{"type":"ScholarlyArticle","title":"Revealing the Excitation Causality between Climate and Political Violence via a Neural Forward-Intensity Poisson Process","authors":[{"name":"Schyler C. Sun","slug":"schyler-c-sun","given":"Schyler C.","family":"Sun","affiliation":"DARTeC , Cranfield University , UK"},{"name":"Bailu Jin","slug":"bailu-jin","given":"Bailu","family":"Jin","affiliation":"DARTeC , Cranfield University , UK"},{"name":"Zhuangkun Wei","slug":"zhuangkun-wei","given":"Zhuangkun","family":"Wei","affiliation":"DARTeC , Cranfield University , UK"},{"name":"Weisi Guo","slug":"weisi-guo","given":"Weisi","family":"Guo","affiliation":"DARTeC , Cranfield University , UK; Alan Turing Institute , UK"}],"abstract":"The causal mechanism between climate and political violence is fraught with complex mechanisms. Current quantitative causal models rely on one or more assumptions: (1) the climate drivers persistently generate conflict, (2) the causal mechanisms have a linear relationship with the conflict generation parameter, and/or (3) there is sufficient data to inform the prior distribution. Yet, we know conflict drivers often excite a social transformation process which leads to violence (e.g., drought forces agricultural producers to join urban militia), but further climate effects do not necessarily contribute to further violence. Therefore, not only is this bifurcation relationship highly non-linear, there is also often a lack of data to support prior assumptions for high resolution modeling. \r\n\r\nHere, we aim to overcome the aforementioned causal modeling challenges by proposing a neural forward-intensity Poisson process (NFIPP) model. The NFIPP is designed to capture the potential non-linear causal mechanism in climate induced political violence, whilst being robust to sparse and timing-uncertain data. Our results span 20 recent years and reveal an excitation-based causal link between extreme climate events and political violence across diverse countries. Our climate-induced conflict model results are cross-validated against qualitative climate vulnerability indices. Furthermore, we label historical events that either improve or reduce our predictability gain, demonstrating the importance of domain expertise in informing interpretation.","doi":"10.24963/ijcai.2022/718","url":"https://ijcai.org/proceedings/2022/718","pdf":"https://ijcai.org/proceedings/2022/0718.pdf","markdown":"https://ijcai.org/proceedings/2022/718.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/718","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Research Papers","track":"AI for Good","number":718,"pages":{"first":5171,"last":5177},"keywords":["Machine Learning: Probabilistic Machine Learning","Multidisciplinary Topics and Applications: Social Sciences","Uncertainty in AI: Applications","Machine Learning: Applications"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987147","length_sec":92,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985290","length_sec":665,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Asaka, 2021] Jeremiah O Asaka. Climate change-terrorism nexus? a preliminary review/analysis of the literature. Per- spectives on Terrorism, 15(1):81-92, 2021.","title":"Climate change-terrorism nexus? a preliminary review/analysis of the literature","authors":"Jeremiah O Asaka","year":"2021","venue":"Perspectives on Terrorism","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Buhaug et al., 2019] H Buhaug, M Burke, J Fearon, C Field, J Maystadt, and J Loughlin. Climate as a risk factor for armed conflict. Nature, 2019.","title":"Climate as a risk factor for armed conflict","authors":"M Buhaug, J Burke, C Fearon, J Field, Maystadt, Loughlin","year":"2019","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2015] Chen Chen, Ian Noble, Jessica Hell- mann, Joyce Coffee, Martin Murillo, and Nitesh Chawla. University of notre dame global adaptation index country index technical report. 2015.","title":"University of notre dame global adaptation index country","authors":"Chen Chen, Ian Noble, Jessica Hellmann, Joyce Coffee, Martin Murillo, Nitesh Chawla","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chvosteková et al., 2021] Martina Chvosteková, Jozef Jakubík, and Anna Krakovská. Granger causality on forward and reversed time series. Entropy, 23(4), 2021.","title":"Martina Chvosteková, Jozef Jakubík, and Anna Krakovská. Granger causality on forward and reversed time series","authors":"Chvosteková","year":"2021","venue":"Entropy","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Field et al., 2012] C Field, V Barros, T Stocker, and D. Qin. Managing the risks of extreme events and disasters to ad- vance climate change adaptation. Intergovernmental Panel on Climate Change (IPCC), 2012.","title":"Managing the risks of extreme events and disasters to advance climate change adaptation","authors":"Field, T Barros, D Stocker, Qin","year":"2012","venue":"Intergovernmental Panel on Climate Change","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Frogner et al., 2015] Charlie Frogner, Chiyuan Zhang, Hos- sein Mobahi, Mauricio Araya, and Tomaso A Poggio. Learning with a wasserstein loss. Advances in Neural In- formation Processing Systems, 28:2053-2061, 2015.","title":"Learning with a wasserstein loss","authors":"Charlie Frogner, Chiyuan Zhang, Hossein Mobahi, Mauricio Araya, Tomaso A Poggio","year":"2015","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gleditsch and Ward, 2013] K Gleditsch and M Ward. Fore- casting is difficult, especially about the future: Using con- tentious issues to forecast interstate disputes. Journal of Peace Research, 2013.","title":"Forecasting is difficult, especially about the future: Using contentious issues to forecast interstate disputes","authors":"Ward ; ] K Gleditsch, M Gleditsch, Ward","year":"2013","venue":"Journal of Peace Research","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Guo et al., 2018] Weisi Guo, Kristian Gleditsch, and Alan Wilson. Retool ai to forecast and limit wars. Nature, 2018.","title":"Retool ai to forecast and limit wars","authors":"Guo","year":"2018","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Guo, 2019] Weisi Guo. Common statistical patterns in ur- ban terrorism. Royal Society open science, 6(9), 2019.","title":"Common statistical patterns in urban terrorism","authors":"Weisi Guo, Guo","year":"2019","venue":"Royal Society open science","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hsiang and Burke, 2014] S Hsiang and M Burke. Climate, conflict, and social stability: what does the evidence say? Climate Change, 2014.","title":"Climate, conflict, and social stability: what does the evidence say? Climate Change","authors":"S Hsiang, M Burke","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hsiang et al., 2011] S Hsiang, K Meng, and M Cane. Civil conflicts are associated with the global climate. Nature, 2011.","title":"Civil conflicts are associated with the global climate","authors":"K Hsiang, M Meng, Cane","year":"2011","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Isham and Westcott, 1979] Valerie Isham and Mark West- cott. A self-correcting point process. Stochastic processes and their applications, 8(3):335-347, 1979.","title":"A self-correcting point process","authors":"Valerie Isham, Mark Westcott","year":"1979","venue":"Stochastic processes and their applications","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Krakovska et al., 2018] A Krakovska, J Jakubik, M Chvostekova, D Coufal, N Jajcay, and M Palus. Comparison of six methods for the detection of causality in a bivariate time series. Physical Review E, 2018.","title":"Comparison of six methods for the detection of causality in a bivariate time series","authors":"Krakovska, M Jakubik, D Chvostekova, N Coufal, M Jajcay, Palus","year":"2018","venue":"Physical Review E","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lee et al., 2018] Jaehoon Lee, Yasaman Bahri, Roman No- vak, Samuel S Schoenholz, Jeffrey Pennington, and Jascha Sohl-Dickstein. Deep neural networks as gaussian pro- cesses. In International Conference on Learning Repre- sentations, 2018.","title":"Deep neural networks as gaussian processes","authors":"Jaehoon Lee, Yasaman Bahri, Roman Novak, S Samuel, Jeffrey Schoenholz, Jascha Pennington, Sohl-Dickstein","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Mei and Eisner, 2017] Hongyuan Mei and Jason M Eisner. The neural hawkes process: A neurally self-modulating multivariate point process. Advances in neural information processing systems, 30, 2017.","title":"The neural hawkes process: A neurally self-modulating multivariate point process","authors":"Eisner ; ] Hongyuan Mei, Jason M Mei, Eisner","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Nakamura et al., 2020] Takaaki Nakamura, Makoto Ima- mura, Ryan Mercer, and Eamonn Keogh. Merlin: Parameter-free discovery of arbitrary length anomalies in massive time series archives. In IEEE International Con- ference on Data Mining (ICDM). IEEE, 2020.","title":"Merlin: Parameter-free discovery of arbitrary length anomalies in massive time series archives","authors":"Takaaki Nakamura, Makoto Imamura, Ryan Mercer, Eamonn Keogh","year":"2020","venue":"IEEE International Conference on Data Mining (ICDM)","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Rogin, 2009] Josh Rogin. Confirmed: Obama to \"surge\" 30,000 troops to afghanistan and \"begin\" withdrawal in july 2011. Foreign Policy, 2009.","title":"Confirmed: Obama to \"surge\" 30,000 troops to afghanistan and \"begin","authors":"Josh Rogin, Rogin","year":"2009","venue":"withdrawal in july 2011","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Rooney, 2009] Katie Rooney. Barack obama's first 100 days: A surge for afghanistan. American Forces Press Ser- vice, 2009.","title":"Barack obama's first 100 days: A surge for afghanistan","authors":"Katie Rooney","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Salehyan, 2014] I. Salehyan. Climate change and conflict: Making sense of disparate findings. Political Geography, 2014.","title":"Climate change and conflict: Making sense of disparate findings","authors":"; I Salehyan, Salehyan","year":"2014","venue":"Political Geography","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Shchur et al., 2021] O Shchur, A Turkmen, T Januschowski, and S Gunnemann. Neural tempo- ral point processes: A review. Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI), 2021.","title":"Neural temporal point processes: A review","authors":"Shchur, T Turkmen, Januschowski, Gunnemann","year":"2021","venue":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":"/proceedings/2021/623"},{"position":21,"raw":"[Shen et al., 2014] Huawei Shen, Dashun Wang, Chaoming Song, and Albert-László Barabási. Modeling and predict- ing popularity dynamics via reinforced poisson processes. In Proceedings of the AAAI Conference on Artificial Intel- ligence, volume 28, 2014.","title":"Modeling and predicting popularity dynamics via reinforced poisson processes","authors":"Shen","year":"2014","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Stoyan et al., 2013] Dietrich Stoyan, Wilfrid S Kendall, Sung Nok Chiu, and Joseph Mecke. Stochastic geometry and its applications. John Wiley & Sons, 2013.","title":"Stochastic geometry and its applications","authors":"Dietrich Stoyan, Wilfrid S Kendall, Sung Nok Chiu, Joseph Mecke","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Sun et al., 2021] Schyler C Sun, Chen Li, Zhuangkun Wei, Antonios Tsourdos, and Weisi Guo. Scalable partial ex- plainability in neural networks via flexible activation func- tions (student abstract). In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 15899-15900, 2021.","title":"Scalable partial explainability in neural networks via flexible activation functions (student abstract)","authors":"Chen Schyler C Sun, Zhuangkun Li, Antonios Wei, Weisi Tsourdos, Guo","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Tench et al., 2016] Stephen Tench, Hannah Fry, and Paul Gill. Spatio-temporal patterns of ied usage by the provi- sional irish republican army. European Journal of Applied Mathematics, 27(3):377-402, 2016.","title":"Spatio-temporal patterns of ied usage by the provisional irish republican army","authors":"Stephen Tench, Hannah Fry, Paul Gill","year":"2016","venue":"European Journal of Applied Mathematics","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xiao et al., 2017] Shuai Xiao, Junchi Yan, Xiaokang Yang, Hongyuan Zha, and Stephen Chu. Modeling the intensity function of point process via recurrent neural networks. In Proceedings of the AAAI Conference on Artificial Intelli- gence, volume 31, 2017.","title":"Modeling the intensity function of point process via recurrent neural networks","authors":"Shuai Xiao, Junchi Yan, Xiaokang Yang, Hongyuan Zha, Stephen Chu","year":"2017","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zammit-Mangion et al., 2012] Andrew Zammit-Mangion, Michael Dewar, Visakan Kadirkamanathan, and Guido Sanguinetti. Point process modelling of the afghan war diary. Proceedings of the National Academy of Sciences, 109(31):12414-12419, 2012.","title":"Point process modelling of the afghan war diary","authors":"Andrew Zammit-Mangion, Michael Dewar, Visakan Kadirkamanathan, Guido Sanguinetti","year":"2012","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}