Spatiotemporal statistical machine learning (ST-SML): theory, methods, and applications

时空统计机器学习 (ST-SML)：理论、方法和应用

• 批准号: EP/V002910/2
• 负责人: Seth Flaxman
• 金额: $ 149.81万
• 依托单位: University of Oxford
• 依托单位国家: 英国
• 项目类别: Fellowship
• 财政年份: 2021
• 资助国家: 英国
• 起止时间: 2021 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FV002910%2F2
• 关键词: Spatiotemporal; statistical; machine; learning; ST

Machine learning (ML) is the computational beating heart of the modern Artificial Intelligence (AI) renaissance. A number of fields, from computer vision to speech recognition have been completely transformed by the successes of machine learning. But practitioners and policymakers struggle when it comes to translating the successes of ML from narrowly defined prediction problems---e.g. "is this a picture of a cat?"---to the broader and messier world of public health and public policy. This fellowship will fund research on new ML methods to enable us to better ask and answer questions concerning change over space and time, such as: 1) How does disease risk, poverty, or housing quality vary within a country and over time?2) Can satellite data enable us to answer policy questions in a more timely and spatially localised manner?3) Do the dynamics of violent crime differ in different cities?4) Did the world achieve the Millennium Development Goals? Will the world achieve the Sustainable Development Goals?Bespoke answers to these questions are not enough, because practitioners in the public sector face new challenges in real-time. They need reproducible and well-documented applied workflows to follow to enable them to tackle important public policy problems as they arise.

机器学习（ML）是现代人工智能（AI）复兴的计算心脏。机器学习的成功彻底改变了从计算机视觉到语音识别的许多领域。但是从业者和政策制定者在将ML的成功从狭义的预测问题中转化出来时会遇到困难-例如，“这是一张猫的照片吗？”“-到更广阔、更混乱的公共卫生和公共政策领域。该奖学金将资助新的ML方法的研究，使我们能够更好地询问和回答有关空间和时间变化的问题，例如：1）疾病风险，贫困或住房质量在一个国家内和随着时间的推移如何变化？2)卫星数据能否使我们能够以更及时和空间局部化的方式回答政策问题？3)不同城市的暴力犯罪动态是否不同？4)世界是否实现了千年发展目标？世界能否实现可持续发展目标？这些问题的定制答案是不够的，因为公共部门的从业人员面临着实时的新挑战。他们需要可复制和记录良好的应用工作流程，以使他们能够在出现重要的公共政策问题时加以解决。

项目成果

Reauthorise PEPFAR to prevent death, orphanhood, and suffering for millions of children.

重新授权总统防治艾滋病紧急救援计划（PEPFAR），以防止数百万儿童死亡、成为孤儿和遭受痛苦。

• DOI: 10.1016/s0140-6736(23)01723-3
• 发表时间: 2023
• 期刊: Lancet (London, England)
• 作者: Cluver L

Genomic characterization and epidemiology of an emerging SARS-CoV-2 variant in Delhi, India.

• DOI: 10.1126/science.abj9932
• 发表时间: 2021-11-19
• 期刊: Science (New York, N.Y.)
• 作者: Dhar MS;Marwal R;Vs R;Ponnusamy K;Jolly B;Bhoyar RC;Sardana V;Naushin S;Rophina M;Mellan TA;Mishra S;Whittaker C;Fatihi S;Datta M;Singh P;Sharma U;Ujjainiya R;Bhatheja N;Divakar MK;Singh MK;Imran M;Senthivel V;Maurya R;Jha N;Mehta P;A V;Sharma P;Vr A;Chaudhary U;Soni N;Thukral L;Flaxman S;Bhatt S;Pandey R;Dash D;Faruq M;Lall H;Gogia H;Madan P;Kulkarni S;Chauhan H;Sengupta S;Kabra S;Indian SARS-CoV-2 Genomics Consortium (INSACOG)‡;Gupta RK;Singh SK;Agrawal A;Rakshit P;Nandicoori V;Tallapaka KB;Sowpati DT;Thangaraj K;Bashyam MD;Dalal A;Sivasubbu S;Scaria V;Parida A;Raghav SK;Prasad P;Sarin A;Mayor S;Ramakrishnan U;Palakodeti D;Seshasayee ASN;Bhat M;Shouche Y;Pillai A;Dikid T;Das S;Maitra A;Chinnaswamy S;Biswas NK;Desai AS;Pattabiraman C;Manjunatha MV;Mani RS;Arunachal Udupi G;Abraham P;Atul PV;Cherian SS
• 通讯作者: Cherian SS

Spatial and temporal fluctuations in COVID-19 fatality rates in Brazilian hospitals.

• DOI: 10.1038/s41591-022-01807-1
• 发表时间: 2022-07
• 期刊: NATURE MEDICINE
• 影响因子: 82.9
• 作者: Brizzi, Andrea;Whittaker, Charles;Servo, Luciana M. S.;Hawryluk, Iwona;Prete Jr, Carlos A.;de Souza, William M.;Aguiar, Renato S.;Araujo, Leonardo J. T.;Bastos, Leonardo S.;Blenkinsop, Alexandra;Buss, Lewis F.;Candido, Darlan;Castro, Marcia C.;Costa, Silvia F.;Croda, Julio;de Souza Santos, Andreza Aruska;Dye, Christopher;Flaxman, Seth;Fonseca, Paula L. C.;Geddes, Victor E. V.;Gutierrez, Bernardo;Lemey, Philippe;Levin, Anna S.;Mellan, Thomas;Bonfim, Diego M.;Miscouridou, Xenia;Mishra, Swapnil;Monod, Melodie;Moreira, Filipe R. R.;Nelson, Bruce;Pereira, Rafael H. M.;Ranzani, Otavio;Schnekenberg, Ricardo P.;Semenova, Elizaveta;Sonnabend, Raphael;Souza, Renan P.;Xi, Xiaoyue;Sabino, Ester C.;Faria, Nuno R.;Bhatt, Samir;Ratmann, Oliver
• 通讯作者: Ratmann, Oliver

Seq2Seq Surrogates of Epidemic Models to Facilitate Bayesian Inference

流行病模型的 Seq2Seq 替代品促进贝叶斯推理

• DOI: 10.1609/aaai.v37i12.26658
• 发表时间: 2023
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Charles G

Improving axial resolution in Structured Illumination Microscopy using deep learning.

• DOI: 10.1098/rsta.2020.0298
• 发表时间: 2021-06-14
• 期刊: Philosophical transactions. Series A, Mathematical, physical, and engineering sciences
• 作者: Boland MA;Cohen EAK;Flaxman SR;Neil MAA
• 通讯作者: Neil MAA