Artificial intelligence analyzed 1,500 guidelines for reducing emissions. These were successful.

researchers used machine learning to analyze around 1,500 climate policy and identify those who have dramatically reduced carbon dioxide emissions. Her study, which was published in science today, showed that policies that combine several instruments are more effective to reduce emissions as independent measures 1 .

The analysis identified 63 interventions in 35 countries that led to significant emission reductions and lowered it by 19 %on average. Most of the reductions were associated with two or more policies. Together, the 63 policies lowered emissions by 0.6 to 1.8 gigatons (GT) carbon dioxide equivalent.

The right mix of policies is more important than using many different policies, says Annika Stechemesser, co-author and researcher at the Potsdam Institute for Climate Impact Research in Germany. For example, the expiry of coal -fired power plants worked in Great Britain because it was used in combination with price mechanisms such as a minimum price for carbon, while in Norway the ban on combustion engines was most effective when it was combined with a price incentive that made electric cars cheaper.

"In my opinion, it is a unique study that provides such a global assessment," says Jan Minx, an environmental economist at the Mercator Research Institute for Global Community Goods and Climate Change in Berlin.

Way to the emission cuts

A database used as part of the analysis and its colleagues with 1,500 climate policy, which were implemented in 41 countries between 1998 and 2022, including the three largest greenhouse gas emitters worldwide: china, The United States and India . The policies fell in 48 categories, from emission trade systems to the reform of subsidies for fossil fuels.

"Previous reviews typically focused on a limited number of prominent politics in selected countries and overlooked the hundreds of other measures," says Stechemesser.

The authors combined machine learning with a statistical analytical approach to identify large emission reductions in four highly emitting sectors - buildings, electricity, industry and transport. They compared the results with the policies in the database to evaluate which political and combinations of politics led to the greatest emission declines.

"This is a pretty clever method," says Zheng Saina, who analyzed global climate policy at the University of Southeast in Nanjing, China. The conventional way would have been to check the many politics and select the important ones, but this approach is subjective and tedious, adds. "Instead, the authors used machine learning to recognize major changes in emissions. This is more objective."

real mix

The results showed that certain political combinations worked better in certain sectors and economies. With regard to reducing emissions in connection with electricity generation, price measures such as energy taxes in highly developed countries were particularly effective, but less in countries with low and medium income.

In the construction industry, political blends doubled, which gradually emission emission -generating activities, and prohibit the reductions in comparison to the implementation of these politics individually.

Taxation was the only policy that achieved almost equally large or larger emission reductions in all four sectors as independent politics, in contrast to a blend of politics.

MINX says that the study-based approach of the study enabled researchers for the first time to evaluate the effectiveness of a large number of climate policy from a global inventory of emissions that cover different countries and sectors.

The paper is alarming for other researchers. "This study warns the countries worldwide that their climate policy has so far only had very limited effects," says Xu Chi, an ecologist at the University of Nanjing. "Existing policies have to be checked and changes have to be made," adds XU.

The Annual emissions of the world , according to the United Nations by 2030, will probably be 15 GT carbon dioxide equivalents than would be necessary to keep global warming at less than 2 ° C above the pre-industrial level.