Search

It is central for climate policy to understand, monitor and forecast greenhouse gas (GHG) emissions, generating insights on the key factors and actions with a greater impact to mitigate and adapt to global warming. Focusing on the leading role of cities, it is relevant to build robust and reliable GHG emissions prospects for every city committing to mitigate and adapt to climate change. In this paper, a novel methodology is proposed to build those prospects, presenting a case study with 6231 EU-27 cities and local municipalities taken from the Global Covenant of Mayors (GCoM). Key GHG emissions predictors for the target years of 2020 and 2030 refer to the baseline energy consumption and associated GHG emissions, as well as the population and the national emissions per capita trend. Additionally, other informative predictors are the baseline inventory year, the reduction target, the disaggregated baseline emissions by type of fuel (fossils or renewables), the heating and cooling degree days and the NUTS urban/rural categorization. The proposed methodology allows assessing the cities' achievements based on their expected performance, and it could be further implemented to support new cities willing to commit to a significant reduction of their GHG emissions. • A robust methodology is proposed to predict GHG emissions for cities committing to climate change mitigation and adaptation. • Key predictors refer to local, regional and national sources of information. • A case study is performed with 6231 European cities: 2030 commitments are expected to achieve a 40 % GHG emissions reduction. • The models described in this paper provide useful information to urban policy makers in the climate action planning process. • The results are replicable in the context of transnational initiatives involving cities in the fight against climate change. [ABSTRACT FROM AUTHOR]

Under the Global Covenant of Mayors (GCoM) initiative, cities present their action plans committing to mitigate greenhouse gas (GHG) emissions and/or adapt to climate change. One concrete objective consists in setting a reduction target, by which cities commit to reduce their baseline GHG emissions for a chosen target year. In monitoring their emissions, cities report inventories for any arbitrary year(s), making available only discrete readings in what can be considered a very sparse yearly time series. Examining the performance of the cities for the target years of 2020 and 2030, the actual measurements are usually not available. Therefore, a machine learning methodology is proposed to predict the GHG emissions inventories for each city on their target year, enabling the assessment of the cities' performance inside a common reporting framework. Using the reported inventories, the methodology identifies a model for each city, minimizing the error for the last known reported value. As a result, the proposed method allows predicting GHG emissions for cities from their yearly inventories, controlling the uncertainty associated to the estimations and extracting reliable information that can be updated as soon as new emissions inventories become available. • A methodology is proposed to forecast the GHG emissions of cities monitoring their actions on climate change. • Forecasting models are validated by the novel Leave Last Known Value Out technique. • The proposed method predicts GHG emissions for cities from their yearly inventories. • The methodology is illustrated for a group of 1950 cities and local administrative units in the EU-27. [ABSTRACT FROM AUTHOR]