{"title":"空间深度卷积神经网络","authors":"Qi Wang, Paul A. Parker, Robert B. Lund","doi":"arxiv-2409.07559","DOIUrl":null,"url":null,"abstract":"Spatial prediction problems often use Gaussian process models, which can be\ncomputationally burdensome in high dimensions. Specification of an appropriate\ncovariance function for the model can be challenging when complex\nnon-stationarities exist. Recent work has shown that pre-computed spatial basis\nfunctions and a feed-forward neural network can capture complex spatial\ndependence structures while remaining computationally efficient. This paper\nbuilds on this literature by tailoring spatial basis functions for use in\nconvolutional neural networks. Through both simulated and real data, we\ndemonstrate that this approach yields more accurate spatial predictions than\nexisting methods. Uncertainty quantification is also considered.","PeriodicalId":501425,"journal":{"name":"arXiv - STAT - Methodology","volume":"47 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Spatial Deep Convolutional Neural Networks\",\"authors\":\"Qi Wang, Paul A. Parker, Robert B. Lund\",\"doi\":\"arxiv-2409.07559\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Spatial prediction problems often use Gaussian process models, which can be\\ncomputationally burdensome in high dimensions. Specification of an appropriate\\ncovariance function for the model can be challenging when complex\\nnon-stationarities exist. Recent work has shown that pre-computed spatial basis\\nfunctions and a feed-forward neural network can capture complex spatial\\ndependence structures while remaining computationally efficient. This paper\\nbuilds on this literature by tailoring spatial basis functions for use in\\nconvolutional neural networks. Through both simulated and real data, we\\ndemonstrate that this approach yields more accurate spatial predictions than\\nexisting methods. Uncertainty quantification is also considered.\",\"PeriodicalId\":501425,\"journal\":{\"name\":\"arXiv - STAT - Methodology\",\"volume\":\"47 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - STAT - Methodology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.07559\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - STAT - Methodology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07559","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Spatial prediction problems often use Gaussian process models, which can be
computationally burdensome in high dimensions. Specification of an appropriate
covariance function for the model can be challenging when complex
non-stationarities exist. Recent work has shown that pre-computed spatial basis
functions and a feed-forward neural network can capture complex spatial
dependence structures while remaining computationally efficient. This paper
builds on this literature by tailoring spatial basis functions for use in
convolutional neural networks. Through both simulated and real data, we
demonstrate that this approach yields more accurate spatial predictions than
existing methods. Uncertainty quantification is also considered.