The Experts below are selected from a list of 40227 Experts worldwide ranked by ideXlab platform
Nuno Carvalhais - One of the best experts on this subject based on the ideXlab platform.
-
deep learning and process understanding for data driven Earth System Science
Nature, 2019Co-Authors: Markus Reichstein, Gustau Campsvalls, Bjorn Stevens, Martin Jung, Joachim Denzler, Nuno CarvalhaisAbstract: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. Complex Earth System challenges can be addressed by incorporating spatial and temporal context into machine learning, especially via deep learning, and further by combining with physical models into hybrid models.
-
deep learning and process understanding for data driven Earth System Science
Nature, 2019Co-Authors: Markus Reichstein, Gustau Campsvalls, Bjorn Stevens, Martin Jung, Joachim Denzler, Nuno CarvalhaisAbstract: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.
Markus Reichstein - One of the best experts on this subject based on the ideXlab platform.
-
deep learning and process understanding for data driven Earth System Science
Nature, 2019Co-Authors: Markus Reichstein, Gustau Campsvalls, Bjorn Stevens, Martin Jung, Joachim Denzler, Nuno CarvalhaisAbstract: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. Complex Earth System challenges can be addressed by incorporating spatial and temporal context into machine learning, especially via deep learning, and further by combining with physical models into hybrid models.
-
deep learning and process understanding for data driven Earth System Science
Nature, 2019Co-Authors: Markus Reichstein, Gustau Campsvalls, Bjorn Stevens, Martin Jung, Joachim Denzler, Nuno CarvalhaisAbstract: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.
-
preface climate extremes and biogeochemical cycles in the terrestrial biosphere impacts and feedbacks across scales
Biogeosciences, 2015Co-Authors: Michael Bahn, Markus Reichstein, Kaiyu Guan, Jose M Moreno, Christopher A WilliamsAbstract:M. Bahn1, M. Reichstein2, K. Guan3, J. M. Moreno4, and C. Williams5 1Institute of Ecology, University of Innsbruck, Innsbruck, Austria 2Max Planck Institute for Biogeochemistry, Jena, Germany 3Department of Environmental Earth System Science, Stanford University, Stanford, CA 94025, USA 4Departamento de Ciencias Ambientales, Universidad de Castilla-La Mancha, Campus Fabrica de Armas, 45071, Toledo, Spain 5Graduate School of Geography, Clark University, 950 Main Street, Worcester MA 01610, USA
Martin Rice - One of the best experts on this subject based on the ideXlab platform.
-
responding to complex societal challenges a decade of Earth System Science partnership essp interdisciplinary research
Current Opinion in Environmental Sustainability, 2012Co-Authors: Ada Ignaciuk, Rik Leemans, Josep G Canadell, John Ingram, Martin Rice, Janos J Bogardi, Shobhakar Dhakal, Mark W RosenbergAbstract:The Earth System is an integrated, self-regulating System under increasing pressure from anthropogenic transformation. The Earth System Science Partnership (ESSP), which was established by the international global environmental change research programs (i.e., DIVERSITAS, IGBP, IHDP and WCRP) facilitates the study of this System in order to understand how and why it is changing, and to explore the implications of these changes for global and regional sustainability. Crucial to this scientific enterprise are interdisciplinary Joint Projects on carbon, food, water and health. This paper analyses the scientific and institutional evolution of ESSP as a framework for interdisciplinary and integrative research of societal relevance. Case studies on food Systems, carbon budgets, water security and biodiversity conservation illustrate how these projects have advanced integrated Earth System knowledge. At the institutional level, we explain the transformation of the ESSP governance and how this has further enabled interdisciplinary research. The lessons learnt from ESSP research can contribute to the development of the next generation of Earth System Science for sustainability.
-
developing a common strategy for integrative global environmental change research and outreach the Earth System Science partnership essp
Current Opinion in Environmental Sustainability, 2009Co-Authors: Rik Leemans, Ghassem R Asrar, Antonio J Busalacchi, Josep G Canadell, John Ingram, Anne Larigauderie, H A Mooney, Carlos A Nobre, Anand Patwardhan, Martin RiceAbstract:The Earth System Science Partnership (ESSP) was established in 2001 by four global environmental change (GEC) research programmes: DIVERSITAS, IGBP, IHDP and WCRP. ESSP facilitates the study of the Earth's environment as an integrated System in order to understand how and why it is changing, and to explore the implications of these changes for global and regional sustainability. Joint research projects on carbon dynamics, food, water and health have been established. As a result of an independent review, the ESSP developed a new strategy that will provide an internationally coordinated and holistic approach to Earth System Science. The approach integrates natural and social Sciences from regional to the global scale. The mainstay of the ESSP is to identify and define Earth System Science challenges, enable integrative research to address these challenges, and build scientific capacity. The GEC research community also faces an increasing challenge to present research results in more accessible and informative ways to stakeholders, especially to policy-makers. In response, the ESSP is developing new services that include knowledge products, Earth System Science fora, a synthesis journal and interdisciplinary collaborative research. Coping with GEC is an enormous challenge and one the world must respond to successfully. Our common goal is, therefore, to develop the essential knowledge base needed to respond effectively and quickly to the great challenge of GEC.
Helene Muri - One of the best experts on this subject based on the ideXlab platform.
-
an overview of the Earth System Science of solar geoengineering
Wiley Interdisciplinary Reviews: Climate Change, 2016Co-Authors: Peter J. Irvine, Ben Kravitz, Mark Lawrence, Helene MuriAbstract:Solar geoengineering has been proposed as a means to cool the Earth by increasing the reflection of sunlight back to space, for example, by injecting reflective aerosol particles (or their precursors) into the lower stratosphere. Such proposed techniques would not be able to substitute for mitigation of greenhouse gas (GHG) emissions as a response to the risks of climate change, as they would only mask some of the effects of global warming. They might, however, eventually be applied as a complementary approach to reduce climate risks. Thus, the Earth System consequences of solar geoengineering are central to understanding its potentials and risks. Here we review the state-of-the-art knowledge about stratospheric sulfate aerosol injection and an idealized proxy for this, ‘sunshade geoengineering,’ in which the intensity of incoming sunlight is directly reduced in models. Studies are consistent in suggesting that sunshade geoengineering and stratospheric aerosol injection would generally offset the climate effects of elevated GHG concentrations. However, it is clear that a solar geoengineered climate would be novel in some respects, one example being a notably reduced hydrological cycle intensity. Moreover, we provide an overview of nonclimatic aspects of the response to stratospheric aerosol injection, for example, its effect on ozone, and the uncertainties around its consequences. We also consider the issues raised by the partial control over the climate that solar geoengineering would allow. Finally, this overview highlights some key research gaps in need of being resolved to provide sound basis for guidance of future decisions around solar geoengineering. WIREs Clim Change 2016, 7:815–833. doi: 10.1002/wcc.423 For further resources related to this article, please visit the WIREs website.
-
An overview of the Earth System Science of solar geoengineering: Overview of the Earth System Science of solar geoengineering
Wiley Interdisciplinary Reviews: Climate Change, 2016Co-Authors: Peter J. Irvine, Ben Kravitz, Mark Lawrence, Helene MuriAbstract:Solar geoengineering has been proposed as a means to cool the Earth by increasing the reflection of sunlight back to space, for example, by injecting reflective aerosol particles (or their precursors) into the lower stratosphere. Such proposed techniques would not be able to substitute for mitigation of greenhouse gas (GHG) emissions as a response to the risks of climate change, as they would only mask some of the effects of global warming. They might, however, eventually be applied as a complementary approach to reduce climate risks. Thus, the Earth System consequences of solar geoengineering are central to understanding its potentials and risks. Here we review the state-of-the-art knowledge about stratospheric sulfate aerosol injection and an idealized proxy for this, ‘sunshade geoengineering,’ in which the intensity of incoming sunlight is directly reduced in models. Studies are consistent in suggesting that sunshade geoengineering and stratospheric aerosol injection would generally offset the climate effects of elevated GHG concentrations. However, it is clear that a solar geoengineered climate would be novel in some respects, one example being a notably reduced hydrological cycle intensity. Moreover, we provide an overview of nonclimatic aspects of the response to stratospheric aerosol injection, for example, its effect on ozone, and the uncertainties around its consequences. We also consider the issues raised by the partial control over the climate that solar geoengineering would allow. Finally, this overview highlights some key research gaps in need of being resolved to provide sound basis for guidance of future decisions around solar geoengineering. WIREs Clim Change 2016, 7:815–833. doi: 10.1002/wcc.423 For further resources related to this article, please visit the WIREs website.
Rik Leemans - One of the best experts on this subject based on the ideXlab platform.
-
responding to complex societal challenges a decade of Earth System Science partnership essp interdisciplinary research
Current Opinion in Environmental Sustainability, 2012Co-Authors: Ada Ignaciuk, Rik Leemans, Josep G Canadell, John Ingram, Martin Rice, Janos J Bogardi, Shobhakar Dhakal, Mark W RosenbergAbstract:The Earth System is an integrated, self-regulating System under increasing pressure from anthropogenic transformation. The Earth System Science Partnership (ESSP), which was established by the international global environmental change research programs (i.e., DIVERSITAS, IGBP, IHDP and WCRP) facilitates the study of this System in order to understand how and why it is changing, and to explore the implications of these changes for global and regional sustainability. Crucial to this scientific enterprise are interdisciplinary Joint Projects on carbon, food, water and health. This paper analyses the scientific and institutional evolution of ESSP as a framework for interdisciplinary and integrative research of societal relevance. Case studies on food Systems, carbon budgets, water security and biodiversity conservation illustrate how these projects have advanced integrated Earth System knowledge. At the institutional level, we explain the transformation of the ESSP governance and how this has further enabled interdisciplinary research. The lessons learnt from ESSP research can contribute to the development of the next generation of Earth System Science for sustainability.
-
developing a common strategy for integrative global environmental change research and outreach the Earth System Science partnership essp
Current Opinion in Environmental Sustainability, 2009Co-Authors: Rik Leemans, Ghassem R Asrar, Antonio J Busalacchi, Josep G Canadell, John Ingram, Anne Larigauderie, H A Mooney, Carlos A Nobre, Anand Patwardhan, Martin RiceAbstract:The Earth System Science Partnership (ESSP) was established in 2001 by four global environmental change (GEC) research programmes: DIVERSITAS, IGBP, IHDP and WCRP. ESSP facilitates the study of the Earth's environment as an integrated System in order to understand how and why it is changing, and to explore the implications of these changes for global and regional sustainability. Joint research projects on carbon dynamics, food, water and health have been established. As a result of an independent review, the ESSP developed a new strategy that will provide an internationally coordinated and holistic approach to Earth System Science. The approach integrates natural and social Sciences from regional to the global scale. The mainstay of the ESSP is to identify and define Earth System Science challenges, enable integrative research to address these challenges, and build scientific capacity. The GEC research community also faces an increasing challenge to present research results in more accessible and informative ways to stakeholders, especially to policy-makers. In response, the ESSP is developing new services that include knowledge products, Earth System Science fora, a synthesis journal and interdisciplinary collaborative research. Coping with GEC is an enormous challenge and one the world must respond to successfully. Our common goal is, therefore, to develop the essential knowledge base needed to respond effectively and quickly to the great challenge of GEC.
