Search Results

You are looking at 1 - 10 of 714 items for :

  • Artificial intelligence x
  • Refine by Access: All Content x
Clear All
Amy McGovern
,
David John Gagne II
,
Christopher D. Wirz
,
Imme Ebert-Uphoff
,
Ann Bostrom
,
Yuhan Rao
,
Andrea Schumacher
,
Montgomery Flora
,
Randy Chase
,
Antonios Mamalakis
,
Marie McGraw
,
Ryan Lagerquist
,
Robert J. Redmon
, and
Taysia Peterson

The NSF AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography (AI2ES) recently held our second annual summer school on trustworthy artificial intelligence (AI) for the environmental sciences. We are an NSF-funded AI institute focused on creating trustworthy AI for a wide variety of atmospheric-, climate-, and ocean-related applications. The goal of this In Box article is to share the innovative approach we developed for the summer school in hopes that it

Open access
Elias C. Massoud
,
Forrest Hoffman
,
Zheng Shi
,
Jinyun Tang
,
Elie Alhajjar
,
Mallory Barnes
,
Renato K. Braghiere
,
Zoe Cardon
,
Nathan Collier
,
Octavia Crompton
,
P. James Dennedy-Frank
,
Sagar Gautam
,
Miquel A. Gonzalez-Meler
,
Julia K. Green
,
Charles Koven
,
Paul Levine
,
Natasha MacBean
,
Jiafu Mao
,
Richard Tran Mills
,
Umakant Mishra
,
Maruti Mudunuru
,
Alexandre A. Renchon
,
Sarah Scott
,
Erica R. Siirila-Woodburn
,
Matthias Sprenger
,
Christina Tague
,
Yaoping Wang
,
Chonggang Xu
, and
Claire Zarakas

processes required for modeling across scales. For biogeochemical cycles, the black arrows denote carbon fluxes, and the purple arrows denote nitrogen fluxes. SCF is snow cover fraction, BVOC indicates biogenic volatile organic compounds, and C/N is the carbon-to-nitrogen ratio. Artificial intelligence (AI) and machine learning (ML) approaches open up new possibilities for obtaining mechanistic insight from the diversity of data available at various scales. However, traditional hypothesis testing has

Open access
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
,
Sue Ellen Haupt
,
Kenneth S. Casey
,
Nikunj Oza
,
Alan J. Geer
,
Eric S. Maddy
, and
Ross N. Hoffman

The Earth and environmental sciences (collectively Earth science in what follows) stand to benefit from leveraging rapid advances in artificial intelligence (AI) from diverse applied science fields due to the combination of fast paced increases in data availability and computational capabilities. Leveraging algorithms used in other fields—what might be called meta-transfer learning—is accelerating the use of AI for environmental data and Earth system applications. We summarize here the main

Open access
Antonios Mamalakis
,
Elizabeth A. Barnes
, and
Imme Ebert-Uphoff

the application of CNNs in the geosciences is their black-box nature, which makes it hard for scientists to interpret predictions and to assess the model from a physical perspective, that is, beyond using prediction performance as the only criterion. The interpretability issue is considered a key issue for deep learning in general, and it has prompted the emergence of a new subfield in computer science, namely, explainable artificial intelligence (XAI; Buhrmester et al. 2019 ; Tjoa and Guan 2019

Free access
Fernando Jaume-Santero
,
David Barriopedro
,
Ricardo García-Herrera
, and
Jürg Luterbacher

information from climate datasets have recently emerged as promising tools to reconstruct spatial fields, while preserving major features of the variability ( Carro-Calvo et al. 2021 ; Kadow et al. 2020 ; Vaccaro et al. 2021 ). Joining statistics and computer science, artificial intelligence (AI) is a multidisciplinary field with different areas of expertise such as machine learning ( LeCun et al. 2015 ; Kadow et al. 2020 ), and optimization ( Swarnkar and Swarnkar 2019 ; Soto et al. 2019 ). Regarding

Full access
Amir Ouyed
,
Xubin Zeng
,
Longtao Wu
,
Derek Posselt
, and
Hui Su

Eq. ( 11 )]. Values were computed for 0000 UTC 1 Jan 2006, Δ t = 60 min, and P = 850 hPa. The structure of the error distribution also raises some questions about overfitting. In this study, we derived an error distribution, under the assumption of an available ground truth V truth . In an operational setting, we would not calculate the error ϵ = V NWP − V truth , since we will use the NWP field itself, e.g., V NWP = V truth + ϵ , rather than constructing an artificial V NWP

Full access
Chang-Hoi Ho
,
Donggyu Hyeon
,
Minhee Chang
,
Greg McFarquhar
, and
Seong-Hee Won

is a pressing need to establish an objective method to reduce such large errors. Therefore, this study aims to develop an algorithm that exclusively utilizes geostationary satellites that are accessible at all times, and addresses the operational constraints faced by the KMA. To achieve this goal, an artificial intelligence (AI) approach was implemented. This AI algorithm was designed to comprehend and analyze nonlinear variations in spatiotemporal domains related to TCs. In the next section

Open access
Amy McGovern
,
Ann Bostrom
,
Marie McGraw
,
Randy J. Chase
,
David John Gagne II
,
Imme Ebert-Uphoff
,
Kate D. Musgrave
, and
Andrea Schumacher

Applications of artificial intelligence (AI) and machine learning (ML) in the Earth sciences have grown exponentially over the past few years. We refer to AI/ML more generally as AI throughout the rest of the paper. It is critically important that AI developers create methods in an ethical and responsible manner lest AI be developed and deployed in a manner that could cause harm. In this work, we build on our earlier research ( McGovern et al. 2022 ), which demonstrated multiple ways where AI

Open access
Long Jin
,
Cai Yao
, and
Xiao-Yan Huang

recognized ( Nohara and Tanaka 2004 ; Zhou and Johnny 2006 ). At present, traditional mathematic modeling methods, such as multivariate analysis and time series analysis are widely used in statistical prediction and dynamical–statistical prediction ( Zhou and Huang 1997 ; Ding et al. 2002 ), in which the future state of a prediction object is forecasted using a statistical prediction equation ( Zhou and Huang 1997 ; Ding et al. 2002 ). With the development of the artificial intelligence technique

Full access
F. Vitart
,
A. W. Robertson
,
A. Spring
,
F. Pinault
,
R. Roškar
,
W. Cao
,
S. Bech
,
A. Bienkowski
,
N. Caltabiano
,
E. De Coning
,
B. Denis
,
A. Dirkson
,
J. Dramsch
,
P. Dueben
,
J. Gierschendorf
,
H. S. Kim
,
K. Nowak
,
D. Landry
,
L. Lledó
,
L. Palma
,
S. Rasp
, and
S. Zhou

skill and understanding on the S2S time scale, the World Weather Research Programme (WWRP) and World Climate Research Programme (WCRP) launched the Subseasonal to Seasonal Prediction Project (S2S) ( Vitart et al. 2015 ) in November 2013. Artificial intelligence (AI) can potentially improve S2S predictions because of its potential to explore very large multimodel forecast and observed datasets more agnostically, to discover emergent patterns in the data (e.g., Weyn et al. 2021 ), instead of first

Free access