diff --git a/_episodes/02-data.md b/_episodes/02-data.md
index 1de641bde56f2fc2cae4f85647271bf73c5cab11..c81f864dc87a5d01564cd6c95c8573b382d407d9 100644
--- a/_episodes/02-data.md
+++ b/_episodes/02-data.md
@@ -37,6 +37,36 @@ keypoints:
 
 ## Numpy
 
+> ## Working with data types
+>
+> 1. Increase the brightness of the image by 100
+> 2. Why does the result look so bizarre? What is going wrong here?
+> 3. How would you fix this issue?
+>
+> > ## Solution
+> > ~~~
+> > # 1
+> > new_image = raw + 100
+> > plt.imshow(new_image, cmap='gray')
+> > ~~~
+> > {: .language-python }
+> >
+> > ![](/fig/overflow_image.png)
+> > ~~~
+> > # 2
+> > print(raw.dtype)
+> > print(np.max(raw))
+> > # The data type is 'uint8' i.e. unsigned 8 bit integer (max value 255)
+> > # When 100 is added, many values overflow, giving unexpected results
+> >
+> > # 3
+> > new_raw = raw.astype('uint32')
+> > plt.imshow(new_raw + 100, cmap='gray')
+> > ~~~
+> > {: .language-python }
+> {: .solution }
+{: .challenge }
+
 ## Reading data to a numpy array
 
 We'll use the popular image analysis package scikit-image,
diff --git a/fig/overflow_image.png b/fig/overflow_image.png
new file mode 100644
index 0000000000000000000000000000000000000000..15e6948736420fcd2ded3297d9cc243b11e97f7b
Binary files /dev/null and b/fig/overflow_image.png differ