Publications
6 results found
Liu Z, Peach R, Laumann F, et al., 2023, Kernel-based joint independence tests for multivariate stationary and non-stationary time series, Royal Society Open Science, Vol: 10, ISSN: 2054-5703
Multivariate time-series data that capture the temporal evolution of interconnected systems are ubiquitous in diverse areas. Understanding the complex relationships and potential dependencies among co-observed variables is crucial for the accurate statistical modelling and analysis of such systems. Here, we introduce kernel-based statistical tests of joint independence in multivariate time series by extending the d-variable Hilbert–Schmidt independence criterion to encompass both stationary and non-stationary processes, thus allowing broader real-world applications. By leveraging resampling techniques tailored for both single- and multiple-realization time series, we show how the method robustly uncovers significant higher-order dependencies in synthetic examples, including frequency mixing data and logic gates, as well as real-world climate, neuroscience and socio-economic data. Our method adds to the mathematical toolbox for the analysis of multivariate time series and can aid in uncovering high-order interactions in data.
Laumann F, von Kuegelgen J, Kanashiro Uehara TH, et al., 2022, Quantitative assessment of complex interlinkages, key objectives and nexuses amongst the Sustainable Development Goals and climate change, The Lancet Planetary Health, Vol: 6, ISSN: 2542-5196
Background. Global sustainability is an enmeshed system of complex socio-economic, climato-logical and ecological interactions. The numerous objectives of the United Nations’ Sustainable Development Goals (SDGs) and the Paris Agreement have various levels of interdependence, making it difficult to ascertain the influence of changes in particular indicators across the whole system.Methods. We present a method to find interlinkages amongst the 17 SDGs and climate change, including non-linear and non-monotonic dependences, by using 400 indicators that track their temporal changes. The method detects statistically significant dependencies amongst the time evolution of the objectives by using partial distance correlations, a non-linear measure of conditional dependence that also discounts spurious correlations originating from lurking variables. We then employ a network representation to identify the most important objectives (using network centrality) and to obtain nexuses of objectives (defined as highly interconnected clusters in the network).Findings. Using temporal data from 181 countries spanning 20 years, we analyse dependencies amongst SDGs and climate for 35 country groupings based on region, development and income 2 level. Our results show that the significant interlinkages, central objectives, and nexuses identified vary greatly across country groupings, yet partnerships for the goals (SDG 17) and climate change rank as highly important across many country groupings.Temperature rise is strongly linked to urbanisation, air pollution, and slum expansion (SDG 11), especially in country groupings likely to be worst affectedby climate breakdown such as Africa. In several groupings encompassing the developing countries, a consistent nexus of strongly interconnected objectives is formed by poverty reduction (SDG 1), education (SDG 4), and economic growth (SDG 8), sometimes incorporating gender equality (SDG 5), and peace and justice (SDG 16).Interpretation. The
Stevenson S, Collins A, Jennings N, et al., 2021, A hybrid approach to identifying and assessing interactions between climate action (SDG13) policies and a range of SDGs in a UK context (vol 2, 43, 2021), DISCOVER SUSTAINABILITY, Vol: 2
Stevenson S, Collins A, Jennings N, et al., 2021, A hybrid approach to identifying and assessing interactions between climate action (SDG13) policies and a range of SDGs in a UK context, Discover Sustainability, Vol: 2, ISSN: 2662-9984
In 2015 the United Nations drafted the Paris Agreement and established the Sustainable Development Goals (SDGs) for all nations. A question of increasing relevance is the extent to which the pursuit of climate action (SDG 13) interacts both positively and negatively with other SDGs. We tackle this question through a two-pronged approach: a novel, automated keyword search to identify linkages between SDGs and UK climate-relevant policies; and a detailed expert survey to evaluate these linkages through specific examples. We consider a particular subset of SDGs relating to health, economic growth, affordable and clean energy and sustainable cities and communities. Overall, we find that of the 89 UK climate-relevant policies assessed, most are particularly interlinked with the delivery of SDG 7 (Affordable and Clean Energy) and SDG 11 (Sustainable Cities and Communities) and that certain UK policies, like the Industrial Strategy and 25-Year Environment Plan, interlink with a wide range of SDGs. Focusing on these climate-relevant policies is therefore likely to deliver a wide range of synergies across SDGs 3 (Good Health and Well-being), 7, 8 (Decent Work and Economic Growth), 9 (Industry, Innovation and Infrastructure), 11, 14 (Life Below Water) and 15 (Life on Land). The expert survey demonstrates that in addition to the range of mostly synergistic interlinkages identified in the keyword search, there are also important potential trade-offs to consider. Our analysis provides an important new toolkit for the research and policy communities to consider interactions between SDGs, which can be employed across a range of national and international contexts.
Laumann F, von Kuegelgen J, Barahona M, 2021, Kernel two-sample and independence tests for non-stationary random processes, ITISE 2021 (7th International conference on Time Series and Forecasting), Publisher: https://www.mdpi.com/2673-4591/5/1/31, Pages: 1-13
Two-sample and independence tests with the kernel-based MMD and HSIC haveshown remarkable results on i.i.d. data and stationary random processes.However, these statistics are not directly applicable to non-stationary randomprocesses, a prevalent form of data in many scientific disciplines. In thiswork, we extend the application of MMD and HSIC to non-stationary settings byassuming access to independent realisations of the underlying random process.These realisations - in the form of non-stationary time-series measured on thesame temporal grid - can then be viewed as i.i.d. samples from a multivariateprobability distribution, to which MMD and HSIC can be applied. We further showhow to choose suitable kernels over these high-dimensional spaces by maximisingthe estimated test power with respect to the kernel hyper-parameters. Inexperiments on synthetic data, we demonstrate superior performance of ourproposed approaches in terms of test power when compared to currentstate-of-the-art functional or multivariate two-sample and independence tests.Finally, we employ our methods on a real socio-economic dataset as an exampleapplication.
Laumann F, von Kuegelgen J, Barahona M, 2020, Non-linear interlinkages and key objectives amongst the Paris Agreement and the Sustainable Development Goals, ICLR 2020 - Workshop on Tackling Climate Change with Machine Learning
The United Nations' ambitions to combat climate change and prosper humandevelopment are manifested in the Paris Agreement and the SustainableDevelopment Goals (SDGs), respectively. These are inherently inter-linked asprogress towards some of these objectives may accelerate or hinder progresstowards others. We investigate how these two agendas influence each other bydefining networks of 18 nodes, consisting of the 17 SDGs and climate change,for various groupings of countries. We compute a non-linear measure ofconditional dependence, the partial distance correlation, given any subset ofthe remaining 16 variables. These correlations are treated as weights on edges,and weighted eigenvector centralities are calculated to determine the mostimportant nodes. We find that SDG 6, clean water and sanitation, and SDG 4,quality education, are most central across nearly all groupings of countries.In developing regions, SDG 17, partnerships for the goals, is stronglyconnected to the progress of other objectives in the two agendas whilst,somewhat surprisingly, SDG 8, decent work and economic growth, is not asimportant in terms of eigenvector centrality.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.