Crop stress detection is a well-explored domain within agricultural research. However, understanding the underlying causes of stress in crops is pivotal for effective farm management. This insight empowers farmers to implement timely interventions, ensuring optimal crop yield while minimizing the yield gap. This chapter delves into the utilization of results from pre-developed models to generate temporal maps that depict areas of crop stress in a maize crop using remote sensing data. The stress areas are subsequently categorised to distinguish between water and/or nitrogen stress. These maps are derived from drone-based top-of-canopy RGB and hyperspectral images. The model was developed using synthetic data generated through the assimilation of spectroradiometer data and corresponding ground-truth information related to leaf water and nitrogen content. The pre-developed models for water and nitrogen stress identification have used narrowband indices that exhibit heightened sensitivity to crop nitrogen levels compared to crop water content. These narrowband indices contribute to the refinement of models and enhance their ability to discern variations in nitrogen stress across different farm irrigation scenarios. In this chapter, the water and nitrogen maps obtained from pre-developed models have been integrated to generate crop water and/or nitrogen stress maps, enabling a comprehensive analysis that sheds light on the intricate relationship between these two essential factors. One notable finding highlighted in this research is the facilitated identification of nitrogen stress in areas concurrently experiencing water stress. However, the model encounters challenges in distinguishing nitrogen stress in farm areas that receive adequate irrigation but are subjected to limited nitrogen fertiliser application.