CSBE-SCGAB

Comparison of Root Zone Water Quality Model (RZWQM) and Artificial Neural Network (ANN) for simulating the impacts of winter rye cover crop on Nitrate-Nitrogen (NO3-N) loss for a corn-soybean crop system.

Description: Subsurface drainage is the main source of NO3-N loss from agricultural fields. Growing winter cover crop is one of the strategies that may reduce NO3-N losses in tile-drained lands. The present study was conducted on corn-soybean crop system to evaluate the effectiveness of this method on water quality. Experimental data collected from Iowa over a 4-year period were used to compare the monthly NO3-N loss simulations results from Root Zone Water Quality Model (RZWQM) and Artificial Neural Network Model (ANN) during calibration and validation periods. In this field experiment, there were 4 different treatments labeled as treatment1, treatment2, control1, and control2. In treatment1 and 2, winter rye was added to corn-soybean rotation as a winter cover while in control 1 and 2 no winter cover was introduced to the rotation system. Treatment 1 and control 1 were used as calibration and treatment 2 and control 2 were used as validation sets. Both models generally provided good correlation and model efficiency for simulating NO3-N loss during calibration and validation according to correlation coefficient (R ), Root Mean Square Error (RMSE), ratio of RMSE to standard deviation (RSR), and Nash-Sutcliffe Efficiency (NS). For treatments with winter cover crop RSR for RZWQM and ANN were 0.5899 and 0.1636 for calibration and 0.668258 and 0.3451 for validation, respectively. While for treatments without winter cover crop RSR for RZWQM and ANN were 0.618589 and 0.3268 for calibration and 0.722217 and 0.5176 for validation, respectively.
Keywords: winter cover crop; nitrate-nitrogen loss; artificial neural network; Root Zone Water Quality Model
Conference name: CSBE/SCGAB 2016 Annual Conference, Halifax, 3-6 July 2016.
Session name: Poster Session (Best Student Poster Award)
Citation: . 2016. Comparison of Root Zone Water Quality Model (RZWQM) and Artificial Neural Network (ANN) for simulating the impacts of winter rye cover crop on Nitrate-Nitrogen (NO3-N) loss for a corn-soybean crop system.. CSBE/SCGAB 2016 Annual Conference, Halifax, 3-6 July 2016.
Publisher: Canadian Society for Bioengineering
Date: 2016-07
Publication type:
  • Conference Proceeding
Type: Text.Article
Format: PDF
Identifier: CSBE16046
Coverage: Canada
Language 1: en
Rights: Canadian Society for Bioengineering
Located in: AGM Halifax (2016)

Search a publication

Search for:
Find entries that have:
Date:
From:
To:
Publication type: