Skip to main content
ARS Home » Plains Area » Bushland, Texas » Conservation and Production Research Laboratory » Soil and Water Management Research » Research » Publications at this Location » Publication #416599
Research Project: Dryland and Irrigated Crop Management Under Limited Water Availability and Drought

Location: Soil and Water Management Research

Title: Building databases to calibrate alfalfa crop models: Paving the way for an advanced yield forecasting tool

Author
item KHUSHI, KHUSHI - University Of Nevada
item ANDRADE, MANUEL - University Of Nevada
item CHOLULA, URIEL - University Of Nevada
item SOLOMON, JUAN - University Of Nevada
item NGUYEN, TIN - Auburn University
item Oshaughnessy, Susan
item Evett, Steven
item ZHANG, JIE - Auburn University

Submitted to: ASABE Annual International Meeting
Publication Type: Proceedings
Publication Acceptance Date: 7/28/2024
Publication Date: 7/28/2024
Citation: Khushi, K., Andrade, M.A., Cholula, U., Solomon, J., Nguyen, T., O'Shaughnessy, S.A., Evett, S.R., Zhang, J. 2024. Building databases to calibrate alfalfa crop models: Paving the way for an advanced yield forecasting tool. ASABE Annual International Meeting. Paper nummber: 2401263. https://doi.org/10.13031/aim.202401263.
DOI: https://doi.org/10.13031/aim.202401263

Interpretive Summary: Forage production is necessary to support the dairy industry, which is an important contributor to the economies of the northern Nevada and the Panhandle region of Texas. Among the various forages, alfalfa is widely grown for dairy cattle due to its nutritive value. However, in these semi-arid regions, water for agriculture is limited. USDA-ARS scientists in Bushland, Texas, and from the University of Nevada at Reno are developing a yield forecasting tool to provide farmers with recommendations to optimize economic yield per unit of irrigation water applied. The software tool will be developed from databases comprised of weather, crop and agronomic information collected from different studies over multiple years in these two regions. This paper describes the data sets and how they will be used to in crop growth models and machine learning algorithms.

Technical Abstract: Escalating pressure on water resources in the western U.S. has led alfalfa (Medicago sativa L.) producers in this region to adopt irrigation practices falling below the crop's optimal evapotranspiration levels. This has resulted in deficit irrigation and diminished yields, posing a significant threat to food security. To address this issue, this study is part of a project dedicated to developing an alfalfa hay Yield Forecasting Tool (YFT) that will use weather, soil characteristics, crop agronomics, crop management, and crop development indicators to estimate alfalfa hay yield. The YFT will be used in the future by a Decision Support System that will be developed to recommend irrigation management decisions that minimize yield losses caused by irrigating alfalfa without meeting its full water demands. The goal of this study is to build databases with different levels of data completeness that can be used to train and test alfalfa crop growth models and machine learning algorithms. The databases will be created utilizing 210 crop years of data collected from historical and ongoing field experiments conducted in the Texas High Plains and Northern Nevada. The effective management of extensive information from diverse experimental domains with varying completeness levels necessitates comprehensive databases that can be used to train different crop growth models and machine learning algorithms. This study will describe the generation of such databases.