@ChrisL no worries, thank you for your efforts! Yes, every image has a corresponding solar power production value, with both recorded at 10-minute intervals. The goal is to use the prior 6 images (e.g., from 10:00 to 10:50) to predict the solar power production value 10 minutes into the future (e.g., at 11:00). The first plot highlights this setup.

I've asked this in the Data Science forum as well (no answers yet)

Yeah you're right in this. I should have clarified my question more. As were calculating the mean of the error of our samples, for example, [50, 12, 0] the error of 0 is a very good prediction and counts the same way to our mean as the other two values. Your formula would then, as i was trying to say, result in 0 for a horrendous prediction if y_true=0, which then counts the same towards the other samples. The formula I posted in the orignial question would overcome this through addition.

wouldn't this, for y_true=0, even for horrendous predictions, result in an error of 0 for the sample? The multiplicative part is still strange to me

but wouldn't this, for a big enough y_true, essentially set the error to 0 regardless of (y_true - y_pred)?