Detection of Locust Breeding and Feeding Zones Using Hyperspectral Signatures and Environmental Variables in South Nyanza Region, Kenya

Emmanuel Ochako  Manyange; Juliana  Kamaghe; Lilian  Mutalemwa

doi:10.51903/jtie.v5i2.554

Authors

Emmanuel Ochako Manyange Dept. of Information Technology, Mount Kigali University, Rwanda, 575
Juliana Kamaghe Dept. of Maths and ICT, Open University of Tanzania, Tanzania, 23049 https://orcid.org/0009-0008-0917-2366
Lilian Mutalemwa Dept. of Maths and ICT, Open University of Tanzania, Tanzania, 23049 https://orcid.org/0000-0003-4342-5562

DOI:

https://doi.org/10.51903/jtie.v5i2.554

Keywords:

Hyperspectral remote sensing, desert locust surveillance, artificial intelligence, Random Forest, environmental indicators, South Nyanza

Abstract

Desert locust infestations continue to threaten agricultural productivity, food security, and environmental sustainability across East Africa. Conventional locust surveillance approaches remain largely dependent on field-based monitoring systems that are reactive, labor-intensive, and constrained by limited spatial coverage. This study investigated the hyperspectral signatures and environmental variables associated with locust breeding and feeding zones in South Nyanza, Kenya, using an Artificial Intelligence (AI)-driven hyperspectral remote sensing framework. Environmental variables including vegetation indices, soil moisture, rainfall, temperature, vegetation stress indicators, and hyperspectral bands were analyzed using correlation analysis, binary logistic regression, Random Forest classification, and variable importance ranking. Correlation analysis revealed weak relationships between individual environmental indicators and historical locust occurrence, with all predictors demonstrating statistically insignificant relationships (p > 0.05). Logistic regression findings similarly indicated that no individual environmental variable independently predicted locust occurrence. However, Random Forest classification achieved a classification accuracy of 75.33% with an Out-of-Bag error rate of 24.67%, suggesting moderate predictive capability when multiple variables were integrated. Variable importance analysis identified rainfall, soil moisture, temperature, and vegetation-related indicators as dominant predictors. The findings suggest that locust breeding and feeding habitats are influenced by complex multidimensional interactions rather than isolated environmental indicators. The study demonstrates the practical potential of AI-driven hyperspectral frameworks for strengthening locust surveillance and early warning systems within emerging high-risk agricultural regions.

References

Cressman, K. (2013). Role of remote sensing in desert locust early warning. Journal of Applied Remote Sensing, 7(1), 075098. https://doi.org/10.1117/1.JRS.7.075098

Cressman, K. (2016). eLocust3: The role of new technology in desert locust early warning systems. Food and Agriculture Organization of the United Nations.

Cressman, K., & Hodson, D. (2019). Surveillance, information sharing and early warning systems for transboundary plant pests. Outlooks on Pest Management, 30(6), 252–256. https://doi.org/10.1564/v30_dec_02

Food and Agriculture Organization. (2020). Desert locust upsurge: Progress report and response overview. Food and Agriculture Organization of the United Nations.

Food and Agriculture Organization. (2021). Desert locust guidelines: Survey. Food and Agriculture Organization of the United Nations.

Hunter, D. M. (2004). Advances in the control of locusts (Orthoptera: Acrididae) in eastern Africa. Journal of Orthoptera Research, 13(1), 25–34.

Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 147, 70–90. https://doi.org/10.1016/j.compag.2018.02.016

Khan, Z. R., Midega, C. A. O., Pittchar, J., Pickett, J. A., & Bruce, T. J. (2014). Push-pull technology: A conservation agriculture approach for integrated management of insect pests. Annual Review of Entomology, 59(1), 147–165.

Magor, J. I., Lecoq, M., & Hunter, D. M. (2008). Preventive control and desert locust plagues. Crop Protection, 27(12), 1527–1533. https://doi.org/10.1016/j.cropro.2008.08.006

Makini, F. W., Mose, L. O., Kamau, G. M., Makelo, M. N., Salasya, B. D., Mulinge, W. W., & Ong’engo, H. (2018). Status of agricultural extension and advisory services in Kenya. Kenya Agricultural and Livestock Research Organization.

Mongare, P. N., Ouma, G., & Ombui, J. (2023). Climate variability and locust outbreak dynamics in East African agricultural systems. African Journal of Agricultural Research, 19(4), 322–337.

Mubarak, S., Nyongesa, H., & Omwenga, E. (2022). Artificial intelligence adoption challenges in agricultural monitoring systems in developing countries. International Journal of Agricultural Informatics, 13(2), 45–59.

Pekel, J. F., Cottam, A., Gorelick, N., & Belward, A. S. (2016). High-resolution mapping of global surface water and its long-term changes. Nature, 540(7633), 418–422. https://doi.org/10.1038/nature20584

Rembold, F., Atzberger, C., Savin, I., & Rojas, O. (2013). Using low resolution satellite imagery for yield prediction and yield anomaly detection. Remote Sensing, 5(4), 1704–1733. https://doi.org/10.3390/rs5041704

Shafiee, M., Babaei, M., & Karami, A. (2021). Artificial intelligence applications in agricultural remote sensing: A review of machine learning approaches. Remote Sensing Applications: Society and Environment, 22, 100493.

Singh, A., Ganapathysubramanian, B., Singh, A. K., & Sarkar, S. (2016). Machine learning for high-throughput stress phenotyping in plants. Trends in Plant Science, 21(2), 110–124.

Thenkabail, P. S., Lyon, J. G., & Huete, A. (2012). Hyperspectral remote sensing of vegetation. CRC Press.

Van Mele, P., Bentley, J. W., & Guéi, R. G. (2010). African seed enterprises: Sowing the seeds of food security. CAB International.

Wang, L., Qu, J. J., Hao, X., & Zhu, Q. (2010). Sensitivity studies of vegetation indices to environmental changes. Remote Sensing of Environment, 114(5), 1070–1086.

World Bank. (2021). Emergency locust response program implementation report for Kenya. World Bank Group.

Yu, H., Zhang, M., Wang, J., & Liu, X. (2021). Machine learning approaches for ecological monitoring using hyperspectral remote sensing data. Ecological Informatics, 64, 101365.

Zhang, C., & Kovacs, J. M. (2012). The application of small unmanned aerial systems for precision agriculture: A review. Precision Agriculture, 13(6), 693–712.