High-precision soil ni content prediction model using visible near-infrared spectroscopy coupled with recurrent neural networks

HIGHLIGHTS

• What: The aim of this study is to seek a high-precision soil Ni content prediction model. The authors comprehensively evaluated the performance of a model using the root mean square error (RMSE), the coefficient of determination (R2), the relative analysis error (RPD), and the ratio of performance to the interquartile range (RPIQ).(17) RMSE measures the gap between the predicted and observed values of the model; the smaller the RMSE value, the more accurate the prediction of the model. In this study, 122 soil Vis-NIR spectroscopy data were first processed using Savitzky-Golay smoothing, and . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.