If we’re going to stand a chance of countering the effects of our climate emergency, we need a global network of weather sensors now
Monitoring the climate emergency requires increasingly more sophisticated and powerful tools. Recent global weather patterns show that the first victim of the climate emergency is our ability to predict what the weather will do. The human species has artificial adaptation mechanisms that other animal species don’t possess, and whose extinction is therefore a dire omen of what awaits us. The disappearance of biodiversity is an even more alarming crisis than the climate emergency itself.
We are on the verge of catastrophe. The data is there, it’s not speculation, it brooks no discussion, doubts, or outdated skepticism. How much higher is the temperature where you live now compared to when you were born? How high will that temperature be in 2050? It can now be seen: there are maps and models predicting it. We are now heading toward a fearful destiny: an uninhabitable planet, too hot to house human life.
How is it possible that the species able to reach the moon half a century ago is unable to solve the climate emergency? There’s no easy answer, but part of it is having prolonged an out-of-date and unsustainable economic model based on unlimited growth.
Looking ahead, growing unpredictability will make it very hard to take decisions. The models we know reflect increasing instability and will require increasingly powerful analytical models and tools. In the near future, machine learning could play an important role in enabling the development of better models with greater capacity for analysis and that could help with making those difficult decisions. One of the people I respect most in this area, Tom Dietterich, has been working on the subject for some time:
“I realized I wanted to have an impact on something that really mattered — and certainly the whole Earth’s ecosystem, of which we are a part, is under threat in so many ways. And so if there’s some way that I can use my technical skills to improve both the science base and the tools needed for policy and management decisions, then I would like to do that. I am passionate about that.”
To create viable models, something fundamental is necessary: data. We need to fill the planet with sensors to capture climate parameters and transmit them in real time to feed predictive models. The cost of sensors has fallen, is a reasonably standardized network of them located in infrastructure of all kinds. 5G, which requires a high density of base stations, provides an opportunity to do this, but there may be other possibilities; we just need to use our imagination. Garnering data for better models could be essential for predicting environmental catastrophes, which are now increasingly frequent in our unstable environment, as well as to better understand how to implement measures to help the planet, such as recovering forests in specific places.
One way to overcome our natural stupidity could be the use of artificial intelligence. Only by understanding how this increasingly out-of-control planet works can we hope to manage the very difficult future looming on the horizon. Data and machine learning could be a key to this.