Refine
Year of publication
Document Type
- Article (12)
- Working Paper (4)
- Part of a Book (1)
- Preprint (1)
Is part of the Bibliography
- no (18)
Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by machine learning, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the machine learning community to join the global effort against climate change.
Road freight transportation accounts for around 7% of total world energy-related carbon dioxide emissions. With the appropriate incentives, energy savings and emissions reductions can be achieved by shifting freight to rail or water modes, both of which are far more efficient than road. We briefly introduce five general strategies for decarbonizing freight transportation, and then focus on the literature and data relevant to estimating the global decarbonization potential through modal shift. We compare freight activity (in tonne-km) by mode for every country where data are available. We also describe major intraregional freight corridors, their modal structure, and their infrastructure needs. We find that the current world road and rail modal split is around 60:40. Most countries are experiencing strong growth in road freight and a shift from rail to road. Rail intermodal transportation holds great potential for replacing carbon-intense and fast-growing road freight, but it is essential to have a targeted design of freight systems, particularly in developing countries. Modal shift can be promoted by policies targeting infrastructure investments and internalizing external costs of road freight, but we find that not many countries have such policies in place. We identify research needs for decarbonizing the freight transportation sector both through improvements in the efficiency of individual modes and through new physical and institutional infrastructure that can support modal shift.
A major question confronting sustainability research today is to what extent our planet, with a finite environmental resource base, can accommodate the faster than exponentially growing human population. Although these concerns are generally attributed to Malthus (1766–1834), early attempts to estimate the maximum sustainable population (ergo, the carrying capacity K) were reported by van Leeuwenhoek (1632–1723) to be at 13 billion people (1). Since then, the concept of carrying capacity has evolved to accommodate many resource limitations originating from available water, energy, and other ecosystem goods and services (1, 2). In PNAS, Suweis et al.(3) apply the concept of carrying capacity using fresh water availability on a national scale as the limiting resource to infer the global K. They estimate a decline in global human population by the middle of this century. We ask to what extent models that are …
Hundreds of organizations and analysts use energy projections, such as those contained in the US Energy Information Administration (EIA)’s Annual Energy Outlook (AEO), for investment and policy decisions. Retrospective analyses of past AEO projections have shown that observed values can differ from the projection by several hundred percent, and thus a thorough treatment of uncertainty is essential. We evaluate the out-of-sample forecasting performance of several empirical density forecasting methods, using the continuous ranked probability score (CRPS). The analysis confirms that a Gaussian density, estimated on past forecasting errors, gives comparatively accurate uncertainty estimates over a variety of energy quantities in the AEO, in particular outperforming scenario projections provided in the AEO. We report probabilistic uncertainties for 18 core quantities of the AEO 2016 projections. Our work frames how to produce, evaluate, and rank probabilistic forecasts in this setting. We propose a log transformation of forecast errors for price projections and a modified nonparametric empirical density forecasting method. Our findings give guidance on how to evaluate and communicate uncertainty in future energy outlooks.
The road freight sector is responsible for a large and growing share of greenhouse gas emissions, but reliable data on the amount of freight that is moved on roads in many parts of the world are scarce. Many low-and middle-income countries have limited ground-based traffic monitoring and freight surveying activities. In this proof of concept, we show that we can use an object detection network to count trucks in satellite images and predict average annual daily truck traffic from those counts. We describe a complete model, test the uncertainty of the estimation, and discuss the transfer to developing countries.
Understanding cities as complex systems, sustainable urban planning depends on reliable high-resolution data, for example of the building stock to upscale region-wide retrofit policies. For some cities and regions, these data exist in detailed 3D models based on real-world measurements. However, they are still expensive to build and maintain, a significant challenge, especially for small and medium-sized cities that are home to the majority of the European population. New methods are needed to estimate relevant building stock characteristics reliably and cost-effectively. Here, we present a machine learning based method for predicting building heights, which is based only on open-access geospatial data on urban form, such as building footprints and street networks. The method allows to predict building heights for regions where no dedicated 3D models exist currently. We train our model using building data from four European countries (France, Italy, the Netherlands, and Germany) and find that the morphology of the urban fabric surrounding a given building is highly predictive of the height of the building. A test on the German state of Brandenburg shows that our model predicts building heights with an average error well below the typical floor height (about 2.5 m), without having access to training data from Germany. Furthermore, we show that even a small amount of local height data obtained by citizens substantially improves the prediction accuracy. Our results illustrate the possibility of predicting missing data on urban infrastructure; they also underline the value of open government data and volunteered geographic information for scientific applications, such as contextual but scalable strategies to mitigate climate change.
It is important for policymakers to understand which financial policies are effective in increasing climate risk disclosure in corporate reporting. We use machine learning to automatically identify disclosures of five different types of climate-related risks. For this purpose, we have created a dataset of over 120 manually-annotated annual reports by European firms. Applying our approach to reporting of 337 firms over the last 20 years, we find that risk disclosure is increasing. Disclosure of transition risks grows more dynamically than physical risks, and there are marked differences across industries. Country-specific dynamics indicate that regulatory environments potentially have an important role to play for increasing disclosure.
With the increasing deployment of artificial intelligence (AI) technologies across society, it is important to understand in which ways AI may accelerate or impede climate progress, and how various stakeholders can guide those developments. On the one hand, AI can facilitate climate change mitigation and adaptation strategies within a variety of sectors, such as energy, manufacturing, agriculture, forestry, and disaster management. On the other hand, AI can also contribute to rising greenhouse gas emissions through applications that benefit high-emitting sectors or drive increases in consumer demand, as well as via energy use associated with AI itself. Here, we provide a brief overview of AI’s multi-faceted relationship with climate change, and recommend policy levers to align the use of AI with climate change mitigation and adaptation pathways.
Great claims have been made about the benefits of dematerialization in a digital service economy. However, digitalization has historically increased environmental impacts at local and planetary scales, affecting labor markets, resource use, governance, and power relationships. Here we study the past, present, and future of digitalization through the lens of three interdependent elements of the Anthropocene: (a) planetary boundaries and stability, (b) equity within and between countries, and (c) human agency and governance, mediated via (i) increasing resource efficiency, (ii) accelerating consumption and scale effects, (iii) expanding political and economic control, and (iv) deteriorating social cohesion. While direct environmental impacts matter, the indirect and systemic effects of digitalization are more profoundly reshaping the relationship between humans, technosphere and planet. We develop three scenarios: planetary instability, green but inhumane, and deliberate for the good. We conclude with identifying leverage points that shift human–digital–Earth interactions toward sustainability.
Building stock management is becoming a global societal and political issue, inter alia because of growing sustainability concerns. Comprehensive and openly accessible building stock data can enable impactful research exploring the most effective policy options. In Europe, efforts from citizen and governments generated numerous relevant datasets but these are fragmented and heterogeneous, thus hindering their usability. Here, we present EUBUCCO v0.1, a database of individual building footprints for ~202 million buildings across the 27 European Union countries and Switzerland. Three main attributes – building height, construction year and type – are included for respectively 73%, 24% and 46% of the buildings. We identify, collect and harmonize 50 open government datasets and OpenStreetMap, and perform extensive validation analyses to assess the quality, consistency and completeness of the data in every country. EUBUCCO v0.1 provides the basis for high-resolution urban sustainability studies across scales – continental, comparative or local studies – using a centralized source and is relevant for a variety of use cases, e.g., for energy system analysis or natural hazard risk assessments.
Predicting cycling traffic in cities: Is bikesharing data representative of the cycling volume?
(2023)
A higher share of cycling in cities can lead to a reduction in greenhouse gas emissions, a decrease in noise pollution, and personal health benefits. Data-driven approaches to planning new infrastructure to promote cycling are rare, mainly because data on cycling volume are only available selectively. By leveraging new and more granular data sources, we predict bicycle count measurements in Berlin, using data from free-floating bike-sharing systems in addition to weather, vacation, infrastructure, and socioeconomic indicators. To reach a high prediction accuracy given the diverse data, we make use of machine learning techniques. Our goal is to ultimately predict traffic volume on all streets beyond those with counters and to understand the variance in feature importance across time and space. Results indicate that bike-sharing data are valuable to improve the predictive performance, especially in cases with high outliers, and help generalize the models to new locations.
There is great interest in how the growth of artificial intelligence and machine learning may affect global GHG emissions. However, such emissions impacts remain uncertain, owing in part to the diverse mechanisms through which they occur, posing difficulties for measurement and forecasting. Here we introduce a systematic framework for describing the effects of machine learning (ML) on GHG emissions, encompassing three categories: computing-related impacts, immediate impacts of applying ML and system-level impacts. Using this framework, we identify priorities for impact assessment and scenario analysis, and suggest policy levers for better understanding and shaping the effects of ML on climate change mitigation.
Despite the importance of ambitious policy action for addressing climate change, large and systematic assessments of public policies and their design are lacking as analysing text manually is labour-intensive and costly. POLIANNA is a dataset of policy texts from the European Union (EU) that are annotated based on theoretical concepts of policy design, which can be used to develop supervised machine learning approaches for scaling policy analysis. The dataset consists of 20,577 annotated spans, drawn from 18 EU climate change mitigation and renewable energy policies. We developed a novel coding scheme translating existing taxonomies of policy design elements to a method for annotating text spans that consist of one or several words. Here, we provide the coding scheme, a description of the annotated corpus, and an analysis of inter-annotator agreement, and discuss potential applications. As understanding policy texts is still difficult for current text-processing algorithms, we envision this database to be used for building tools that help with manual coding of policy texts by automatically proposing paragraphs containing relevant information.