Digital Images in Sustainable Agriculture: different spatial and spectral scales for assessing legume crops performance

Legume Crops, such as soybean (Glycine max L. Merr) and chickpea (Cicer arietinum L.), play an important role in Sustainable Agriculture (SA), due to their ability to fix atmospheric nitrogen and their adaptability to different environmental conditions. In the near future it will be necessary to produce more food while remaining sustainable, addressing the challenges of climate change, resource scarcity, and growing global food demand. The use of Precision Agriculture (PA) and the cultivation of crops that are resilient and adaptable to various environmental conditions is therefore essential to achieve these goals. To address these challenges, the application of Digital Soil Mapping (DSM) techniques, particularly with the use of synthetic bare soil images (SYSI) derived from Sentinel-2 satellite imagery, enabled the assessment of soil variability and the identification of homogeneous zones for growing legumes. These homogeneous zones were analyzed with a Linear Mixed Model (LMM), allowing a detailed assessment of their ability to support legume growth. The study revealed that Silty Clay Loam soils are particularly favorable for optimum growth and stability yield of legume crops, due to their balanced texture, which provides an ideal combination of water retention and drainage. Therefore, choosing an appropriate soil texture helps reduce water and nutrient stress, improving plant growth and ultimately leading to optimal crop yields without depleting resources. In addition to soil suitability, it is imperative to focus on the rapid detection of abiotic and biotic stresses in legume crops, which are critical for maintaining crop health and maximizing productivity. Several vegetation indices were used to monitor crop conditions, using satellite, drone and handheld sensors. These indices were integrated into a Synthetic Stress Index (SSI) through Principal Component Analysis (PCA), providing a comprehensive tool for early detection of crop stress. The SSI has proven to be an effective means of identifying stressed plants well before the appearance of visible symptoms, enabling early intervention and improved crop management. Integrating spatial and spectral data at different scales not only improves understanding of legume crops management, but also offers scalable solutions for precision agriculture, contributing to more resilient and sustainable agricultural systems. The methods developed are scalable from field level to regional and potentially national level, offering valuable insights to both farmers and companies operating in the agri-food supply chain.