You are on page 1of 3

News Story Discussion

The accurate modelling of extreme weather events is at the forefront of climate change research.

This is because modelling extreme weather events to predict how the earth’s climate may change

over decades is important in understanding how to resolve climate-related issues. One major

development in this area of research is the use of artificial intelligence (AI) and machine learning

methods that are otherwise applied to generate images and other forms of content. Scientists

from the Earth System Modelling at the Technical University of Munich and at the Potsdam

Institute for Climate Impact Research are applying machine learning algorithms within climate

research.

The researchers started using Generative Adversarial Networks (GANs) which consists of two

neutral networks; one of which tries to create an example from previously defined products while

the other attempts to differentiate the generated sample from real examples (Boulaguiem et al.,

2022). GANs have been practically applied in translating paintings into photorealistic images.

Using this model, climate simulations can be enhanced by artificial intelligence to create

depictions of significant weather and climatic events such as heat waves.

This development has enhanced my appreciation of technology in the world of climate change.

Such a realization is impactful considering that technology has been viewed negatively in

climate change conversations. E-waste and other forms of environmental pollution resulting from

the use of electronics have severely affected climate change, and caused many technological

firms to embrace green products, practices and sustainable value chains. Activities like Bitcoin

mining consumes a lot of energy and results in depleted electronics that are not always well

recycled, thus contributing to the climate change crisis by harming the environment when
improperly disposed. This new development means that more computing resources can be used

to predict and solve climate change issues rather than contribute negatively to it.
References

Boulaguiem, Y., Zscheischler, J., Vignotto, E., van der Wiel, K., & Engelke, S. (2022).

Modeling and simulating spatial extremes by combining extreme value theory with

generative adversarial networks. Environmental Data Science, 1, e5.

You might also like