16,938 Hits in 5.7 sec

Assessing the Potential of Deep Learning for Emulating Cloud Superparameterization in Climate Models With Real‐Geography Boundary Conditions

Griffin Mooers, Michael Pritchard, Tom Beucler, Jordan Ott, Galen Yacalis, Pierre Baldi, Pierre Gentine
2021 Journal of Advances in Modeling Earth Systems  
offline fits to data from the superparameterized community atmospheric model.  ...  accurate emulation and hopefully quick implementation of hybrid climate models.  ...  concept for hybrid climate models powered by machine learning.  ... 
doi:10.1029/2020ms002385 fatcat:vpverrmiqjcflgcs25i6ze4xla

Outlook for Exploiting Artificial Intelligence in the Earth and Environmental Sciences*

Sid-Ahmed Boukabara, Vladimir Krasnopolsky, Stephen G. Penny, Jebb Q. Stewart, Amy McGovern, David Hall, John E. Ten Hoeve, Jason Hickey, Hung-Lung Allen Huang, John K. Williams, Kayo Ide, Philippe Tissot (+6 others)
2020 Bulletin of The American Meteorological Society - (BAMS)  
Capsule Summary Current research applying artificial intelligence to the Earth and environmental sciences is progressing quickly, with emerging developments in terms of efficiency, accuracy, and discovery  ...  Grateful acknowledgement is made for funding and support provided by NOAA for the AI workshop and for several of the authors. NCAR is sponsored by the National Science Foundation.  ...  SGP acknowledges support from NOAA NGGPS (NA18NWS4680048), ONR (N00014-19-1-2522), and NOAA NESDIS.  ... 
doi:10.1175/bams-d-20-0031.1 fatcat:2wcohkjb2bb4nhmfteu2brydme

HESS Opinions: Incubating deep-learning-powered hydrologic science advances as a community

Chaopeng Shen, Eric Laloy, Amin Elshorbagy, Adrian Albert, Jerad Bales, Fi-John Chang, Sangram Ganguly, Kuo-Lin Hsu, Daniel Kifer, Zheng Fang, Kuai Fang, Dongfeng Li (+2 others)
2018 Hydrology and Earth System Sciences  
Interrogative methods are then invoked to interpret DL models for scientists to further evaluate.  ...  </strong> Recently, deep learning (DL) has emerged as a revolutionary and versatile tool transforming industry applications and generating new and improved capabilities for scientific discovery and model  ...  from deep networks to interpretable, reduced-order models; and (iii) visualization of network activations.  ... 
doi:10.5194/hess-22-5639-2018 fatcat:hy2y6srekjc7bpeyczna2xlwzi

The History and Practice of AI in the Environmental Sciences

2021 Bulletin of The American Meteorological Society - (BAMS)  
While AI methods have changed from expert systems in the eighties to neural networks and other data-driven methods, and more recently deep learning, the environmental problems tackled have remained similar  ...  We finish with a look at where AI as employed in environmental science appears to be headed and some thoughts on how it might be best blended with physical / dynamical modeling approaches to further advance  ...  in new hybrid NWP models.  ... 
doi:10.1175/bams-d-20-0234.1 fatcat:cdt6q5qotjebljinavjlwdrpva

Paradigm Shift Through the Integration of Physical Methodology and Data Science [article]

Takashi Miyamoto
2021 arXiv   pre-print
scientific methodologies while revealing unprecedented challenges such as the interpretability of computations and the demand for extrapolative predictions on the amount of data.  ...  Data science methodologies, which have undergone significant developments recently, provide flexible representational performance and fast computational means to address the challenges faced by traditional  ...  Acknowledgment The author would like to express my gratitude to Dr. Marlon Nuske in German Research Center for Artificial Intelligence for his suggestive advice.  ... 
arXiv:2110.01408v1 fatcat:jndzsb3krja7bhearq75tog2xy

Artificial Intelligence, Chaos, Prediction and Understanding in Science [article]

Miguel A. F. Sanjuan
2020 arXiv   pre-print
Machine learning and deep learning techniques are contributing much to the advancement of science.  ...  Furthermore, it is emphasized the important role played by that nonlinear dynamical systems for the process of understanding.  ...  Precisely one of the challenges they establish for deep learning methods is the need for understanding and for what they call interpretability, and causal discovery from observational data.  ... 
arXiv:2003.01771v2 fatcat:ntqr2e5swnepzoserktody6dya

DOE Computational Science Graduate Fellowship Research Showcase

Jaydeep Bardhan, Mary Ann Leung, Eileen Martin, Amanda Randles
2021 Computing in science & engineering (Print)  
These are two key issues in climate science, which must be managed even as the community continually refines earth system model codes to add new physical processes, incorporate algorithmic advances, and  ...  for interpretation).  ... 
doi:10.1109/mcse.2021.3124033 fatcat:kw3gvcwhjfeyplwa7kj76x4dci

An Overview of Technological Revolution in Satellite Image Analysis

Aroma R. Jenice, Department of Computer Science & Engineering, Karuny a University, Coimbatore, India, Kumudha Raimond, Department of Computer Science & Engineering, Karuny a University, Coimbatore, India
2016 Journal of Engineering Science and Technology Review  
And it leads to increased research efforts on designing intelligent assessment models using more advanced machine learning (ML) schemes for better satellite image interpretation.  ...  This paper focuses on bringing a clear understanding on satellite image interpretation methods right from the traditional statistical models to the more recent ML methods through stating the gradual revolution  ...  Few more hybrid models for satellite image interpretation have been tabulated below in the following Tab. 2.  ... 
doi:10.25103/jestr.094.01 fatcat:yvt73z7furhenmrjov6dgnkxom

The Science to Save Us from Philosophy of Science

Ahti-Veikko J. Pietarinen
2014 Axiomathes  
Far from rendering science irrational, I conclude that catering well for the right conditions in which to cultivate ignorance is a key to how fertile retroductive inferences (true guesses) can arise.  ...  A scientist, never frightened of unknown unknowns, strives to advance the forefront of uncertainty, not that of belief or knowledge.  ...  Earth Sciences & Astronomy: Geographical abduction in geoinformatics (e.g., crime prevention and analysis); Geophysical image interpretation (e.g., determining shapes of asteroids and other small objects  ... 
doi:10.1007/s10516-014-9261-8 fatcat:hevn3bmbbfchzkesw3o6knx6ty

Congressional Science Fellow: Report from D.C

Rafael D. Sagarin
2003 GSA Today  
Acknowledgments The authors are indebted to the following persons and institutions: The Division of Rare and Manuscript Collections, Kroch Library, and the Department of Earth and Atmospheric Sciences,  ...  Paul Getty Museum; and to the known and anonymous reviewers of the manuscript. For references, please contact Brice.  ...  Applicants should have an advanced degree in earth science, and at least five years relevant professional experience.  ... 
doi:10.1130/1052-5173(2003)013<0025:csfrfd>;2 fatcat:a6twtcizffci3ojtv6ktxdgs24

Data-driven modeling and learning in science and engineering

Francisco J. Montáns, Francisco Chinesta, Rafael Gómez-Bombarelli, J. Nathan Kutz
2019 Comptes rendus. Mecanique  
In this paper we review the application of data-driven modeling and model learning procedures to different fields in science and engineering.  ...  Some scientific fields have been using artificial intelligence for some time due to the inherent difficulty in obtaining laws and equations to describe some phenomena.  ...  JNK acknowledges support from the Air Force Office of Scientific Research (AFOSR) grant FA9550-17-1-0329.  ... 
doi:10.1016/j.crme.2019.11.009 fatcat:7rtlth7ncreqthugtduxtzjpky

Impact of Integrated Science and Mathematics Instruction on Middle School Science and Mathematics Achievement [chapter]

Zenaida Aguirre-Muñoz, Brian Dang, Elias S. Loria Garro
2022 Advances in Research in STEM Education [Working Title]  
Despite the impetus from professional organizations for science and math integration, evidence in support of such efforts in raising both science and mathematics achievement is scarce, particularly for  ...  Multiple regression results indicated that (MS)2 group membership and opportunity to learn through integrated instruction were significant predictors of students' science and mathematics scores.  ...  ., [33, 34] ) with K-R20 coefficients ranging from 0.87 to 0.933 for the mathematics and 0.90 for science batteries.  ... 
doi:10.5772/intechopen.104082 fatcat:cxxqggtgmbc7tfwtqsjqta527m

Man, machine, scientific models and creation science

Steven Gollmer
2018 The Proceedings of the International Conference on Creationism  
In addition, advancements in machine learning tend to blur the lines between human insight and computational power.  ...  Historically, physics was the most quantitative of the sciences. Geologists and biologists built their models based on observation, categorization and generalization.  ...  My colleagues in the Department of Science and Mathematics and participants in the Data Science Seminar Series provided much food for thought.  ... 
doi:10.15385/jpicc.2018.8.1.13 fatcat:ow5dtw3kgfa4jdbatlem7abkza

Sustainability Science: A Paradigm in Crisis?

Iván González-Márquez, Víctor M. Toledo
2020 Sustainability  
This paper addresses this question taking into consideration some insights from the philosophy of science.  ...  Subsequently, the way forward for SS is discussed.  ...  Kuhn's model of scientific progress. Figure 1 . 1 Figure 1. Kuhn's model of scientific progress. Figure 2 . 2 Figure 2. Hybrid disciplines. Modified from [32].Figure 2. Hybrid disciplines.  ... 
doi:10.3390/su12072802 doaj:d202976493d44d5292b4f44a901dde71 fatcat:v7tksutmarh4bbgjtv6vsme56m

Applications of physics-informed scientific machine learning in subsurface science: A survey [article]

Alexander Y. Sun, Hongkyu Yoon, Chung-Yan Shih, Zhi Zhong
2021 arXiv   pre-print
Fast advances in machine learning (ML) algorithms and novel sensing technologies in recent years have presented new opportunities for the subsurface research community to improve the efficacy and transparency  ...  Although recent studies have shown the great promise of scientific ML (SciML) models, questions remain on how to best leverage ML in the management of geosystems, which are typified by multiscality, high-dimensionality  ...  Department of Energy, National Energy Technology Laboratory (NETL) under grants DE-FE0026515, DE-FE0031544, and the Scienceinformed Machine Learning for Accelerating Real-Time Decisions in Subsurface Applications  ... 
arXiv:2104.04764v2 fatcat:h2vx3gn2snc6th23x5bylahy6i
« Previous Showing results 1 — 15 out of 16,938 results