Publications on the impact of climate change have grown in number so huge, so fast that it is impossible to for humans to wrap their heads around the whole expanse of literature on the subject.

Researchers at the Mercator Research Institute on Global Commons and Climate Change (MCC) in Germany observe in a new paper that it is now humanly impossible to keep up with the massive growth in the scientific literature on climate change and its impact.

Climate change is a huge subject and understandably there is a wealth of related research, studies and scientific papers. The problem is how to capture, study, and draw coherent and meaningful insights from this trove of data? (Science Alert)

AI can be trained to address the problem

“Since the first assessment report (AR) of the Intergovernmental Panel on Climate Change (IPCC) in 1990, we estimate that the number of studies relevant to observed climate impacts published per year has increased by more than two orders of magnitude,” says the paper by first author and quantitative data researcher Max Callaghan.

“This exponential growth in peer-reviewed scientific publications on climate change is already pushing manual expert assessments to their limits.”

The alternative? Harnessing the power of AI to go through it all to analyze and report.

The researchers deployed a deep-learning language analysis AI tool called BERT to identify and classify over 100,000 scientific studies on the subject of the impact of climate change.

BERT crunched through the data and made coherent sense of it by classifying into the different kinds of impacts, showing their continental spread, and their correlation with historical temperature and precipitation trends.

Troubling results

The preliminary results from the exercise revealed that 80 percent of global land area (excluding Antarctica), already shows trends in temperature and/or precipitation that can be attributed at least in part to the activities of human beings.

More significantly, about 48% of the world’s land, where 74% of the global population lived, showed that temperature or precipitation trends had a correlation with the impact of climate change on human and natural systems.

“Ultimately, we hope that our global, living, automated and multi-scale database will help to jump start a host of reviews of climate impacts on particular topics or particular geographic regions,” the researchers said.

Related Story: AI Helps Researchers Understand Extreme Weather In The Midwest