MSc thesis topic: Potato Nitrogen Stress Assessment via UAV and Growth Modelling at Sentinel-2 Scale

This thesis leverages multi-year UAV campaigns (2023–2025) to evaluate canopy development in relation to N stress using hyperspectral, multispectral, and thermal imagery. By integrating the Tipstar growth model with PROSAIL radiative transfer and anomaly classification approaches, this research aims to establish robust links between modeled crop performance and sensor-derived indicators. To facilitate broader applicability and satellite-based upscaling, simulation outputs and remote sensing analyses will be exported and assessed at Sentinel-2 spectral resolution, enabling transferability of findings to operational Earth Observation platforms for precision agriculture.

In the 2023–2024 campaigns, field trials were conducted to simulate key stress scenarios—nitrogen deficiency, weed presence, and low emergence—generating rich datasets for hybrid model training. Synthetic NDVI time series were derived from the Tipstar crop growth model coupled with PROSAIL. The upcoming 2025 aerial campaign offers a unique opportunity to validate these models under new nitrogen regimes, incorporating additional SIF measurements. This work builds on efforts to link physiological traits with spectral responses, addressing spatial and temporal variability in potato crop performance. To improve operational relevance, all simulations and remote sensing outputs will be resampled to Sentinel-2 spectral resolution, supporting scaling strategies and the transferability of UAV-based insights to satellite platforms.

Relevance to research/projects at GRS or other groups

This thesis builds on work in the GRS and Agrosystems groups, contributing to digital agriculture, model-data fusion, and crop stress detection. It connects to ongoing ESA and WUR research on integrating hyperspectral UAV sensing and radiative transfer modelling to improve crop monitoring systems.

Objectives and Research questions

This thesis aims to integrate UAV-based hyperspectral and multispectral remote sensing with process-based crop modelling to improve the detection and understanding of nitrogen stress and canopy anomalies in potato crops. By coupling the Tipstar crop growth model with the PROSAIL radiative transfer model, the study will simulate canopy reflectance using multi-year field observations from the 2023–2025 campaigns A comprehensive validation dataset from 2025—featuring a range of nitrogen regimes—will be used to assess retrieval accuracy. The focus will be on analyzing physiological traits such as NDVI, and LAI, and exploring their variability across seasons and stress conditions. To support broader applicability, the study will resample all data and simulations to Sentinel-2 spectral resolution, enabling scalability from UAV to satellite-based monitoring systems.

Research Questions:

• How do different nitrogen influence canopy traits (e.g., NDVI, LAI,) across multi-year UAV datasets?
• Can Tipstar-PROSAIL simulations accurately reproduce temporal patterns of canopy development under varying nitrogen inputs?
• What spectral and spatial patterns are most indicative of nitrogen stress, and how can these be translated to Sentinel-2 resolution for satellite-based monitoring?

Requirements

• Required: GeoScripting, Remote Sensing
• Optional: Crop Growth Modelling, Spatial Statistics

Literature and information

• 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
• Jacquemoud, S., Verhoef, W., Baret, F., Bacour, C., Zarco-Tejada, P.J., Asner, G.P., François, C., Ustin, S.L., 2009. PROSPECT + SAIL models: A review of use for vegetation characterization. Remote Sensing of Environment 113, S56–S66.

Expected reading list before starting the thesis research

• 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.
• P.A.J. van Oort, B. Maestrini, A.A. Pronk, H. Vaessen, F.K. van Evert (2024), A simulation study to quantify the effect of sidedress fertilisation on N leaching and potato yield, Field Crops Research, 314, 109425.

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