Remote sensing represents a useful tool for agriculture thus enabling to intervene in a timely and prudent manner, meeting economic, social and environmental sustainability needs.Wheat and cotton are two of the most important crops in the Australian context. Infact wheat is the main winter dry land crop and cotton the main summer irrigated crop. Although some dry land cropping does occur in some years. Nitrogen is a key nutrient for these infact it is essential for photosynthesis and therefore an insufficient supply will affect both development and production in terms of quality and quantity but sometimes an excessive supply can make plants more susceptible to stress, negatively affect yield and damage local ecosystems. It is important to monitor vegetation nitrogen nutrition via chlorophyll as a proxy for leaf nitrogen content and nitrogen use efficiency and how these may vary according to different application modes (split or singleapplications). Therefore, it is clear the importance of identifying which may be not only the best application strategies for the crops being studied but also the effect that these may have on development, also paying attention to any stress, in particular water stress , which may have influenced the response of the vegetation.The main characteristics that can accompany the study for the evaluation of nitrogen and water nutrition of crops are the height of the crop, the degree of soil coverage, flowering and final yield, availability at sowing and during crop growt period. My proposed thesis aims to investigate the development and yield of wheat and cotton in response to different application strategies of nitrogen and water stress by utilising multispectral and hyperspectral remote sensing and the derivation of data from maps with specific indexes, machine learning and deep learning algorithms and, to increase the level of precision, RTM and SIF (solar-induced chlorophyll fluorescence: an optical signal emitted in the spectral range 650–850 nm from chlorophyll a molecules in vegetation). SIF may be assessed remotely using high-resolution spectral sensors. Recent studies have demonstrated that solar-induced chlorophyll fluorescence (SIF) quantified from hyperspectral imagery is a reliable indicator of photosynthetic activity in the context of precision agriculture and for early stress detection purposes. For these reasons, spectral indicators related to the leaf functioning, as chlorophyll fluorescence, is a potentially important candidate for improving the quantification of N concentration.