Browsing by Author "Ghajar, Shayan"

Now showing 1 - 5 of 5
  • Thumbnail Image
    DeepPaSTL: Spatio-Temporal Deep Learning Methods for Predicting Long-Term Pasture Terrains Using Synthetic Datasets
    Rangwala, Murtaza; Liu, Jun; Ahluwalia, Kulbir Singh; Ghajar, Shayan; Dhami, Harnaik Singh; Tracy, Benjamin F.; Tokekar, Pratap; Williams, Ryan K. (MDPI, 2021-11-05)
    Effective management of dairy farms requires an accurate prediction of pasture biomass. Generally, estimation of pasture biomass requires site-specific data, or often perfect world assumptions to model prediction systems when field measurements or other sensory inputs are unavailable. However, for small enterprises, regular measurements of site-specific data are often inconceivable. In this study, we approach the estimation of pasture biomass by predicting sward heights across the field. A convolution based sequential architecture is proposed for pasture height predictions using deep learning. We develop a process to create synthetic datasets that simulate the evolution of pasture growth over a period of 30 years. The deep learning based pasture prediction model (DeepPaSTL) is trained on this dataset while learning the spatiotemporal characteristics of pasture growth. The architecture purely learns from the trends in pasture growth through available spatial measurements and is agnostic to any site-specific data, or climatic conditions, such as temperature, precipitation, or soil condition. Our model performs within a 12% error margin even during the periods with the largest pasture growth dynamics. The study demonstrates the potential scalability of the architecture to predict any pasture size through a quantization approach during prediction. Results suggest that the DeepPaSTL model represents a useful tool for predicting pasture growth both for short and long horizon predictions, even with missing or irregular historical measurements.
  • Thumbnail Image
    Evaluating digestibility and toxicity of native warm-season grasses for equines
    Ghajar, Shayan; McKenzie, H. C.; Fike, John H.; McIntosh, B.; Tracy, B. F. (2021-01)
    Introduced cool-season grasses are dominant in Virginia's grasslands, but their high digestible energy and nonstructural carbohydrate (NSC) levels pose a risk for horses prone to obesity and laminitis. Native warm-season grasses (NWSGs) have lower digestible energy and NSC levels that may be more suitable for horses susceptible to laminitis. Although NWSGs have desirable characteristics, they are novel forages for horses. Little is known about NWSG intake or potential toxicity to horses or how grazing by horses may affect NWSG swards. The overall objectives of this research were to 1) assess voluntary intake, toxicological response, and apparent digestibility of NWSG hays fed to horses; and 2) evaluate the characteristics of three NWSG species under equine grazing. For the first objective, a hay feeding trial using indiangrass (IG) (Sorghastrum nutans) and big bluestem (BB) (Andropogon gerardii) was conducted with nine Thoroughbred geldings in a replicated 3 x 3 Latin square design. Voluntary dry matter intake of IG and BB hays by horses were 1.3% and 1.1% of BW/d, lower than orchardgrass (Dactylis glomerata), an introduced cool-season grass, at 1.7% of BW/d (P = 0.0020). Biomarkers for hepatotoxicity remained within acceptable ranges for all treatments. Apparent dry matter digestibility (DMD) did not differ among hays, ranging from 39% to 43%. NSC levels ranged from 4.4% to 5.4%, below maximum recommended concentrations for horses susceptible to laminitis. For the second objective, a grazing trial was conducted comparing IG, BB, and eastern gamagrass (EG) (Tripsacum dactyloides) yields, forage losses, changes in vegetative composition, and effects on equine bodyweight. Nine, 0.1-ha plots were seeded with one of the three native grass treatments, and each plot was grazed by one Thoroughbred gelding in two grazing bouts, one in July and another in September 2019. IG had the greatest available forage, at 4,340 kg/ha, compared with 3,590 kg/ha from BB (P < 0.0001). EG plots established poorly, and had only 650 kg/ha available forage during the experiment. Grazing reduced standing cover of native grasses in IG and BB treatments by about 30%. Horses lost 0.5-1.5 kg BW/d on all treatments. Findings suggest IG and BB merit further consideration as forages for horses susceptible to obesity and pasture-associated laminitis.
  • Thumbnail Image
    Home on the Digital Range: Ranchers' Web Access and Use
    Ghajar, Shayan; Fernández‑Giménez, María E.; Wilmer, Hailey (2019-06)
    Access to the Internet continues to grow in rural areas, ensuring ranchers will have increasing opportunities to use the Web to find information about management practices that may provide them ecological and financial benefits. Although past studies have examined the role of the Internet in informing daily decision making by agricultural producers, no studies have focused specifically on the use of the Internet by ranchers in the western United States. This study uses a mixed-methods approach (a survey and semistructured interviews) to assess the extent and patterns of ranchers' Internet use in Colorado and Wyoming, identify barriers to greater use, and establish a typology of Web use behavior by ranchers. Our findings indicate that Internet use is widespread and that age, education, and risk tolerance predict the extent to which a rancher will rely on the Internet for dayto-day ranch management. A duster analysis delineated four distinct types of Web usage among ranchers: unin-fluenced, focused on sales and herd management, moderately influenced, and an Internet-reliant type. Outreach personnel can use this classification to determine the potential utility of digital outreach tools for their programming on the basis of their target audience and outreach topics.
  • Thumbnail Image
    Managing for the middle: rancher care ethics under uncertainty on Western Great Plains rangelands
    Wilmer, Hailey; Fernández‑Giménez, María E.; Ghajar, Shayan; Taylor, Peter Leigh; Souza, Caridad; Derner, Justin D. (2019-12)
    Ranchers and pastoralists worldwide manage and depend upon resources from rangelands (which support indigenous vegetation with the potential for grazing) across Earth's terrestrial surface. In the Great Plains of North America rangeland ecology has increasingly recognized the importance of managing rangeland vegetation heterogeneity to address conservation and production goals. This paradigm, however, has limited application for ranchers as they manage extensive beef production operations under high levels of social-ecological complexity and uncertainty. We draw on the ethics of care theoretical framework to explore how ranchers choose management actions. We used modified grounded theory analysis of repeated interviews with ranchers to (1) compare rancher decision-making under relatively certain and uncertain conditions and (2) describe a typology of practices used to prioritize and choose management actions that maintain effective stewardship of these often multi-generational ranches. We contrast traditional decision-making frameworks with those described by interviewees when high levels of environmental and market uncertainty or ecological complexity led ranchers toward use of care-based, flexible and relational frameworks for decision-making. Ranchers facing complexity and uncertainty often sought "middle-ground" strategies to balance multiple, conflicting responsibilities in rangeland social-ecological systems. For example, ranchers' care-based decision-making leads to conservative stocking approaches to "manage for the middle," e.g. to limit risk under uncertain weather and forage availability conditions. Efforts to promote heterogeneity-based rangeland management for biodiversity conservation through the restoration of patch burn grazing and prairie dog conservation will require increased valuation of ranchers' care work.
  • Thumbnail Image
    Proximal Sensing in Grasslands and Pastures
    Ghajar, Shayan; Tracy, Benjamin F. (MDPI, 2021-08-04)
    Reliable measures of biomass, species composition, nitrogen status, and nutritive value provide important indicators of the status of pastures and rangelands, allowing managers to make informed decisions. Traditional methods of sample collection necessitate significant investments in time and labor. Proximal sensing technologies have the potential to collect more data with a smaller investment in time and labor. However, methods and protocols for conducting pasture assessments with proximal sensors are still in development, equipment and software vary considerably, and the accuracy and utility of these assessments differ between methods and sites. This review summarizes the methods currently being developed to assess pastures and rangelands worldwide and discusses these emerging technologies in the context of diffusion of innovation theory.