Thesis subject

MSc thesis topic: Remote Sensing for Maize Phenotyping: Integrating Hyperspectral Imaging, Machine Learning, and Radiative Transfer Modelling

Accurate phenotyping of maize (Zea mays L.) is essential for advancing agricultural research, optimizing nitrogen (N) management, and improving crop yields. Traditional phenotyping methods are labour-intensive and lack scalability. UAV-based hyperspectral imaging, integrated with LiDAR and radiative transfer models (RTMs), offers a non-destructive approach to assessing maize growth parameters. This study leverages remote sensing and machine learning to characterize maize canopy structure, photosynthetic efficiency, and nitrogen stress responses.

Nitrogen availability significantly influences maize physiology, affecting photosynthetic capacity, biomass production, and overall crop performance. Key indicators such as solar-induced fluorescence (SIF), assimilation rate, chlorophyll content (Cab), and leaf area index (LAI) provide critical insights into maize health. UAV-mounted hyperspectral, FluorSpec, thermal, and LiDAR sensors enable high-resolution monitoring of these traits. By integrating biophysical models and machine learning, this research aims to enhance precision agriculture techniques for maize phenotyping.

Relevance to research/projects at GRS or other groups

This study aligns with ongoing research topics at the Geo-Information Science and Remote Sensing (GRS) group, led by Prof. Lammert Kooistra, on precision agriculture, crop stress monitoring, and sustainable nitrogen management. It contributes to hyperspectral remote sensing applications in agronomy, with potential collaborations between GRS group and experimental agronomy teams at WUR.

Objectives and Research questions

This study aims to evaluate the impact of different nitrogen treatments on key physiological traits in maize crops using UAV-based hyperspectral, thermal, and LiDAR imaging. By integrating radiative transfer models (RTMs) and machine learning, the research will improve the accuracy of nitrogen stress detection and identify the most effective spectral indices for precision agriculture applications.

How do different nitrogen levels influence the relationship between solar-induced fluorescence (SIF) and photosynthetic traits retrieved through RTM inversion in maize?
What is the impact of canopy structural variations on the retrieval accuracy of physiological traits under different nitrogen conditions in maize?
How does the interaction between leaf biochemical composition and canopy architecture affect nitrogen stress detection across different maize varieties?

Requirements

Required: GeoScripting, Remote Sensing, Advance Earth Observation
Optional: Spatial Modelling and Statistics, Deep Learning

Literature and information

Wang, N., Siegmann, B., Rascher, U., Clevers, J. G. P. W., Muller, O., Bartholomeus, H., Bendig, J., Masiliūnas, D., Pude, R., & Kooistra, L. (2022). Comparison of a UAV- and an airborne-based system to acquire far-red sun-induced chlorophyll fluorescence measurements over structurally different crops. Agricultural and Forest Meteorology, 323.
Camino, C., González-Dugo, V., Hernández, P., Sillero, J. C. C., & Zarco‐Tejada, P. J. (2018). Improved nitrogen retrievals with airborne-derived fluorescence and plant traits quantified from VNIR-SWIR hyperspectral imagery in the context of precision agriculture. International Journal of Applied Earth Observation and Geoinformation, 70(April), 105–117.
Potgieter, A. B., Camino, C., Poblete, T., Zhi, X., Reynolds-Massey-Reed, S., Zhao, Y., Belwalkar, A., Ruizhu, J., George-Jaeggli, B., Chapman, S., Jordan, D., Wu, A., Hammer, G. L., & Zarco-Tejada, P. J. (2023). Advances in the Study of Biochemical, Morphological and Physiological Traits of Wheat and Sorghum Crops in Australia Using Hyperspectral Data and Machine Learning. International Geoscience and Remote Sensing Symposium (IGARSS), 2023-July, 1952–1955.

Expected reading list before starting the thesis research

Li, J., Ge, Y., Puntel, L. A., Heeren, D. M., Bai, G., Balboa, G. R., Gamon, J. A., Arkebauer, T. J., & Shi, Y. (2024). Integrating UAV hyperspectral data and radiative transfer model simulation to quantitatively estimate maize leaf and canopy nitrogen content. International Journal of Applied Earth Observation and Geoinformation, 129.
Wang, S., Guan, K., Wang, Z., Ainsworth, E. A., Zheng, T., Townsend, P. A., Liu, N., Nafziger, E., Masters, M. D., Li, K., Wu, G., & Jiang, C. (2021). Airborne hyperspectral imaging of nitrogen deficiency on crop traits and yield of maize by machine learning and radiative transfer modeling. International Journal of Applied Earth Observation and Geoinformation, 105.

Theme(s): Sensing & measuring; Modelling & visualisation