Deep learning and process understanding for data-driven Earth system science

Reichstein Markus; Camps-Valls Gustau; Stevens Bjorn; Jung Martin; Denzler Joachim; Carvalhais Nuno; Prabhat

首页> 外文期刊>Nature >Deep learning and process understanding for data-driven Earth system science

【24h】

Deep learning and process understanding for data-driven Earth system science

机译：数据驱动地球系统科学的深度学习和过程理解

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Machine learning approaches are increasingly used to extract patterns and insights from the ever-increasing stream of geospatial data, but current approaches may not be optimal when system behaviour is dominated by spatial or temporal context. Here, rather than amending classical machine learning, we argue that these contextual cues should be used as part of deep learning (an approach that is able to extract spatio-temporal features automatically) to gain further process understanding of Earth system science problems, improving the predictive ability of seasonal forecasting and modelling of long-range spatial connections across multiple timescales, for example. The next step will be a hybrid modelling approach, coupling physical process models with the versatility of data-driven machine learning.

机译：机器学习方法越来越多地用于从不断增长的地理空间数据流中提取模式和见解，但是当系统行为受空间或时间上下文支配时，当前的方法可能不是最佳方法。在这里，我们认为不应将这些上下文线索用作深度学习的一部分（能够自动提取时空特征的方法），以获取对地球系统科学问题的进一步过程理解，而不是对传统的机器学习进行修正。例如，季节性预测的预测能力以及跨多个时间尺度的远程空间连接建模。下一步将是一种混合建模方法，将物理过程模型与数据驱动的机器学习的多功能性结合在一起。

著录项

来源
《Nature》 |2019年第7743期|195-204|共10页
作者
Reichstein Markus; Camps-Valls Gustau; Stevens Bjorn; Jung Martin; Denzler Joachim; Carvalhais Nuno; Prabhat;
展开▼
作者单位

Univ Valencia, Image Proc Lab, Valencia, Spain;

Friedrich Schiller Univ, Comp Vis Grp, Comp Sci, Jena, Germany;

Michael Stifel Ctr Jena Data Driven & Simulat Sci, Jena, Germany;

Max Planck Inst Biogeochem, Dept Biogeochem Integrat, Jena, Germany;

Max Planck Inst Meteorol, Hamburg, Germany;

Lawrence Berkeley Natl Lab, Natl Energy Res Supercomp Ctr, Berkeley, CA USA;

Univ Nova Lisboa, Dept Ciencias & Engn Ambiente, CENSE, Fac Ciencias & Tecnol, Lisbon, Portugal;

展开▼
收录信息美国《科学引文索引》(SCI);美国《工程索引》(EI);美国《生物学医学文摘》(MEDLINE);美国《化学文摘》(CA);
原文格式 PDF
正文语种 eng
中图分类
关键词

相似文献

外文文献
中文文献
专利

1. Machine learning for data-driven discovery in solid Earth geoscience [J] . Bergen Karianne J., Johnson Paul A., de Hoop Maarten V., Science . 2019,第6433期

机译：机器学习用于固体地球科学中数据驱动的发现
2. Understanding the Earth as a Complex System – recent advances in data analysis and modelling in Earth sciences [J] . R. Donner, S. Barbosa, J. Kurths, The European Physical Journal Special Topics . 2009,第1期

机译：将地球理解为复杂系统–地球科学中数据分析和建模的最新进展
3. Understanding the Earth as a Complex System _ recent advances in data analysis and modelling in Earth sciences [J] . R. Donner, S. Barbosa, J. Kurths, The European physical journal: Special topics . 2009,第Null期

机译：了解地球是一个复杂的系统_地球科学中数据分析和建模的最新进展
4. Machine Learning for Modelling and Understanding in Earth Sciences [C] . Gustau Camps-Vails International conference on discovery science . 2020

机译：地球科学建模与理解的机器学习
5. Large-scale Optimization and Deep Learning Techniques for Data-driven Signal Processing [D] . ?DeGuchy, Omar 2020

机译：用于数据驱动信号处理的大规模优化和深度学习技术
6. Modeling and Analysis of Data-Driven Systems through Computational Neuroscience Wavelet-Deep Optimized Model for Nonlinear Multicomponent Data Forecasting [O] . Xue-Bo Jin, Jia-Hui Zhang, Ting-Li Su, 2021

机译：通过计算神经科学对数据驱动系统的建模与分析非线性多组分数据预测的计算神经科学小波深度优化模型
7. Deep learning and process understanding for data-driven Earth system science [O] . Markus Reichstein, Gustau Camps-Valls, Bjorn Stevens, 2019

机译：数据驱动地球系统科学的深度学习和过程理解

Deep learning and process understanding for data-driven Earth system science

摘要

著录项

相似文献

相关主题

期刊订阅