diff --git a/pes_to_spec/__init__.py b/pes_to_spec/__init__.py
index cc1b4a38efdd3d7366c91f28c4aa276bd6a5fb6b..1f747822ee6f034d8a4187097c908045560ba40b 100644
--- a/pes_to_spec/__init__.py
+++ b/pes_to_spec/__init__.py
@@ -2,4 +2,4 @@
 Estimate high-resolution photon spectrometer data from low-resolution non-invasive measurements.
 """
 
-VERSION = "0.1.6"
+VERSION = "0.1.7"
diff --git a/pes_to_spec/model.py b/pes_to_spec/model.py
index f17347aa4bfdf30d74ebf450b29c95c74057c451..0dcb032fe304e2b4fcfb59646bd2bae32300422d 100644
--- a/pes_to_spec/model.py
+++ b/pes_to_spec/model.py
@@ -3,7 +3,7 @@ from __future__ import annotations
 import joblib
 
 import numpy as np
-from scipy.signal import convolve
+from scipy.signal import fftconvolve
 #from scipy.signal import find_peaks_cwt
 from scipy.optimize import fmin_l_bfgs_b
 from sklearn.decomposition import PCA
@@ -331,7 +331,7 @@ class HighResolutionSmoother(TransformerMixin, BaseEstimator):
         gaussian = np.exp(-0.5*(energy - mu)**2/self.high_res_sigma**2)
         gaussian /= np.sum(gaussian, axis=1, keepdims=True)
         # apply it to the data
-        high_res_gc = convolve(X, gaussian, mode="same", axes=1)
+        high_res_gc = fftconvolve(X, gaussian, mode="same", axes=1)
         return high_res_gc
 
     def inverse_transform(self, Xt: np.ndarray) -> np.ndarray:
@@ -519,7 +519,7 @@ class SelectRelevantLowResolution(TransformerMixin, BaseEstimator):
         gaussian = np.exp(-0.5*(axis - sum_low_res.shape[0]//2)**2/20**2)
         gaussian /= np.sum(gaussian, axis=0, keepdims=True)
         # apply it to the data
-        smoothened = convolve(sum_low_res, gaussian, mode="same", axes=0)
+        smoothened = fftconvolve(sum_low_res, gaussian, mode="same", axes=0)
         peak_idx = [np.argmax(smoothened)]
         if len(peak_idx) < 1:
             raise PromptNotFoundError()
@@ -1011,7 +1011,7 @@ class Model(TransformerMixin, BaseEstimator):
         M = self.wiener_filter.shape[0]
         B = expected.shape[0]
         assert expected.shape[1] == M
-        deconvolved = convolve(expected,
+        deconvolved = fftconvolve(expected,
                                   np.broadcast_to(self.wiener_filter.reshape(1, -1), (B, M)),
                                   mode="same",
                                   axes=1)