Skip to main content
ARS Home » Plains Area » Lincoln, Nebraska » Agroecosystem Management Research » Research » Publications at this Location » Publication #214373
Title: Artificial neural network estimation of soil erosion and nutrient concentrations in runoff from land application areas

Author
item Kim, Minyoung
item Gilley, John

Submitted to: Computers and Electronics in Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 10/1/2007
Publication Date: 3/15/2008
Citation: Kim, M., Gilley, J.E. 2008. Artificial neural network estimation of soil erosion and nutrient concentrations in runoff from land application areas. Computers and Electronics in Agriculture. 64(2):268-275.

Interpretive Summary: Manure management programs have been developed to enhance crop production; however reducing sediment or nutrient transport in runoff from land application areas is a challenge. Quantifying sediment and nutrient transport processes is expensive, time-consuming, and labor intensive. Therefore, a simulation tool to predict soil erosion, dissolved phosphorus (DP), and ammonium-nitrogen (NH4-H) concentrations in runoff from land application areas was developed in this study. Previously reported runoff data used in the simulation tool was obtained from sixty plots on which beef cattle manure was applied. Runoff from each plot was collected and soil erosion rates, nutrient concentrations, pH and EC were measured. Contributions of selected hydrologic and water quality factors to soil erosion and nutrient transport were defined from an Artificial Neural Network (ANN). Using ANN calculations, erosion was related to rainfall and runoff characteristics, and concentrations of DP and NH4-N in overland flow were related to measurements of runoff, EC and pH. Analytical procedures identified in this study can be used to determine if established concentration or total maximum daily load requirements are exceeded during a runoff event.

Technical Abstract: The transport of sediment and nutrients from land application areas is an environmental concern. New methods are needed for estimating soil and nutrient concentrations of runoff from cropland areas on which manure is applied. Artificial Neural Networks (ANN) trained with a Backpropagation (BP) algorithm were used to estimate soil erosion, dissolved P (DP) and NH4-N concentrations of runoff from a land application site near Lincoln, Nebraska, USA. Simulation results from ANN derived models showed that the amount of soil eroded is positively correlated with rainfall and runoff. In addition, concentrations of DP and NH4-N in overland flow were related to measurements of runoff, EC and pH. Coefficient of determination values (R2) relating predicted versus measured estimates of soil erosion, DP, and NH4-N were 0.62, 0.72 and 0.92, respectively. The ANN models derived from measurements of runoff, EC and pH provided reliable estimates of DP and NH4-N concentrations in runoff.