Thesis subject

MSc thesis topic: Remote Sensing for Assessing Nitrogen Stress in Potato Crops: Integrating Hyperspectral Imaging, Machine Learning, and Radiative Transfer Modelling

Potato production faces significant challenges under nitrogen (N) stress, impacting yield and sustainability. Understanding crop physiological responses to varying nitrogen levels is critical for optimizing fertilization strategies and improving agricultural sustainability. Hyperspectral remote sensing offers a high-resolution approach to assess key photosynthetic and canopy traits, enabling precise monitoring of nitrogen stress. This study integrates UAV-based hyperspectral imaging, solar-induced fluorescence (SIF), LiDAR, and thermal sensing with machine learning and radiative transfer models to evaluate potato crop performance under different nitrogen regimes.

Nitrogen availability is essential for potato growth, influencing photosynthetic capacity, biomass accumulation, and yield. Traditional methods for assessing nitrogen stress, such as destructive sampling, are labor-intensive and time-consuming. Remote sensing technologies provide non-destructive, scalable solutions for monitoring physiological traits such as chlorophyll content, Vcmax (Rubisco carboxylation rate), LAI (leaf area index), and canopy fluorescence. This research aims to advance nitrogen stress detection in potato crops by integrating hyperspectral and thermal data with modeling approaches to enhance precision agriculture techniques.

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 potato crops using UAV-based hyperspectral and thermal imaging. By integrating radiative transfer models and machine learning, the research will enhance the accuracy of nitrogen stress detection and identify the most effective spectral indices for commercial applications in precision agriculture.

How do different nitrogen treatments influence potato physiological traits, such as chlorophyll content, SIF, and LAI, as measured by remote sensing?
Can machine learning models effectively predict nitrogen stress indicators in potato crops using UAV-based hyperspectral imaging?
What functional plant traits and spectral indices are best suited for assessing nitrogen stress in potatoes using commercially available multispectral sensors?

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.
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.
Clevers, J. G. P. W., & Kooistra, L. (2012). Using hyperspectral remote sensing data for retrieving canopy chlorophyll and nitrogen content. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(2), 574–583

Expected reading list before starting the thesis research

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.
Prikaziuk, E., Ntakos, G., ten Den, T., Reidsma, P., van der Wal, T., & van der Tol, C. (2022). Using the SCOPE model for potato growth, productivity and yield monitoring under different levels of nitrogen fertilization. International Journal of Applied Earth Observation and Geoinformation, 114.

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