A peer-reviewed article published Monday in the Proceedings of the National Academy of Sciences journal suggests a significant risk of crossing critical global warming thresholds earlier than indicated in previous assessments.
Achieving the United Nations Paris Agreement goals of holding global warming to below 2 degrees Celsius above preindustrial levels -- and ideally below 1.5 degrees Celsius -- requires an understanding of when greenhouse gas emissions and global temperatures cross thresholds beyond which the goals are no longer achievable.
Noah Diffenbaugh from Stanford University and Elizabeth Barnes from Colorado State University used artificial neural networks trained on climate models to simulate global warming scenarios as part of their latest research. Let’s break down what they found.
What are neural networks?
First, let’s talk about neural networks. IBM explains it best:
“Neural networks, also known as artificial neural networks (ANNs) or simulated neural networks (SNNs), are a subset of machine learning and are at the heart of deep learning algorithms. Their name and structure are inspired by the human brain, mimicking the way that biological neurons signal to one another.
“... Neural networks rely on training data to learn and improve their accuracy over time. However, once these learning algorithms are fine-tuned for accuracy, they are powerful tools in computer science and artificial intelligence, allowing us to classify and cluster data at a high velocity.”
What the researchers found
Using maps of observed historical annual temperatures, the researchers’ artificial neural networks accurately predicted historical global warming, and estimated that the planet will reach the 1.5 degrees Celsius threshold between 2033 and 2035. The neural networks suggested a substantial probability of crossing the 2 degrees Celsius threshold, even in a low-emissions scenario, which is a higher probability than found by previous assessments.
Analysis of the neural network outputs suggested that its predictions focus on warming in specific regions, including the Indian Ocean, Tibetan Plateau and western North America. According to the authors, the results suggest that the current global warming trajectory is close to crossing the 1.5 degrees Celsius threshold, and suggest a possibility of exceeding the 2 degrees Celsius threshold even with substantial greenhouse gas mitigation.
The authors further say that their “framework provides a unique, data-driven approach for quantifying the signal of climate change in historical observations and for constraining the uncertainty in climate model projections. Given the substantial existing evidence of accelerating risks to natural and human systems at 1.5 °C and 2 °C, our results provide further evidence for high-impact climate change over the next three decades.”
The bottom line here: According to this research, we are heading toward a near future of significant additional ramifications from the unnatural rate of warming our planet is experiencing.
I have said for many years now in my climate change lectures that we are nearing the point of not being able to stop the warming, but that we still have the ability to slow it down. This is a very important point, as slowing the global temperature rise will buy time for some species to adapt or migrate, and, in the case of humans, to mitigate.
The new research released Monday, Jan. 30, highlights that the headlights coming at us are closer than originally thought.