Knowledge of crop abiotic and biotic stress is important for optimal irrigation management. While spectral reflectance and infrared thermometry provide a means to quantify crop stress remotely, these measurements can be cumbersome. Computer vision offers an inexpensive way to remotely detect crop stress independent of vegetation cover. This paper presents a technique using computer vision to detect disease stress in wheat. Digital images of differentially stressed wheat were segmented into soil and vegetation pixels using expectation maximization (EM). In the first season, the algorithm to segment vegetation from soil and distinguish between healthy and stressed wheat was developed and tested using digital images taken in the field and later processed on a desktop computer. In the second season, a wireless camera with near real-time computer vision capabilities was tested in conjunction with the conventional camera and desktop computer. For wheat irrigated at different levels and inoculated with wheat streak mosaic virus (WSMV), vegetation hue determined by the EM algorithm showed significant effects from irrigation level and infection. Unstressed wheat had a higher hue (118.32) than stressed wheat (111.34). In the second season, the hue and cover measured by the wireless computer vision sensor showed significant effects from infection (p = 0.0014), as did the conventional camera (p < 0.0001). Vegetation hue obtained through a wireless computer vision system in this study is a viable option for determining biotic crop stress in irrigation scheduling. Such a low-cost system could be suitable for use in the field in automated irrigation scheduling applications.

Highlights The ARSPivot software seamlessly integrates site-specific irrigation scheduling methods with weather, plant, and soil water sensing systems in the operation of variable-rate irrigation (VRI) center pivot systems. ARSPivot embodies an Irrigation Scheduling Supervisory Control and Data Acquisition (ISSCADA) system that incorporates site-specific irrigation scheduling methods and automates the collection and processing of data obtained from sensing systems supporting them. ARSPivot incorporates a friendly graphical user interface (GUI) that assists in the process of setting up a computerized representation of a coupled ISSCADA VRI center pivot system and simplifies the review of irrigation prescriptions automatically generated based on sensor feedback. ARSPivot’s GUI includes a geographic information system (GIS) that relates sensed data and imported GIS data to specific field control zones. Abstract. The commercial availability of variable-rate irrigation (VRI) systems gives farmers access to unprecedented control of the irrigation water applied to their fields. To take full advantage of these systems, their operations must integrate site-specific irrigation scheduling methods that in turn should be supported by a network of sensing systems. An Irrigation Scheduling Supervisory Control and Data Acquisition (ISSCADA) system patented by scientists with the USDA-Agricultural Research Service (ARS) at Bushland, Texas, incorporates site-specific irrigation scheduling methods informed by weather, plant, and soil water sensing systems. This article introduces a software package, ARSPivot, developed to integrate the ISSCADA system into the operation of VRI center pivot systems. ARSPivot assists the operation and integration of a complex network of sensing systems, irrigation scheduling methods, and irrigation machinery to achieve this end. ARSPivot consists of two independent programs interacting through a client-server architecture. The client program is focused on automatically collecting and processing georeferenced data from sensing systems and communicating with a center pivot control panel, while the server program is focused on communicating with users through a friendly graphical user interface (GUI) involving a geographic information system (GIS). The GUI allows users to visualize and modify site-specific prescription maps automatically generated based on sensor-based irrigation scheduling methods, and to control and monitor the application of irrigation amounts specified in these recommended prescription maps using center pivots equipped for VRI zone control or VRI speed control. This article discusses the principles and design considerations followed in the development of ARSPivot and presents tools implemented in the software for the virtual design and physical operation of a coupled ISSCADA VRI center pivot system. This article also illustrates how the ISSCADA system and ARSPivot constitute a comprehensive sensor-based decision support system (DSS) for VRI management that is accessible to users without in-depth knowledge of sensing systems or irrigation scheduling methods. Keywords: Center pivot irrigation, Decision support system, Precision agriculture, Sensors, Site-specific irrigation scheduling, Software, Variable rate irrigation.n

Highlights Corn response to irrigation was influenced by the precipitation distribution in 2018 and 2019, and that impacted the response of CWSI as an irrigation scheduling signaling method. CWSI was sensitive to changes in soil water storage, increasing due to crop evapotranspiration and decreasing after a precipitation or irrigation event. In 2018, both seasonal CWSI and yield were not different among the irrigation treatments, while in 2019, seasonal CWSI and yield were all statistically different among the treatments evaluated. Post analysis of canopy and air temperature indicated that the temperature-time threshold (TTT) method might not appropriately signal crop water stress in a humid environment. Abstract. Irrigation scheduling based on the crop water stress index (CWSI) and temperature-time threshold (TTT) methods is promising for semi-arid and arid climates. The objective of this study was to investigate if CWSI and TTT methods could be used as irrigation signaling tools for a humid environment in the southeastern U.S. Corn canopy temperature data were collected in Alabama in 2018 and 2019 using infrared leaf temperature sensors on a fully irrigated treatment and on two limited irrigation treatments. A set of three soil water sensors installed at 0.15, 0.3, and 0.6 m soil depth were used to prescribe irrigation time and amount. CWSI was sensitive to precipitation, irrigation, and plant water uptake. No statistical differences in CWSI or yield among the three irrigation levels were found in 2018 when precipitation was well distributed during the season. In contrast, during 2019 both CWSI and yield differed significantly among the three irrigation treatments. Precipitation events in 2019 were sparse compared to 2018; therefore, irrigation promoted greater differences in water availability between treatments. Inconsistencies observed in potential irrigation signaling using the TTT method with or without the inclusion of a limiting relative humidity algorithm indicate that the TTT method may not be a reliable irrigation signaling tool for humid environments. Keywords: Corn yield, Crop water stress index, Irrigation scheduling, Limiting relative humidity, Soil water depletion, Temperature-time threshold.