International Journal for Asian Contemporary Research, 6(1):24-30
AI-Driven High-Throughput Phenotyping for Drought-Resilient Maize ( Zea mays L) in Bangladesh
Received: 28 July, 2026 || Accepted: 20 August, 2026 || Published: 27 August, 2026
A B S T R A C T
Drought stress is a major limitation for maize productivity in Bangladesh, creating a need for rapid and reliable approaches to identify tolerant genotypes. This study developed an artificial intelligence (AI)-assisted high-throughput phenotyping framework by integrating unmanned aerial vehicle (UAV)-based multispectral imaging, machine learning, and conventional statistical analyses for drought response evaluation in maize. Four elite maize genotypes (BHM-9, BHM-14, BHM-17, and BWMRI-1) were evaluated under managed drought conditions maintained at 40% field capacity. A comprehensive dataset consisting of agronomic, physiological, and UAV-derived spectral traits was generated throughout crop development. Analysis of variance revealed significant differences among genotypes for important drought-related traits, including plant height, grain yield attributes, and relative water content. Multivariate analyses, including principal component analysis (PCA) and hierarchical clustering, effectively differentiated drought-responsive genotypes, with BHM-9 showing superior performance under water-limited conditions. AI-based prediction models combining ResNet-50 and Random Forest algorithms demonstrated strong predictive ability for drought-related phenotypic traits, achieving high accuracy with R² values above 0.85 and low prediction errors. The findings demonstrate that AI-driven phenotyping can accelerate drought tolerance screening by combining rapid image-based assessment with physiological measurements. The identified tolerant genotype and developed analytical framework may support future maize breeding programs aimed at improving drought resilience in Bangladesh.
Keywords: Maize; drought tolerance; high-throughput phenotyping; UAV imaging; artificial intelligence; machine learning.
Copyright information: Copyright © 2026 Author(s) retain the copyright of this article. This work is licensed under a Creative Commons Attribution 4.0 International License
To cite this article: Bayazid, K.N., Ferdous, J., Mahmud, Q.M., Bir,M.S.H., Ullah, M.A., Khalil, I., Akther1, Maria Akter, M.T., Nishe, S. and Jharna, M.B.A. (2026). AI-Driven High-Throughput Phenotyping for Drought-Resilient Maize ( Zea mays L) in Bangladesh. International Journal for Asian Contemporary Research, 6 (1), 24-30
References
- Adak, A., DeSalvio, A. J., Arik, M. A., & Murray, S. C. (2024). Field-based high-throughput phenotyping enhances phenomic and genomic predictions for grain yield and plant height across years in maize. G3: Genes, Genomes, Genetics, 14.
- An, J., Li, W., Li, M., Cui, S., & Yue, H. (2019). Identification and Classification of Maize Drought Stress Using Deep Convolutional Neural Network. Symmetry, 11, 256.
- Bongomin, O., et al. (2024). UAV image acquisition and processing for high-throughput phenotyping in agricultural research and breeding programs. The Plant Phenome Journal.
- Farooq, M. A., Gao, S., Hassan, M. A., Huang, Z., Rasheed, A., Hearne, S., Prasanna, B., Li, X., & Li, H. (2024). Artificial intelligence in plant breeding. Trends in Genetics, 40, 891–908.
- Gano, B., et al. (2024). Drone-based imaging sensors, techniques, and applications in plant phenotyping for crop breeding: A comprehensive review. The Plant Phenome Journal.
- Herrmann, I., Bdolach, E., Montekyo, Y., Rachmilevitch, S., Townsend, P. A., & Karnieli, A. (2019). Assessment of maize yield and phenology by drone-mounted superspectral camera. Precision Agriculture, 21, 51–76.
- Hoque, M. I. U., Uddin, M. N., Fakir, M. S. A., & Rasel, M. (2018). Drought and salinity affect leaf and root anatomical structures in three maize genotypes. Journal of the Bangladesh Agricultural University, 16, 47–55.
- Hossain, M. (2021). Drought Stress in Maize: Impacts and Adaptation in Northwest Bangladesh. J. Agro. Environ., 15(2), 45–58.
- Rahman, M. (2022). Drought Tolerance Mechanisms in Bangladesh Maize. Crop Sci., 62(4), 1892–1905.
- Shamsuddin, D., et al. (2024). Multimodal Deep Learning Integration of Image, Weather, and Phenotypic Data Under Temporal Effects for Early Prediction of Maize Yield. Remote Sensing, 16, 4043.
- Shao, G., et al. (2022). Estimation of transpiration coefficient and aboveground biomass in maize using time-series UAV multispectral imagery. The Crop Journal, 10, 1376–1385.
- Sheikh, M., et al. (2024). Integrating artificial intelligence and high-throughput phenotyping for crop improvement. Journal of Integrative Agriculture, 23, 1787–1802.
- Song, P., Wang, J., Guo, X., Yang, W., & Zhao, C. (2021). High-throughput phenotyping: Breaking through the bottleneck in future crop breeding. The Crop Journal, 9, 633–645.
- Teodoro, P.E., et al. (2024). High-throughput phenotyping in maize and soybean genotypes using vegetation indices and computational intelligence. Plant Methods, 20, 164.
- Zhang, X. (2022). UAV Phenotyping for Drought Response in Cereals. Plant Phenomics, 4, 987.
Article View: 21 times