continuous_time_identification (Burgers)

maziarraissi / PINNs

Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations

https://maziarraissi.github.io/PINNs

MIT License

3.73k stars 1.25k forks source link

continuous_time_identification (Burgers) #28

Open omerbme opened 3 years ago

omerbme commented 3 years ago

Why do you use exp for lambda_2 def net_f(self, x, t): lambda_1 = self.lambda_1 lambda_2 = tf.exp(self.lambda_2) u = self.net_u(x,t) u_t = tf.gradients(u, t)[0] u_x = tf.gradients(u, x)[0] u_xx = tf.gradients(u_x, x)[0] f = u_t + lambda_1*u*u_x - lambda_2*u_xx

amiralizadeh1 commented 1 year ago

I have the same question!

nish-ant commented 1 year ago

It's been discussed here: https://github.com/maziarraissi/PINNs/issues/34

Roy-fyq commented 1 month ago

make sure that lambda2 always is positive