through precise detection of diseases and optimized use of resources. In the future studies, models should be deployed to the real-time system of agriculture and also should be expanded to more crops and conditions.

оптимизациякомпьютерное зрениемашинное обучениеглубокое обучениесверточные нейронные сетисельское хозяйствоискусственный интеллектобнаружение болезней растенийоптимизация удобренийпредиктивное моделированиеoptimizationcomputer visionmachine learningdeep learningconvolutional neural networksagricultureartificial intelligenceplant disease detectionfertilizer optimizationpredictive modelingReferencesRama Devi, O., Naga Lakshmi, P., Naga Babu, S., Vinaya Sree Bai, K., Sowmya, and Akansha. Fertilizer Forecasting using Machine Learning. Proceedings of the 2023 International Conference on Inventive Computation Technologies (ICICT), Lalitpur, Nepal, April 2023. https://doi.org/10.1109/ICICT57646.2023.10134061.Rama Devi, O., Naga Lakshmi, P., Naga Babu, S., Vinaya Sree Bai, K., Sowmya, and Akansha. Fertilizer Forecasting using Machine Learning. Proceedings of the 2023 International Conference on Inventive Computation Technologies (ICICT), Lalitpur, Nepal, April 2023. https://doi.org/10.1109/ICICT57646.2023.10134061.Vaishnavi, S., Shanmugam, N., Kiran, G., and Saraswathi Priyadharshini, A. Dependency analysis of various factors and ML models related to Fertilizer Recommendation. Proceedings of the 2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC), Jalandhar, India, May 2023. https://doi.org/10.1109/ICSCCC58608.2023.10176974.Vaishnavi, S., Shanmugam, N., Kiran, G., and Saraswathi Priyadharshini, A. Dependency analysis of various factors and ML models related to Fertilizer Recommendation. Proceedings of the 2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC), Jalandhar, India, May 2023. https://doi.org/10.1109/ICSCCC58608.2023.10176974.Ali, Md S., Rohit, B., Roshith, R., Biradar, V., and Jabbar, M.A. Crop Prediction & Fertilizer Recommendation using AODE Algorithm. Proceedings of the 2024 IEEE 9th International Conference for Convergence in Technology (I2CT), Pune, India, April 2024.https://doi.org/10.1109/I2CT61223.2024.10543894.Ali, Md S., Rohit, B., Roshith, R., Biradar, V., and Jabbar, M.A. Crop Prediction & Fertilizer Recommendation using AODE Algorithm. Proceedings of the 2024 IEEE 9th International Conference for Convergence in Technology (I2CT), Pune, India, April 2024.https://doi.org/10.1109/I2CT61223.2024.10543894.Mohanty, S.P., Hughes, D.P., and Salathé, M. Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419 (2016). https://doi.org/10.3389/fpls.2016.01419.Mohanty, S.P., Hughes, D.P., and Salathé, M. Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419 (2016). https://doi.org/10.3389/fpls.2016.01419.Sladojevic, S., et al. Deep neural networks based recognition of plant diseases by leaf image classification. Computational Intelligence and Neuroscience, 2016, Article ID 3289801 (2016). https://doi.org/10.1155/2016/3289801.Sladojevic, S., et al. Deep neural networks based recognition of plant diseases by leaf image classification. Computational Intelligence and Neuroscience, 2016, Article ID 3289801 (2016). https://doi.org/10.1155/2016/3289801.Brahimi, M., Boukhalfa, K., and Moussaoui, A. Deep learning for tomato diseases: classification and symptoms visualization. Applied Artificial Intelligence, 31 (4), 299–315 (2017). https://doi.org/10.1080/08839514.2017.1315516.Brahimi, M., Boukhalfa, K., and Moussaoui, A. Deep learning for tomato diseases: classification and symptoms visualization. Applied Artificial Intelligence, 31 (4), 299–315 (2017). https://doi.org/10.1080/08839514.2017.1315516.Fuentes, A., et al. A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition. Sensors, 17 (9), 2022 (2017). https://doi.org/10.3390/s17092022.Fuentes, A., et al. A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition. Sensors, 17 (9), 2022 (2017). https://doi.org/10.3390/s17092022.Durmuş, H., Güneş, E.O., and Kırcı, M. Disease detection on the leaves of the tomato plants by using deep learning. Proceedings of the 2017 6th International Conference on Agro-Geoinformatics, Fairfax, VA, USA, 2017. https://doi.org/10.1109/Agro-Geoinformatics.2017.8047016.Durmuş, H., Güneş, E.O., and Kırcı, M. Disease detection on the leaves of the tomato plants by using deep learning. Proceedings of the 2017 6th International Conference on Agro-Geoinformatics, Fairfax, VA, USA, 2017. https://doi.org/10.1109/Agro-Geoinformatics.2017.8047016.Zhang, Keke, et al. «Can deep learning identify tomato leaf disease?.» Advances in Multimedia 2018 (2018). https://doi.org/10.1155/2018/6710865.Zhang, Keke, et al. «Can deep learning identify tomato leaf disease?.» Advances in Multimedia 2018 (2018). https://doi.org/10.1155/2018/6710865.Jiang, P., et al. Real-time detection of apple leaf diseases using deep learning approach based on improved convolutional neural networks. IEEE Access, 7, 59069–59080 (2019). https://doi.org/10.1109/ACCESS.2019.2914929.Jiang, P., et al. Real-time detection of apple leaf diseases using deep learning approach based on improved convolutional neural networks. IEEE Access, 7, 59069–59080 (2019). https://doi.org/10.1109/ACCESS.2019.2914929.Adhikari, S., et al. Tomato plant diseases detection system using image processing. Proceedings of the 1st KEC Conference on Engineering and Technology, Lalitpur, Nepal, Vol. 1, 2018.Adhikari, S., et al. Tomato plant diseases detection system using image processing. Proceedings of the 1st KEC Conference on Engineering and Technology, Lalitpur, Nepal, Vol. 1, 2018.Priya, K.D., et al. ENSEMBLED CROPIFY – Crop & Fertilizer Recommender System with Leaf Disease Prediction. Proceedings of the 2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA), Tirunelveli, India, 2023. https://doi.org/10.1109/ICIDCA56705.2023.10100117.Priya, K.D., et al. ENSEMBLED CROPIFY – Crop & Fertilizer Recommender System with Leaf Disease Prediction. Proceedings of the 2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA), Tirunelveli, India, 2023. https://doi.org/10.1109/ICIDCA56705.2023.10100117.

The authors declare that there are no conflicts of interest present.