Skip to main content
ARS Home » Research » Publications at this Location » Publication #386533

Research Project: Towards Resilient Agricultural Systems to Enhance Water Availability, Quality, and Other Ecosystem Services under Changing Climate and Land Use

Location: Location not imported yet.

Title: Short-range winter wheat yield prediction in Oklahoma using artificial neural network

item YILDIRIM, TUGBA - Oklahoma State University
item Moriasi, Daniel
item MIRCHI, ALI - Oklahoma State University
item Starks, Patrick

Submitted to: ASA-CSSA-SSSA Annual Meeting Abstracts
Publication Type: Abstract Only
Publication Acceptance Date: 8/31/2021
Publication Date: 11/17/2021
Citation: Yildirim, T., Moriasi, D.N., Mirchi, A., Starks, P.J. 2021. Short-range winter wheat yield prediction in Oklahoma using artificial neural network [abstract]. ASA-CSSA-SSSA International Annual Meeting, November 7-10, 2021, Salt Lake City, Utah. Poster No. 1113. Available:

Interpretive Summary: Abstract only.

Technical Abstract: Winter wheat is a dual-purpose crop and contributes greatly to Oklahoma’s economy, whether through grain yield (grain only), serving as a forage for livestock (graze out), or used for both in a given year (graze-grain). Climate factors (principally precipitation and temperature) affect the both grain and biomass production and thereby affect a farmer’s choices as to how to manage (grain, graze out, graze-grain) wheat resources, which ultimately impacts farm income. We investigate the use of readily available vegetation and drought indexes antecedent to planting and during early growth as a tool to predict wheat yield. Early prediction of winter wheat yield may provide farmers a tool for livestock and/or crop management decision-making. Artificial neural network (ANN) models have been used to provide reasonably accurate crop yield predictions using readily available climate, drought indices, and remotely sensed vegetation indices. However, the use of ANNs to predict crop yield has not been done in Oklahoma. This study will use winter wheat yield data reported by the NASS, a combination of two meteorologically-based drought indices (Standardized Precipitation Index (SPI) and the Standardized Precipitation Evapotranspiration Index (SPEI)) and three remotely-sensed vegetation indices (Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Land Surface Water Index (LSWI)) as well as cumulative precipitation and heat units to predict winter wheat yield using ANN.