Table of Contents
A. Objectives of the study
The fast growth of digital textual information in the last two decades represents a largely untapped potential for methodological advances in the analysis and forecasting of climate change risks based on text mining and machine learning approaches already applied in other areas of computational social sciences. In the research proposed here, we aim to combine text mining and fuzzy cognitive maps (FCM). More specifically, we intend to use the potential of topic modeling (TpM) to leverage the obtained data for climate change risks analysis and forecasting and to develop risk scenarios using FCM.
B. Methodical approach and planned procedure
We intend to analyse unstructured text-based data sources of potential interest related to climate change risks (policy papers, research articles, study reports, news coverage, etc.) as a knowledge source for fuzzy cognitive maps (FCM)- based scenario development. With risk assessments now widely being adopted into climate change policy agendas, there has been a rapid growth in text available through online archives that may be appropriate for text mining . A variety of tools, such as application programming interfaces (APIs), i.e. the Web of Science API, Scopus API, or the World Bank Climate Data API, or pre-existing climate change risks databases, can support in identifying and downloading large volumes of data. Web-scraping tools can also be implemented to construct unique databases of texts.
Topic Modeling (TpM), which raises attention in the field of text mining, enables the discovery of hidden topics within multiple documents and conducts effective predictive analysis by suggesting the proportions of hidden topics throughout the document set . TpM generates a probabilistic model that essentially assumes that a given corpus contains an existing set of topics and that each document within the corpus contains a mixture of these topics. Each topic has a word catalog that is most closely associated with that topic which can be identified based on the probability of words occurring simultaneously .
Fuzzy cognitive maps (FCMs) are one of the representative techniques in developing scenarios that include risk analysis and forecasting, as well as causal relationships between risk factors and risks . Even though such scenarios cannot predict the future, it does enable the investigation of a variety of plausible future situations with the goal of expanding the thinking sphere of the participants in the scenario development process. FCMs are based on causal cognitive mapping, which provides an efficient way to elicit, capture and communicate causal knowledge and make them useful for risk analysis. The method allows inputs from large, diverse, and even dissipated groups and can therefore be easily integrated to overcome the limitations of expert opinions and groupthink. Recently, FCM has been used successfully in scenario analysis because it can improve the ability to respond to uncertainty and can enhance the usefulness of overall decision making through scenarios. The following is a typical process for developing scenarios based on Fuzzy Cognitive Maps by integrating scenario planning and FCM modeling processes :
1. Scenario preparation: Clarification of the objective, time frame and boundaries of the scenario project.
2. Knowledge capture: Identify relevant concepts/potential scenario drivers through experts and literature review, merge mental models of various experts and subsequently translate these into conceptual FCM scenario model.
3. Scenario modeling: Streamline the causal links and assign weights and signs to all links, choose threshold functions for all concepts.
4. Scenario development: Calculate the FCM model for different input vectors that represent plausible combinations of concept states.
5. Scenario selection and refinement: These raw scenarios developed after step 4 are further assessed and refined by scenario simulation.
6. Strategic decisions: The developed scenarios are used for making strategic decisions.
C. Thematic note: Forecasting Climate Change Risks
Climate change is a major challenge for society, particularly in terms of its capacity to take individual and collective decisions that will enable appropriate responses to address it . In many respects, it differs from other environmental problems facing modern civilization in its time scale and in its complex relationship between human activities, the embedded societal structures and interactions that are emerging between different environmental systems . Climate change is leading to cascade-like risks in technical installations, ecological systems, the economy and society, all of which are often interlinked and create the conditions for irreversible and unwanted exceeding of threshold values at various levels . Forecasting climate risks across sectors and in a way that is meaningful to decision-makers thus represents a major scientific challenge. Big data analytics is seen as very promising in terms of predicting risks associated with climate change. [8-10].
The Intergovernmental Panel on Climate Change (IPCC) has described the benefits of a risk-based approach to better understand both the dynamic interactions of spatial and temporal determinants leading to specific impacts of climate change and the role of adaptation initiatives in managing corresponding risks . The most fundamental component for the analysis and prediction of climate risks is verifiable, up-to-date and comparable data and relevant modelling. Conventional approaches to risk forecasting and assessment are challenged by the substantial temporal and geospatial dynamics of climate change, by the enhancement of risks by certain societal settings, and by the interaction of several risk factors. However, today big data from climate model simulations is increasingly being used to predict future trends in climate change and to assess the associated risks [10, 11]. There are various ways in which big data elements could contribute to improving the modelling of climate risks and impacts. New forms of data could be useful for the calibration of risk models and crowdsourcing and crowdsensing data collected for a specific purpose could be useful, as the assumption of constancy can be justified by reference to the user base . To manage their responses, stakeholders and policy makers need to forecast the potential local risk impacts of climate change at the county-to-city level. Part of this information could be derived by combining fine-grained climate risk assessments with AI-based big data analytics of weather extremes, property damage, health impairment and other variables . A number of big data analytics-based tools for screening climate risks are currently being developed, including the World Bank’s “Climate and Disaster Risk Screening Tool” , and many institutions are using them to better understand climate risk in their decision-making.
The primary challenge in forecasting the risks of global climate change is clearly the complexity and myriad of interacting factors. Each incremental change in greenhouse emissions and temperature gives rise to different responses in climatological, ecological, hydrological and other biophysical systems, varying from short term impacts on primary productivity to longer term effects such as rising sea levels, degradation or land formation , whereby the coupling of systems can lead to reactions that affect other systems, including feedback effects on climate . Some recent studies emphasise the changing nature of the three components of risk (hazard, exposure and vulnerability) and point to the need for the development of coherent guidance on strategies and methodologies that better account for the dynamic nature of the individual risk components and their interaction . This is particularly important since climate risks are not only a function of physical processes and shifting characteristics of climate systems but are also shaped by complex interactions with socio-economic drivers that can change and evolve within the macroscale conditions and may also change norms and values. With the driving forces and physical consequences of climate change being better known, researchers are increasingly turning their focus on analysing these socio-economic drivers of climate change. Big-data elements could become useful in this research field, as there are no well-proven universal theoretical concepts for such target systems .
1. Lesnikowski, A., et al., Frontiers in data analytics for adaptation research: Topic modeling. WIREs Climate Change, 2019. 10(3): p. e576.
2. Park, J.S., et al., A new forecasting system using the latent dirichlet allocation (LDA) topic modeling technique. WSEAS TRANSACTIONS on ENVIRONMENT and DEVELOPMENT, 2018. 14.
3. Kim, J., et al., Futuristic data-driven scenario building: Incorporating text mining and fuzzy association rule mining into fuzzy cognitive map. Expert Systems with Applications, 2016. 57: p. 311-323.
4. Jetter, A. and W. Schweinfort, Building scenarios with Fuzzy Cognitive Maps: An exploratory study of solar energy. Futures, 2011. 43(1): p. 52-66.
5. IPCC, Global warming of 1.5 C, in An IPCC Special Report on the impacts of global warming of 1.5°C above pre-industrial levels and related global greenhouse gas emission pathways, in the context of strengthening the global response to the threat of climate change, sustainable development, and efforts to eradicate poverty, V. Masson-Delmotte, et al., Editors. 2018, Intergovernmental Panel on Climate Change: Geneva. p. 1-630.
6. Adger, W.N., I. Brown, and S. Surminski, Advances in risk assessment for climate change adaptation policy. 2018, The Royal Society Publishing.
7. King, D., et al., Climate change: a risk assessment, ed. J. Hynard and T. Rodger. 2017, London, Beijing, Delhi, Cambridge (MA): Centre for Science and Policy. 1-79.
8. Knüsel, B., et al., Applying big data beyond small problems in climate research. Nature Climate Change, 2019. 9(3): p. 196-202.
9. Kennel, C.F., S. Briggs, and D.G. Victor, Making climate science more relevant. Science, 2016. 354(6311): p. 421-422.
10. Zhang, Z. and J. Li, Big Data Mining for Climate Change. 2019, Amsterdam, Oxford, Cambridge (MA): Elsevier. 1-346.
11. Ganguly, A.R., et al., Data-driven solutions. Climate 2020: Degrees of Devastation, 2018: p. 82-85.
12. Xu, Y., V. Ramanathan, and D.G. Victor, Global warming will happen faster than we think. 2018, Nature Publishing Group.
13. World Bank Group. Climate & Disaster Risk Screening Tool. 2019 15.05.2020]; Available from: https://olc.worldbank.org/content/climate-disaster-risk-screening-tool.
14. Viner, D., et al., Understanding the dynamic nature of risk in climate change assessments—A new starting point for discussion. Atmospheric Science Letters, 2020. 21(4): p. e958.