According to an article that has just been published in the journal Nature Climate Change , at least 85% of humanity is already suffering the consequences of climate change in some way. The authors used a new research technique that uses machine learning models to synthesize 100,000 empirical studies with models and data on changes in temperature and precipitation. The objective: to provide a more global and complete picture of the impacts of climate change on human activity.
“Our study leaves no doubt that the climate crisis is already being felt almost everywhere in the world. It is also widely scientifically documented,” explains Max Callaghan, postdoctoral researcher at the Mercator Research Institute on Global Commons and Climate Change (MCC) and author. principal of the study.
The ‘attribution gap’
The document also identifies an ‘attribution gap’: the lack of documents and data from low-income countries makes it difficult to understand climate impacts in these areas, despite observed changes in global climate models.
Strong levels of evidence for attributable impacts are twice as prevalent in high-income countries as in low-income countries, and 23% of the population of low-income countries live in areas with low-impact evidence.
“Developing countries are at the forefront of climate impacts, but we can see from our study that there are real blind spots when it comes to climate impact data . Most of the areas where we cannot connect the dots in terms of attribution are found in Africa, “says Shruti Nath, contributing author and researcher for Climate Analytics.” This has real implications for adaptation planning and access to finance in these places. “
Climate Science Reviews in the Age of Great Literature
The climate science literature is growing exponentially. Since the IPCC’s first assessment report in 1990, the number of studies on climate impacts has multiplied by more than one hundred.
The methods used in this study aim to provide a solution to address this massive amount of data. The team used a cutting-edge deep learning approach to identify and classify around 100,000 scientific papers, documenting observed climate impacts ranging from social vulnerabilities to environmental impacts, from freshwater lakes to ecosystems and glaciers.
The algorithm extracts information about the impact, the climate driver and the geolocation of the study area. This information is then combined with spatially explicit assessments of trends in local temperature and precipitation that are attributable to human-induced climate change. The combination of these two sources of big data, a large database of unprecedented literature of documented climate impacts with human-attributable changes in local temperature and precipitation, provides a unique resource for reporting climate action.
Max Callaghan concludes: “Our global map of climate impacts provides guidance for the global fight against global warming, for regional and local risk assessments and also for action on the ground on climate adaptation.”
Referencia: Callaghan, M. et al. 2021. Machine learning-based evidence and attribution mapping of 100,000 climate impact studies, Nature Climate Change https://www.nature.com/articles/s41558-021-01168-6
