Smart Agriculture Using UAV Imagery and Deep Learning
DOI:
https://doi.org/10.64137/3108088X/IJAES-V2I2P105Keywords:
Precision Agriculture, Unmanned Aerial Vehicles, Deep Learning, Convolutional Neural Networks, Remote Sensing, Yield PredictionAbstract
Climate change, population growth, and resource scarcity present unprecedented challenges to global food security, demanding a paradigm shift toward precision agriculture. Labor-intensive, low temporal resolution, and atmospheric interference represented drawbacks associated with traditional crop monitoring methods involving manual field surveys or satellite remote sensing. This study presents a novel hybrid smart agriculture framework using Unmanned Aerial Vehicle (UAV) images and deep learning architectures to achieve high-resolution crop health monitoring and fully automated yield prediction. Multi-season datasets of high-resolution multispectral and digital aerial imagery were collected over an extensive area comprising a variety of experimental plots. The imagery was processed using a hybrid deep learning architecture that comprised a modified Convolutional Neural Network (CNN) to extract spatial features and incorporate them into a Long Short-Term Memory network for temporal sequence analysis. The framework combines multispectral vegetation indices with raw spatial information in two tasks: classifying crop health, localized nutrient deficiencies, and predicting final crop yields. Using experimental data as the illustrative showcase, we validate that a deep learning model achieves crop stress classification accuracy of 96.4% and yield prediction with $R^2$ =0.89, outperforming traditional machine-learning models by a large margin on two axes (classification/regression). We develop a scalable and automated pipeline to enhance the translation of high resolution remote sensing into actionable agronomic insights, bridging disciplinary divides between computational science, plant biology, and agriculture such that it provides valuable tools for optimizing resource allocation in sustainable farms.
References
[1] S. Ahirwar, R. Swarnkar, S. Bhukya, and G. Namwade, "Application of Drone in Agriculture," International Journal of Current Microbiology and Applied Sciences, vol. 8, no. 01, pp. 2500–2505, Jan. 2019, doi: 10.20546/ijcmas.2019.801.264.
[2] M. Bhandari et al., "Assessing the Effect of Drought on Winter Wheat Growth Using Unmanned Aerial System (UAS)-Based Phenotyping," Remote Sensing, vol. 13, no. 6, p. 1144, Mar. 2021, doi: 10.3390/rs13061144.
[3] J. G. A. Barbedo, "A Review on the Use of Unmanned Aerial Vehicles and Imaging Sensors for Monitoring and Assessing Plant Stresses," Drones, vol. 3, no. 2, p. 40, Apr. 2019, doi: 10.3390/drones3020040
[4] T. Chen and C. Guestrin, "XGBoost: a Scalable Tree Boosting System," Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16, vol. 1, no. 1, pp. 785–794, Aug. 2016, doi: 10.1145/2939672.2939785.
[5] Kamilaris and F. X. Prenafeta-Boldú, "Deep learning in agriculture: A survey," Computers and Electronics in Agriculture, vol. 147, pp. 70–90, Apr. 2018, doi: 10.1016/j.compag.2018.02.016.
[6] T. Kattenborn, J. Leitloff, F. Schiefer, and S. Hinz, "Review on Convolutional Neural Networks (CNN) in vegetation remote sensing," ISPRS Journal of Photogrammetry and Remote Sensing, vol. 173, pp. 24–49, Mar. 2021, doi: 10.1016/j.isprsjprs.2020.12.010.
[7] Khan, A. D. Vibhute, S. Mali, and C. H. Patil, "A systematic review on hyperspectral imaging technology with a machine and deep learning methodology for agricultural applications," Ecological Informatics, vol. 69, p. 101678, July 2022, doi: 10.1016/j.ecoinf.2022.101678.
[8] N. Kussul, M. Lavreniuk, S. Skakun, and A. Shelestov, "Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data," IEEE Geoscience and Remote Sensing Letters, vol. 14, no. 5, pp. 778–782, May 2017, doi: 10.1109/lgrs.2017.2681128.
[9] V. Singh, N. Sharma, and S. Singh, "A review of imaging techniques for plant disease detection," Artificial Intelligence in Agriculture, vol. 4, Oct. 2020, doi: 10.1016/j.aiia.2020.10.002.
[10] M. Maimaitijiang, V. Sagan, P. Sidike, S. Hartling, F. Esposito, and F. B. Fritschi, "Soybean yield prediction from UAV using multimodal data fusion and deep learning," Remote Sensing of Environment, vol. 237, p. 111599, Feb. 2020, doi: 10.1016/j.rse.2019.111599.
[11] P. Radoglou-Grammatikis, P. Sarigiannidis, T. Lagkas, and I. Moscholios, "A Compilation of UAV Applications for Precision Agriculture," Computer Networks, vol. 172, p. 107148, Feb. 2020, doi: 10.1016/j.comnet.2020.107148.
[12] V. Sagan et al., "UAV-Based High Resolution Thermal Imaging for Vegetation Monitoring, and Plant Phenotyping Using ICI 8640 P, FLIR Vue Pro R 640, and thermoMap Cameras," Remote Sensing, vol. 11, no. 3, p. 330, Feb. 2019, doi: 10.3390/rs11030330.
[13] D. C. Tsouros, S. Bibi, and P. G. Sarigiannidis, "A Review on UAV-Based Applications for Precision Agriculture," Information, vol. 10, no. 11, p. 349, Nov. 2019, doi: 10.3390/info10110349.
[14] M. Weiss, F. Jacob, and G. Duveiller, "Remote sensing for agricultural applications: A meta-review," Remote Sensing of Environment, vol. 236, p. 111402, Jan. 2020, doi: 10.1016/j.rse.2019.111402.
[15] P. Muruganantham, S. Wibowo, S. Grandhi, N. H. Samrat, and N. Islam, "A Systematic Literature Review on Crop Yield Prediction with Deep Learning and Remote Sensing," Remote Sensing, vol. 14, no. 9, p. 1990, Apr. 2022, doi: 10.3390/rs14091990.
