[laughs]

I mean, I think I kind of learned as I did it.

As I said, like, you know, when I was first sending pitches to some of these titles, like, I dread to think what they were like.

You know, they, there was a reason they weren't getting commissioned I'm sure.

I think the more I did it, and particularly getting feedback, maybe an editor comes back and is asking questions, so it might be like, "Oh, well, you know, you're talking about this amazing animal behavior that's been seen.

Have they got pictures? Have they got video?" Whereas now my first thought is, like, okay, they're gonna ask for pictures.

They're gonna ask for video.

Yeah.

[laughs]

But yeah, the, I had been truly bitten by the bug.

So that kind of planted the seed, I guess.

And then I did a little bit more diving when I was traveling after university.

And then I went to London, got a job in a PR agency, and kind of thought that that was my path.

And I did 10 or so years in London in PR, kind of agency side and in-house, um, for all various different types of clients, from food and drink, and travel, and charity stuff.

Um, and then I went to a small agency where they did quite a lot of charity.

Did it feel that way?

We're talking about people here that often don't have much, and they are trying to feed their children.

Naveen, now seventeen, is well aware of the socioeconomic issues related to poaching.

But given his existing interest in bioacoustics, he decided to look at the issue through this lens.His focus was on how acoustic recordings can help rangers prevent gun-based poaching.

He taught himself a programming language called Python and dove into the scientific literature to learn what had already been tried in the area of gunshot detection.

Existing detectors had some key problems, Naveen says.

But that actually helped it because it made sure it didn't overfit to this data set that I had, and that allowed it to, when it was only trained on a data set from Belize, also detect gunshots from Africa and Vietnam because it wasn't overfitting to this one specific data set.

To make sure the model could pick out gunshots in different habitats, Naveen also overlaid different examples of sounds from various recordings on top of his gunshot spectrograms.

The creation he made with Cornell for the Elephant Listening Project was incredibly accurate.