Understanding the best way to allocate limited resources is a constant challenge for water quality improvement efforts. The synoptic approach is a tool for geographic prioritization of these efforts. It uses a benefit-cost framework to calculate indices for functional criteria in subunits (watersheds, counties) of a region and then rank the subunits. The synoptic approach was specifically designed to incorporate best professional judgment in cases where information and resources are limited. To date, the synoptic approach has been applied primarily to local or regional wetland restoration prioritization projects. The goal of this work was to develop a synoptic model for prioritizing watersheds within which suites of agricultural best management practices (BMPs) can be implemented to reduce sediment load at the watershed outlets. The model ranks candidate watersheds within an ecoregion or river basin so that BMP implementation within the highest ranked watersheds will result in the most sediment load reduction per conservation dollar invested. The model can be applied anywhere and at many scales provided that the selected suite of BMPs is appropriate for the evaluation area’s biophysical and climatic conditions. The model was specifically developed as a tool for prioritizing BMP implementation efforts in ecoregions containing watersheds associated with the USDA-NRCS conservation effects assessment project (CEAP). This paper presents the testing of the model in the little river experimental watershed (LREW) which is located near Tifton, Georgia, USA and is the CEAP watershed representing the southeastern coastal plain. The application of the model to the LREW demonstrated that the model represents the physical drivers of erosion and sediment loading well. The application also showed that the model is quite responsive to social and economic drivers and is, therefore, best applied at a scale large enough to ensure differences in social and economic drivers across the candidate watersheds. The prioritization model will be used for planning purposes. Its results are visualized as maps which enable resource managers to identify watersheds within which BMP implementation would result in the most water quality improvement per conservation dollar invested.

To assess the potential of precision irrigation, a research and demonstration project whose goal is to develop a soil moisture sensor-based variable rate irrigation (VRI) control system was begun. The control system consists of a wireless soil moisture sensing array with a high density of sensor nodes, a VRI enabled center pivot irrigation system, and a web-based user interface with an integrated irrigation scheduling decision support system. This paper describes the system in detail providing some results from the components which have been completed and are operational and a detailed description of the components under development.

Using UAV and multispectral images has contributed to identifying field variability and improving crop management through different data modeling methods. However, knowledge on application of these tools to manage peanut maturity variability is still lacking. Therefore, the objective of this study was to compare and validate linear and multiple linear regression with models using artificial neural networks (ANN) for estimating peanut maturity under irrigated and rainfed conditions. The models were trained (80% dataset) and tested (20% dataset) using results from the 2018 and 2019 growing seasons from irrigated and rainfed fields. In each field, plant reflectance was collected weekly from 90 days after planting using a UAV-mounted multispectral camera. Images were used to develop vegetation indices (VIs). Peanut pods were collected on the same dates as the UAV flights for maturity assessment using the peanut maturity index (PMI). The precision and accuracy of the linear models to estimate PMI using VIs were, in general, greater in irrigated fields with R² > 0.40 than in rainfed areas, which had a maximum R² value of 0.21. Multiple linear regressions combining adjusted growing degree days (aGDD) and VIs resulted in decreased RMSE for both irrigated and rainfed conditions and increased R² in irrigated areas. However, these models did not perform successfully in the test process. On the other hand, ANN models that included VIs and aGDD showed accuracy of R² = 0.91 in irrigated areas, regardless of using Multilayer Perceptron (MLP; RMSE = 0.062) or Radial Basis Function (RBF; RMSE = 0.065), as well as low tendency (1:1 line). These results indicated that, regardless of the ANN architecture used to predict complex and non-linear variables, peanut maturity can be estimated accurately through models with multiple inputs using VIs and aGDD. Although the accuracy of the MLP or RBF models for irrigated and rainfed areas separately was high, the overall ANN models using both irrigated and rainfed areas can be used to predict peanut maturity with the same precision.