Deep Learning the Climate Emergency
2022 | GAN-generated moving image with audio, 07:35
![](https://freight.cargo.site/t/original/i/c11428f6751dff25dfb397e78d8f50307d8c2a17a6de67f4937b31945e34927f/Najdowski_Deep-Learning-at-Fed-Square-2.jpg)
Deep Learning the Climate Emergency uses photography and machine learning to (re)generate the aesthetic patterning of ecological collapse. For this work, I was interested to see if familiar images of the climate emergency, ones that have perhaps lost their potency through repetition, could be reconfigured into a new affective experience. The moving image artwork was made with generative adversarial networks (GANs) trained on image-based datasets depicting the effects of a heating planet: wildfire, bleached coral, drought, melting glaciers, and suns through smoke-filled skies. Refracted through the prism of machine learning, the video is a rendering of the shapes and textures of the climate emergency.
![](https://freight.cargo.site/t/original/i/4c6f0f085361c1198c7b9eb0d80a1b5df1653d6e4c03c8ddf4a051f0ea6c666b/Najdowski_Deep-Learning-still-image-2.jpg)
![](https://freight.cargo.site/t/original/i/ad2f60a1a4f48eddcea747456d5c5e88ad74dfd662f4cbbea69cec60b774e37b/Najdowski_Deep-Learning-still-image-6.jpg)
![](https://freight.cargo.site/t/original/i/674e5cb9b09b1708fc70b7a5e7a2464456b8ae8e3bd07afeb166fe990c93b2b7/Najdowski_Deep-Learning-still-image-3.jpg)
Deep Learning the Climate Emergency, video preview