Remote Sensing & Agro-informatics Lab

Agricultural productivity is subject to various stressors, including abiotic and biotic threats, many of which climate change exacerbates. Identification of key yield determinants will, therefore, provide the ability to predict yield and enhance the ability to manage within-field variability. Furthermore, relationships between resource inputs and yield must be determined to implement zonal management strategies effectively. Accurate and timely yield prediction is critical for growers to manage their farm resources correctly to optimize water, nutrients, and other resources. Yet, yield predictions of tree crops such as almond orchards are incredibly complex. Hence, collecting and integrating multi-layer heterogeneous large datasets and advanced analytics are needed to generate insights about the key constraints to yield potential at the tree-scale. Agricultural inputs (e.g., water and nutrients) can then be optimized at the field level or in each management zones (MZ) to maximize yield and profit margins. Thus, we propose to investigate the environmental, biological, and management factors that determine tree-level yield variability of almond orchards. We aim to achieve this by integrating
multiple factors that are known to affect yield, including manageable primary resources (i.e., irrigation and fertilizer application), using machine learning algorithms and spatial statistics. These will assist in developing a spatial decision support system (SDSS) for irrigation and fertilization based on site-specific management. This research will utilize intensive sensing data with machine learning algorithms to enhance precision by implementing a data-driven, yet easy to use, MZs. These by considering dynamic in-season MZs based on detecting abiotic and biotic stress-causing factors (i.e., water status, N-pool, N-use-efficacy, light interception, and vegetative growth), management of sensors\sampling, and minimizing the use of costly UAVs by fusing with recently accessible satellite data. The deliverables from this proposal will be a decision-making tool for precision fertilization and irrigation to minimize the yield gap at the tree level, which will be developed using data from two almond orchards in Israel and the USA. We will spatially evaluate the effects of abiotic and biotic stress-causing factors on the yield gap, and monitor the crops using standard sampling (i.e., soil and leaves), UAVs (i.e., thermal, LiDAR, multispectral), and satellite with high spatial resolution and high revisit time. These will be transformed into tree-based data-driven SDSSs, including processes of determining management zones and building prescription irrigation and fertilization maps to optimize differentiated yield. Once completed, our research should bridge the gap between fundamental science and farming applications by supporting decisions for optimizing almond yield.