Lmetal-resnet: a lightweight convolutional neural network model for soil arsenic concentration estimation

HIGHLIGHTS

• What: In this study, a lightweight CNN model, LMetal-ResNet, was proposed, and the models PLSR, support vector regression (SVR), and GoogleNet7 were also constructed for the prediction of arsenic concentration. The aims of this study are as follows: Soil samples for this study were obtained from February 11 to 15, 2022, and a total of 183 soil samples were obtained by the grid method. The network structure diagrams of the two CNN models used in this study, GoogleNet7 and LMetal-ResNet, are shown in Figs 1 and 2, respectively.
• Who: MYU Tokyo and colleagues . . .
  

   

  

  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.