TRTim Repke

Tim Repke

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Tim Repke has a total of 81 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • An ecosystem of carbon dioxide removal reviews to inform research, policy and practice

    by Claire Fyson, Christiane Hamann, Leon Stephan, Tim Repke, Finn Müller-Hansen, Ingrid Schulte, Malgorzata Borchers, Wolfram Buss, Annette Cowie, Christiana Dietzen, et al.

    Claire Fyson et al. introduce the Energy and Environmental Science themed reviews issue on CO 2 reduction.

  • Open Access

    Climate–Health Risks Outpace Research Attention in Chinese Cities

    by Yuze Sun, Shihui Zhang, Wenjia Cai, Xiaomeng Huang, Tim Repke, Jing Su, Jing Zhang, Weiyi Liao, Cunrui Huang, Zehua Liu

    Background: Climate-related health risks are rising rapidly in cities, yet it remains unclear whether scientific research reflects the geography and mechanisms of these emerging risks. Methods: We systematically map city-level climate–health research in China using a large language model–based multi-agent framework, analyzing 2,902 Chinese- and English-language publications from 1993 to 2023. The AI agent system performed document appraisal, information extraction, and structured evidence synthesis. Findings: We identify 2,902 studies, including 1,151 city-level analyses covering 2,012 mentions of 408 unique cities in the articles. Research attention is highly concentrated in a small number of metropolitan areas, with strong geographic inequality in research exposure. Across 408 cities, the growth of climate-related health risks is negatively correlated with research attention (r = −0・329), indicating a mismatch between emerging risks and the distribution of scientific evidence. The literature also focuses predominantly on exposure–disease relationships, while vulnerability, socioeconomic determinants, and system-level responses remain underexplored. Interpretation: Structural gaps exist in the climate–health evidence base. Geographically balanced and mechanism-focused research is urgently needed to support urban climate adaptation and public health action. 

  • Open Access

    Don't Stop Me Now, `Cause I'm Having a Good Time Screening: Evaluation of Stopping Methods for Safe Use of Priority Screening in Systematic Reviews

    by Tim Repke, Francesca Tinsdeall, Diana Danilenko, Sergio Graziosi, Finn Müller‐Hansen, Lena Schmidt, James Thomas, Gert van Valkenhoef

    Introduction: Priority screening has the potential to reduce the number of records that need to be annotated in systematic literature reviews. So‐called technology‐assisted reviews (TAR) use machine‐learning with prior include/exclude annotations to continuously rank unseen records by their predicted relevance to find relevant records earlier. In this article, we present a systematic evaluation of methods to determine when it is safe to stop screening when using prioritization. Methods: We implement an open‐source evaluation framework that features a novel method to generate rankings and simulate priority screening processes for 81 real‐world data sets. We use these simulations to evaluate 15 statistical or rule‐based (heuristic) stopping methods, testing a range of hyperparameters for each. Results: The work‐saving potential and performance of stopping criteria heavily rely on “good” rankings, which are typically not achieved by a single ranking algorithm across the entire screening process. Our evaluation shows that almost all existing stopping methods either fail to reliably stop without missing relevant records or fail to utilize the full potential work‐savings. Only one method reliably meets the set recall target, but stops conservatively. Conclusions: Many digital evidence synthesis tools provide priority screening features that are already used in many research projects. However, the theoretical work‐savings demonstrated in retrospective simulations of prioritization can only be unlocked with safe and reproducible stopping criteria. Our results highlight the need for improved stopping methods and guidelines on how to responsibly use priority screening. We also urge screening platforms to provide indicators and authors to transparently report metrics when automating (parts of) their synthesis.


  • A systematic map of machine learning for urban climate change mitigation

    by Marie Josefine Hintz, Nikola Milojevic-Dupont, Felix Creutzig, Tim Repke, Lynn H. Kaack


  • Open Access

    Don’t stop me now, ’cause I’m having a good me screening: Evaluation of stopping methods for safe use of priority screening in systemaic maps and reviews

    by Tim Repke, Francesca Tinsdeall, Lena Schmidt, Diana Danilenko, James Thomas, Sergio Graziosi, Gert van Valkenhoef, Finn Müller-Hansen

    Introduction Priority screening has the potential to reduce the number of records that need to be annotated in systematic literature reviews. So‐called technology‐assisted reviews (TAR) use machine‐learning with prior include/exclude annotations to continuously rank unseen records by their predicted rele‐ vance to find relevant records earlier. In this article, we present a systematic evaluation of methods to determine when it is safe to stop screening when using prioritisation. Methods We implement an open‐source evaluation framework that features a novel method to generate rankings and simulate priority screening processes for 86 real‐world datasets. We use these sim‐ ulations to evaluate 12 statistical or rule‐based (heuristic) stopping methods, testing a range of hyper‐parameters for each. Results The work‐saving potential and performance of stopping criteria heavily rely on ‘good’ rankings, which is typically not achieved by a single ranking algorithm across the entire screening process. Our evaluation shows that the existing stopping methods either fail to reliably stop without missing relevant records or fail to utilise the full potential work‐savings. Only one method reliably met the set recall target but stops conservatively. Conclusions Many digital evidence synthesis tools provide priority screening features that are already used in many research projects. However, the theoretical work‐savings demonstrated in retrospective sim‐ ulations of prioritisation can only be unlocked with safe and reproducible stopping criteria. Our results highlight the need for improved stopping methods and guidelines on how to responsibly use priority screening. We also urge screening platforms to provide indicators and authors to transpar‐ently report metrics when automating (parts of) their synthesis.

  • Open Access

    Systematic global stocktake of over 50,000 urban climate change studies

    by Simon Montfort, Max Callaghan, Felix Creutzig, William F. Lamb, Chenxi Lu, Tim Repke, Ke Ge, Jan Minx

    Taking stock of climate change evidence is essential to helping cities address climate change. However, such efforts face challenges in appraising the growing scholarship in this fast-moving area. Here we use supervised and unsupervised machine learning to identify and classify over 53,000 urban climate studies, creating a dynamic, interactive and searchable evidence database for researchers and policymakers. Nearly 20,000 are city-specific case studies, revealing a rapidly growing yet unevenly distributed knowledge base. Notably, small and fast-growing cities, particularly in Africa and Asia, remain substantially underrepresented, contributing to topical, geographic and disciplinary biases in previous Intergovernmental Panel on Climate Change (IPCC) assessments. We propose three strategies to address this: (1) synthesizing case studies to support IPCC uptake, (2) identifying cross-city learning opportunities and (3) closing evidence gaps in the Global South. Thereby, our systematic stocktake helps inform adaptation and mitigation efforts in cities, guides future research and strengthens the IPCC’s ability to deliver robust, policy-relevant evidence.


  • Open Access

    How global crises compete for our attention: Insights from 13.5 million tweets on climate change during COVID-19

    by Tim Repke, Max Callaghan, William F. Lamb, Sarah Lück, Finn Müller-Hansen, Jan C. Minx


  • Open Access

    NACSOS-nexus: NLP Assisted Classification, Synthesis and Online Screening with New and EXtended Usage Scenarios

    by Tim Repke, Max Callaghan

    NACSOS is a web-based platform for curating data used in systematic maps. It contains several (experimental) features that aid the evidence synthesis process from finding and ingesting primary data (mainly scientific publications), basic search and exploration thereof, but mainly the handling of managing the manual and automated annotations. The platform supports prioritised screening algorithms and is the first to fully implement statistical stopping criteria. Annotations by multiple coders can be resolved and customisable quality metrics are computed on-the-fly. In its current state, the annotations are performed on document level. The ecosystem around NACSOS offers packages for accessing the underlying database and practical utility functions that have proven useful in a multitude of projects. Further, it provides the backbone of living maps, review ecosystems, and our public literature hub for sharing high-quality curated corpora.


  • Open Access

    Growing online attention and positive sentiments towards carbon dioxide removal

    by Tim Repke, Finn Muller-Hansen, Emilx Cox, Jan Minx

    Scaling up CO2 removal is crucial to achieve net-zero targets and limit global warming. Understanding public perception of large-scale carbon dioxide removal (CDR) is vital to avoid opposition that could slow down development, investments, and deployment. Using Twitter data from 2010 to 2022, we analysed attention and sentiments towards ten CDR methods. Our study provides up-to-date time series evidence complementing survey studies, capturing the opinions of users with knowledge or awareness of emerging CDR methods. Attention towards CDR has grown exponentially, particularly in recent years. Overall, the discourse on CDR has become more positive, except for BECCS. Conventional CDR methods are the most discussed and receive more positive sentiments. We examined three user types, each with varying levels of involvement in the discourse. Infrequent users (assumed less familiar) pay more attention to methods with biological sinks, while frequent users (assumed more familiar) focus more on novel CDR methods.