diff --git a/GPy/kern/src/sde_stationary.py b/GPy/kern/src/sde_stationary.py
index 3ac5f402..8e7ad6f5 100644
--- a/GPy/kern/src/sde_stationary.py
+++ b/GPy/kern/src/sde_stationary.py
@@ -129,14 +129,14 @@ class sde_Exponential(Exponential):
         """
 
         self.variance.gradient = gradients[0]
-        self.lengthscale.gradient = gradients[1]
+        self.lengthscale.gradient = gradients[1] * 2.0
 
     def sde(self):
         """
         Return the state space representation of the covariance.
         """
         variance = float(self.variance.values)
-        lengthscale = float(self.lengthscale)
+        lengthscale = float(self.lengthscale*2.0)
 
         F  = np.array(((-1.0/lengthscale,),))
         L  = np.array(((1.0,),))
diff --git a/GPy/models/state_space_main.py b/GPy/models/state_space_main.py
index d65364e5..891c0326 100644
--- a/GPy/models/state_space_main.py
+++ b/GPy/models/state_space_main.py
@@ -3237,6 +3237,7 @@ class ContDescrStateSpace(DescreteStateSpace):
             AB = np.dot(AB, np.vstack((np.zeros((n,n)),np.eye(n))))
 
             Q_noise_1 = linalg.solve(AB[n:,:].T,AB[:n,:].T)
+            Q_noise_2  = P_inf - A.dot(P_inf).dot(A.T)
             # The covariance matrix Q by matrix fraction decomposition <-
 
             if compute_derivatives:
@@ -3276,8 +3277,9 @@ class ContDescrStateSpace(DescreteStateSpace):
             else:
               dA = None
               dQ = None
-              Q_noise = Q_noise_1
-
+              Q_noise = Q_noise_2
+	      # Innacuracies have been observed when Q_noise_1 was used.
+	
             #Q_noise = Q_noise_1
 
             # Return
@@ -3484,4 +3486,4 @@ def balance_ss_model(F,L,Qc,H,Pinf,P0,dF=None,dQc=None,dPinf=None,dP0=None):
 
     # (F,L,Qc,H,Pinf,P0,dF,dQc,dPinf,dP0)
 
-    return bF, bL, bQc, bH, bPinf, bP0, bdF, bdQc, bdPinf, bdP0, T
\ No newline at end of file
+    return bF, bL, bQc, bH, bPinf, bP0, bdF, bdQc, bdPinf, bdP0, T