Computer-Generated Chess Problem 02745

Here is a 'KQNNP vs krpp' mate in 3 chess puzzle created by the program, Chesthetica, using the Digital Synaptic Neural Substrate (DSNS) computational creativity approach. It doesn't use endgame tablebases, deep learning or any kind of traditional AI. There is no known limit to the quantity or type of compositions that can be generated. The largest endgame tablebase in existence today is for 7 pieces (Lomonosov) which contains over 500 trillion positions, most of which have not and never will be seen by human eyes. This problem with 9 pieces goes even beyond that and was therefore composed without any such help whatsoever.

8/5p2/4N1p1/1r5k/4N2P/8/6Q1/K7 w - - 0 1
White to Play and Mate in 3
Chesthetica v11.32 (Selangor, Malaysia)
Generated on 10 Sep 2019 at 4:59:14 AMSolvability Estimate = Difficult
Chess puzzles are ancient. Some are over a thousand years old but only in the 21st century have computers been able to compose original ones on their own like humans can. Get a glimpse into the 'mind' of a computer composer. Try to solve this as quickly as you can. If you like it, please share with your friends. Some of these problems may be trivial for you, especially if you're a club or master player but bear in mind that chess lovers can be found at all levels of play. So do check out some of the other problems. You can probably find something more to your taste.
Solution
<| Book | DTube | Facebook | Instagram | Twitter | Website |>