Transfer Learning for Predictive Models of Small-Scale Agricultural Crops
Blessings Samuel
Ladoke Akintola University of Technology
Abstract
You have to know which crops will grow to be able to grow more food and ensure that everyone has enough to eat. That is particularly true on small farms without a great deal of money or land that might not have the capacity for old-fashioned methods. However, it is difficult in these instances to make models where crops can be adequately predicted due to an absence of good, labelled data. The research pursues the concept of transfer learning as a valid solution to this problem. We investigate how utilizing data from comprehensive agricultural datasets aids in enhancing the accuracy of predictions about smaller crop datasets. We showcase the use of different deep learning architectures and transfer learning methods, enhancing the accuracy and robustness of tasks such as crop yield and health prediction. We further identify from our study that transfer learning speeds up the model training and utilization in resource and data-scarce farming situations. The work ends with consideration of the implication for real life and suggestions for further studies in the future.
Keywords
Transfer Learning, Crop Prediction, Small-Scale Agriculture, Deep Learning, Domain Adaptation, Precision Farming, Data Scarcity, Agricultural AI, Yield Forecasting, Model Generalization.
References
[1] Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 147, 70–90.
[2] Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419.
[3] Chlingaryan, A., Sukkarieh, S., & Whelan, B. (2018). Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review. Computers and Electronics in Agriculture, 151, 61–69.
[4] Liakos, K. G., Busato, P., Moshou, D., Pearson, S., & Bochtis, D. (2018). Machine learning in agriculture: A review. Sensors, 18(8), 2674.
[5] Reyes, C., et al. (2022). Domain adaptation in agricultural deep learning models: A review. Agricultural Systems, 195, 103290.
[6] Singh, A., Ganapathysubramanian, B., Singh, A. K., & Sarkar, S. (2018). Deep learning for plant stress phenotyping: Trends and future perspectives. Trends in Plant Science, 23(10), 883–898.
[7] You, J., Li, X., Low, M., Lobell, D., & Ermon, S. (2017). Deep Gaussian process for crop yield prediction based on remote sensing data. AAAI, 4559–4566.
[8] Jin, X., et al. (2021). Review of machine learning techniques for precision agriculture. Precision Agriculture, 22, 1123–1150.
[9] Rani, S., & Singh, S. (2021). Transfer learning-based approach for detection and classification of plant leaf diseases. Multimedia Tools and Applications, 80, 6943–6963.
[10] Chen, J., & Gupta, A. (2019). Webly supervised learning of convolutional networks. ICCV, 1431–1439.
[11] Sa, I., et al. (2018). DeepFruits: A fruit detection system using deep neural networks. Sensors, 16(8), 1222.
[12] Modaresnejad, M., & Shakeri, M. (2021). Crop yield prediction using LSTM recurrent neural network. Neural Processing Letters, 53, 1341–1355.
[13] Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6, 60.
[14] Cui, Y., Jia, M., Lin, T. Y., Song, Y., & Belongie, S. (2019). Class-balanced loss based on effective number of samples. CVPR, 9268–9277.
[15] Lu, Y., et al. (2020). An in-field automatic wheat disease diagnosis system. Computers and Electronics in Agriculture, 142, 369–379.