Agriculture plays a crucial role in ensuring global food security, but its intensification has resulted in groundwater depletion, particularly in arid regions like Saudi Arabia. Although the significance of agriculture in Saudi Arabia is well-recognized, there is limited understanding of the agroinformatics aspects required to manage them at a regional or national level. High-resolution satellite data has the potential to provide valuable insights, including the number, location, size, and crop type of agriculture fields, as well as patterns of behavior. Machine learning techniques have emerged as the state-of-the-art methods to extract agricultural informatics from satellite data due to their efficiency and accuracy. However, in regions like Saudi Arabia where even basic agroinformatics data is not routinely available, the lack of ground truth data required to drive machine learning approaches is a critical consideration in model selection. One potential solution is to create a dataset by collecting field data or interpreting satellite imagery using human interpreters, but this can be time-consuming and labor-intensive. Another option is to explore unsupervised techniques that require limited or no ground truth data, but this can result in accuracy sacrifices. Ultimately, we aim to strike a balance between usability, data availability, accuracy, and computational efficiency when developing solutions to address these issues. In this study, a hybrid machine learning framework was developed to accurately delineate agricultural fields in a regional scale of Saudi Arabia, with high accuracy and stable transferability when applied to different temporal and spatial regions across the country. The framework was used to conduct the first retrospective analysis of agriculture activity over three decades on a national scale, including changes in the number, acreage, field size distribution, and the dynamics of expansion and contraction of center-pivot fields. Additionally, a novel unsupervised framework was developed to identify within-field dynamics and map critical crop phenology stages and crop types, providing valuable information for in-field agricultural practices. The agroinformatics retrieved in this study can provide valuable insights for policymakers, farmers, and other stakeholders involved in agriculture and environmental management and exhibited significant implications for the management and sustainability of agricultural systems in Saudi Arabia and other regions facing similar challenges.

The Midwest US has experienced significant changes in agricultural land use and management practices in recent decades. Cropland expansion, crop rotation change, and crop phenology changes could lead to divergent environmental impacts on linked ecosystems. The overall objective is to examine agricultural land use and management changes and their impacts on water quality in the Midwest US, which is addressed in three separate studies. The first study examined spatial and temporal dimensions of agricultural land use dynamics in east-central Iowa, 2001-2012. Results of this study indicated that increases in corn production in response to US biofuel policies had been achieved mainly by altering crop rotation. This study also examined spatial relationships between cultivated fields and crop rotation practices with respect to underlying soils and terrain. The most intensively cultivated land had shallower slopes and fewer pedologic limitations than others, and the corn was planted on the most suitable soils. The second study characterized key crop phenological parameters (SOS and EOS) for corn and soybean and analyzed their spatial patterns to evaluate their change trends in the Midwest US, 2001-2015. Results showed that MODIS-derived SOS and EOS values are sensitive to input time-series data and threshold values chosen for crop phenology detection. The non-winter MODIS NDVI time-series input data, and a lower threshold value (i.e., 40%) both generated better results for SOS and EOS estimates. Spatial analyses of SOS and EOS values displayed clear south-north gradient for corn and trend analyses of SOS revealed only a small percentage of counties showed statistically significant earlier trends within a user-defined temporal window (2001-2012). The third study integrated remote sensing-derived products from the first two studies with the SWAT model to assess impacts of agricultural management changes on sediment and nutrient yields for three selected watersheds in the Midwest US. With satisfied calibration and validation results for stream flows, sediment and nutrient yields, considered under differing management scenarios, were compared at different spatial scales. Results showed that intensive crop rotation, advancing the planting date with the same length of growing season, and longer growing seasons, dramatically increased, maintained, and slightly reduced sediment, total nitrogen, and total phosphorous yields, respectively. Overall, these studies together illuminate relationships between broad-scale agricultural policies, management decisions, and environmental impacts, and the value of multi-temporal, broad-scale, geospatial analysis of agricultural landscapes. / Ph. D.