Predicting European cities' climate mitigation performance using machine learning.
Predicting European cities' climate mitigation performance using machine learning.
复制标题
DOI：
10.1038/s41467-022-35108-5
复制
发表时间：
2022-12-05
影响因子：
16.6
通讯作者：
Goyal, Nihit
中科院分区：
文献类型：
--
作者：
Hsu, Angel;Wang, Xuewei;Tan, Jonas;Toh, Wayne;Goyal, Nihit
尽管城市已成为气候变化的重要参与者，但排放数据的匮乏一直是评估其表现的主要挑战。在这里，我们开发了一种可扩展、可复制的机器学习方法，用于评估2001年至2018年欧洲几乎所有地方行政区域的缓解绩效。通过将可公开获得的空间明确的环境和社会经济数据与欧洲城市自我报告的排放数据相结合，我们预测了年度二氧化碳排放量，以探索城市规模减排绩效的趋势。我们发现，自2001年以来，参与跨国气候倡议的欧洲城市可能已经减少了排放量，其中略多于一半的城市可能实现了2020年的减排目标。报告排放数据的城市比没有报告任何数据的城市更有可能实现更大的减排。尽管存在局限性，但我们的模型为了解城市层面的气候减排绩效提供了一个可复制、可扩展的起点。自2015年《巴黎协定》达成以来，各城市承诺采取的气候行动往往超出了本国政府政策的范围和目标，但这些行动的成果却缺乏证据，主要原因是缺乏报告的排放数据。在这里，作者利用与欧洲城市的城市碳排放和自我报告的排放数据相关的空间明确数据集，并开发了一种机器学习方法来预测和探索城市规模缓解的趋势。
Although cities have risen to prominence as climate actors, emissions’ data scarcity has been the primary challenge to evaluating their performance. Here we develop a scalable, replicable machine learning approach for evaluating the mitigation performance for nearly all local administrative areas in Europe from 2001-2018. By combining publicly available, spatially explicit environmental and socio-economic data with self-reported emissions data from European cities, we predict annual carbon dioxide emissions to explore trends in city-scale mitigation performance. We find that European cities participating in transnational climate initiatives have likely decreased emissions since 2001, with slightly more than half likely to have achieved their 2020 emissions reduction target. Cities who report emissions data are more likely to have achieved greater reductions than those who fail to report any data. Despite its limitations, our model provides a replicable, scalable starting point for understanding city-level climate emissions mitigation performance. Since the Paris Agreement recognized in 2015 cities have pledged climate actions that often exceed the scope and ambition of their national governments’ policies but there is scant evidence of these actions’ outcomes, largely because of the lack of reported emissions data. Here the authors utilize spatially explicit datasets relevant to urban carbon emissions and self-reported emissions data from European cities, and develops a machine-learning approach to predict and explore trends in city-scale mitigation.
登录
查看更多内容
影响因子：
9.8
作者：
Hsu A;Yeo ZY;Rauber R;Sun J;Kim Y;Raghavan S;Chin N;Namdeo V;Weinfurter A
通讯作者：
Weinfurter A
影响因子：
30.7
作者：
Hsu, Angel;Tan, Jonas;Goyal, Nihit
通讯作者：
Goyal, Nihit
影响因子：
4.8
作者：
Hale, Thomas
通讯作者：
Hale, Thomas
影响因子：
4.8
作者：
Hale, Thomas
通讯作者：
Hale, Thomas
影响因子：
7.9
作者：
Hsu, Angel;Rauber, Ross
通讯作者：
Rauber, Ross