Fiona E Turner, Caitlin E Buck, Julie M Jones, Louise C Sime, Irene Malmierca Vallet, Richard D Wilkinson
Abstract The Antarctic ice sheet (AIS) is the Earth’s largest store of frozen water; understanding how it changed in the past allows us to improve projections of how it, and sea levels, may change. Here, we use previous AIS reconstructions, water isotope ratios from ice cores, and simulator predictions of the relationship between the ice-sheet shape and isotope ratios to create a model of the AIS at the Last Glacial Maximum. We develop a prior distribution that captures expert opinion about the AIS, generate a designed ensemble of potential shapes, run these through the climate model HadCM3, and train a Gaussian process emulator of the link between ice-sheet shape and isotope ratios. To make the analysis computationally tractable, we develop a preferential principal component method that allows us to reduce the dimension of the problem in a way that accounts for the differing importance we place in reconstructions, allowing us to create a basis that reflects prior uncertainty. We use Markov chain Monte Carlo to sample from the posterior distribution, finding shapes for which HadCM3 predicts isotope ratios closely matching observations from ice cores. The posterior distribution allows us to quantify the uncertainty in the reconstructed shape, a feature missing in other analyses.
{"title":"Reconstructing the Antarctic ice-sheet shape at the Last Glacial Maximum using ice-core data","authors":"Fiona E Turner, Caitlin E Buck, Julie M Jones, Louise C Sime, Irene Malmierca Vallet, Richard D Wilkinson","doi":"10.1093/jrsssc/qlad078","DOIUrl":"https://doi.org/10.1093/jrsssc/qlad078","url":null,"abstract":"Abstract The Antarctic ice sheet (AIS) is the Earth’s largest store of frozen water; understanding how it changed in the past allows us to improve projections of how it, and sea levels, may change. Here, we use previous AIS reconstructions, water isotope ratios from ice cores, and simulator predictions of the relationship between the ice-sheet shape and isotope ratios to create a model of the AIS at the Last Glacial Maximum. We develop a prior distribution that captures expert opinion about the AIS, generate a designed ensemble of potential shapes, run these through the climate model HadCM3, and train a Gaussian process emulator of the link between ice-sheet shape and isotope ratios. To make the analysis computationally tractable, we develop a preferential principal component method that allows us to reduce the dimension of the problem in a way that accounts for the differing importance we place in reconstructions, allowing us to create a basis that reflects prior uncertainty. We use Markov chain Monte Carlo to sample from the posterior distribution, finding shapes for which HadCM3 predicts isotope ratios closely matching observations from ice cores. The posterior distribution allows us to quantify the uncertainty in the reconstructed shape, a feature missing in other analyses.","PeriodicalId":49981,"journal":{"name":"Journal of the Royal Statistical Society Series C-Applied Statistics","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135154123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jiachen Zhang, Matthew Bonas, Diogo Bolster, Geir-Arne Fuglstad, S. Castruccio
Obtaining high-resolution maps of precipitation data can provide key insights to stakeholders to assess a sustainable access to water resources at urban scale. Mapping a non-stationary, sparse process such as precipitation at very high spatial resolution requires the interpolation of global datasets at the location where ground stations are available with statistical models able to capture complex non-Gaussian global space–time dependence structures. In this work, we propose a new approach based on capturing the spatially varying anisotropy of a latent Gaussian process via a locally deformed stochastic partial differential equation (SPDE) with a buffer allowing for a different spatial structure across land and sea. The finite volume approximation of the SPDE, coupled with integrated nested Laplace approximation ensures feasible Bayesian inference for tens of millions of observations. The simulation studies showcase the improved predictability of the proposed approach against stationary and no-buffer alternatives. The proposed approach is then used to yield high-resolution simulations of daily precipitation across the United States.
{"title":"High-resolution global precipitation downscaling with latent Gaussian models and non-stationary stochastic partial differential equation structure","authors":"Jiachen Zhang, Matthew Bonas, Diogo Bolster, Geir-Arne Fuglstad, S. Castruccio","doi":"10.1093/jrsssc/qlad084","DOIUrl":"https://doi.org/10.1093/jrsssc/qlad084","url":null,"abstract":"\u0000 Obtaining high-resolution maps of precipitation data can provide key insights to stakeholders to assess a sustainable access to water resources at urban scale. Mapping a non-stationary, sparse process such as precipitation at very high spatial resolution requires the interpolation of global datasets at the location where ground stations are available with statistical models able to capture complex non-Gaussian global space–time dependence structures. In this work, we propose a new approach based on capturing the spatially varying anisotropy of a latent Gaussian process via a locally deformed stochastic partial differential equation (SPDE) with a buffer allowing for a different spatial structure across land and sea. The finite volume approximation of the SPDE, coupled with integrated nested Laplace approximation ensures feasible Bayesian inference for tens of millions of observations. The simulation studies showcase the improved predictability of the proposed approach against stationary and no-buffer alternatives. The proposed approach is then used to yield high-resolution simulations of daily precipitation across the United States.","PeriodicalId":49981,"journal":{"name":"Journal of the Royal Statistical Society Series C-Applied Statistics","volume":"29 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86900064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Claudio Heinrich‐Mertsching, J. C. Wahl, A. Ordoñez, M. Stien, John Elvsborg, O. Haug, T. Thorarinsdottir
{"title":"Assessing present and future risk of water damage using. Response to Comments","authors":"Claudio Heinrich‐Mertsching, J. C. Wahl, A. Ordoñez, M. Stien, John Elvsborg, O. Haug, T. Thorarinsdottir","doi":"10.1093/jrsssc/qlad067","DOIUrl":"https://doi.org/10.1093/jrsssc/qlad067","url":null,"abstract":"","PeriodicalId":49981,"journal":{"name":"Journal of the Royal Statistical Society Series C-Applied Statistics","volume":"26 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83202519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Ankur Dutta’s contribution to the Discussion of “The First Discussion Meeting on Statistical aspects of climate change”","authors":"Ankur Dutta","doi":"10.1093/jrsssc/qlad052","DOIUrl":"https://doi.org/10.1093/jrsssc/qlad052","url":null,"abstract":"","PeriodicalId":49981,"journal":{"name":"Journal of the Royal Statistical Society Series C-Applied Statistics","volume":"7 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82465798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Austin Talbot, David Dunson, Kafui Dzirasa, David Carlson
Targeted brain stimulation has the potential to treat mental illnesses. We develop an approach to help design protocols by identifying relevant multi-region electrical dynamics. Our approach models these dynamics as a superposition of latent networks, where the latent variables predict a relevant outcome. We use supervised autoencoders (SAEs) to improve predictive performance in this context, describe the conditions where SAEs improve predictions, and provide modelling constraints to ensure biological relevance. We experimentally validate our approach by finding a network associated with stress that aligns with a previous stimulation protocol and characterizing a genotype associated with bipolar disorder.
{"title":"Estimating a brain network predictive of stress and genotype with supervised autoencoders.","authors":"Austin Talbot, David Dunson, Kafui Dzirasa, David Carlson","doi":"10.1093/jrsssc/qlad035","DOIUrl":"https://doi.org/10.1093/jrsssc/qlad035","url":null,"abstract":"<p><p>Targeted brain stimulation has the potential to treat mental illnesses. We develop an approach to help design protocols by identifying relevant multi-region electrical dynamics. Our approach models these dynamics as a superposition of latent networks, where the latent variables predict a relevant outcome. We use supervised autoencoders (SAEs) to improve predictive performance in this context, describe the conditions where SAEs improve predictions, and provide modelling constraints to ensure biological relevance. We experimentally validate our approach by finding a network associated with stress that aligns with a previous stimulation protocol and characterizing a genotype associated with bipolar disorder.</p>","PeriodicalId":49981,"journal":{"name":"Journal of the Royal Statistical Society Series C-Applied Statistics","volume":"72 4","pages":"912-936"},"PeriodicalIF":1.6,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10474874/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10163295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Proposer of the vote of thanks to Narayanan, Kosmidis and Dellaportas and contribution to the Discussion of “Flexible marked spatio-temporal point processes with applications to event sequences from association football”","authors":"D. Karlis","doi":"10.1093/jrsssc/qlad071","DOIUrl":"https://doi.org/10.1093/jrsssc/qlad071","url":null,"abstract":"","PeriodicalId":49981,"journal":{"name":"Journal of the Royal Statistical Society Series C-Applied Statistics","volume":"413 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74125391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Ron Yurko and Rebecca Nugent’s contribution to the Discussion of “Flexible marked spatio-temporal point processes with applications to event sequences from association football” by Narayanan, Kosmidis and Dellaportas","authors":"Ronald Yurko, Rebecca Nugent","doi":"10.1093/jrsssc/qlad069","DOIUrl":"https://doi.org/10.1093/jrsssc/qlad069","url":null,"abstract":"","PeriodicalId":49981,"journal":{"name":"Journal of the Royal Statistical Society Series C-Applied Statistics","volume":"32 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76269443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Seconder of the vote of thanks to Narayanan, Kosmidis and Dellaportas and contribution to the Discussion of “Flexible marked spatio-temporal point processes with applications to event sequences from association football”","authors":"Leonardo Egidi","doi":"10.1093/jrsssc/qlad072","DOIUrl":"https://doi.org/10.1093/jrsssc/qlad072","url":null,"abstract":"","PeriodicalId":49981,"journal":{"name":"Journal of the Royal Statistical Society Series C-Applied Statistics","volume":"37 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74107240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Paul Smith’s contribution to the Discussion of “Flexible marked spatio-temporal point processes with applications to event sequences from association football” by Narayanan, Kosmidis and Dellaportas","authors":"Paul A. Smith","doi":"10.1093/jrsssc/qlad070","DOIUrl":"https://doi.org/10.1093/jrsssc/qlad070","url":null,"abstract":"","PeriodicalId":49981,"journal":{"name":"Journal of the Royal Statistical Society Series C-Applied Statistics","volume":"1 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81334409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Jorge Mateu’s contribution to the Discussion of ‘Flexible marked spatio-temporal point processes with applications to event sequences from association football’ by Narayanan, Kosmidis and Dellaportas","authors":"J. Mateu","doi":"10.1093/jrsssc/qlad073","DOIUrl":"https://doi.org/10.1093/jrsssc/qlad073","url":null,"abstract":"","PeriodicalId":49981,"journal":{"name":"Journal of the Royal Statistical Society Series C-Applied Statistics","volume":"40 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85694113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：