I don't think you can do it in a single statement but its easy to do in 2. The first creates a mask of pixels greater than 0.2179 and less than 0.8449. Pixels with values that meet this threshold are assigned a 1 in the mask and all others are set to 0. Then multiply by the original data: (b1 gt 0.2179 and b1 lt 0.8449) * (b1 * 1.515 - 0.33) This one finds the pixels greater than 0.8449 in the original image and multiplies them by 0.95 (all other pixels are 0 in the mask) and then add it to the result from above: ((b1 gt 0.8449)*0.95) + b2 There are probably other ways to do this but you get the idea of how you can apply a conditional statement.