Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313893684> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4313893684 abstract "Abstract Neural networks (NN) have become an important tool for prediction tasks—both regression and classification—in environmental science. Since many environmental-science problems involve life-or-death decisions and policy making, it is crucial to provide not only predictions but also an estimate of the uncertainty in the predictions. Until recently, very few tools were available to provide uncertainty quantification (UQ) for NN predictions. However, in recent years the computer-science field has developed numerous UQ approaches, and several research groups are exploring how to apply these approaches in environmental science. We provide an accessible introduction to six of these UQ approaches, then focus on tools for the next step, namely, to answer the question: Once we obtain an uncertainty estimate (using any approach), how do we know whether it is good or bad? To answer this question, we highlight four evaluation graphics and eight evaluation scores that are well suited for evaluating and comparing uncertainty estimates (NN based or otherwise) for environmental-science applications. We demonstrate the UQ approaches and UQ-evaluation methods for two real-world problems: 1) estimating vertical profiles of atmospheric dewpoint (a regression task) and 2) predicting convection over Taiwan based on Himawari-8 satellite imagery (a classification task). We also provide Jupyter notebooks with Python code for implementing the UQ approaches and UQ-evaluation methods discussed herein. This article provides the environmental-science community with the knowledge and tools to start incorporating the large number of emerging UQ methods into their research. Significance Statement Neural networks are used for many environmental-science applications, some involving life-or-death decision-making. In recent years new methods have been developed to provide much-needed uncertainty estimates for NN predictions. We seek to accelerate the adoption of these methods in the environmental-science community with an accessible introduction to 1) methods for computing uncertainty estimates in NN predictions and 2) methods for evaluating such estimates." @default.
- W4313893684 created "2023-01-10" @default.
- W4313893684 creator A5017837598 @default.
- W4313893684 creator A5049880907 @default.
- W4313893684 creator A5055751078 @default.
- W4313893684 creator A5082309905 @default.
- W4313893684 creator A5091139186 @default.
- W4313893684 date "2023-04-01" @default.
- W4313893684 modified "2023-10-07" @default.
- W4313893684 title "Creating and Evaluating Uncertainty Estimates with Neural Networks for Environmental-Science Applications" @default.
- W4313893684 doi "https://doi.org/10.1175/aies-d-22-0061.1" @default.
- W4313893684 hasPublicationYear "2023" @default.
- W4313893684 type Work @default.
- W4313893684 citedByCount "0" @default.
- W4313893684 crossrefType "journal-article" @default.
- W4313893684 hasAuthorship W4313893684A5017837598 @default.
- W4313893684 hasAuthorship W4313893684A5049880907 @default.
- W4313893684 hasAuthorship W4313893684A5055751078 @default.
- W4313893684 hasAuthorship W4313893684A5082309905 @default.
- W4313893684 hasAuthorship W4313893684A5091139186 @default.
- W4313893684 hasBestOaLocation W43138936841 @default.
- W4313893684 hasConcept C111919701 @default.
- W4313893684 hasConcept C119857082 @default.
- W4313893684 hasConcept C154945302 @default.
- W4313893684 hasConcept C177803969 @default.
- W4313893684 hasConcept C202444582 @default.
- W4313893684 hasConcept C2522767166 @default.
- W4313893684 hasConcept C32230216 @default.
- W4313893684 hasConcept C33923547 @default.
- W4313893684 hasConcept C41008148 @default.
- W4313893684 hasConcept C44154836 @default.
- W4313893684 hasConcept C50644808 @default.
- W4313893684 hasConcept C519991488 @default.
- W4313893684 hasConcept C9652623 @default.
- W4313893684 hasConceptScore W4313893684C111919701 @default.
- W4313893684 hasConceptScore W4313893684C119857082 @default.
- W4313893684 hasConceptScore W4313893684C154945302 @default.
- W4313893684 hasConceptScore W4313893684C177803969 @default.
- W4313893684 hasConceptScore W4313893684C202444582 @default.
- W4313893684 hasConceptScore W4313893684C2522767166 @default.
- W4313893684 hasConceptScore W4313893684C32230216 @default.
- W4313893684 hasConceptScore W4313893684C33923547 @default.
- W4313893684 hasConceptScore W4313893684C41008148 @default.
- W4313893684 hasConceptScore W4313893684C44154836 @default.
- W4313893684 hasConceptScore W4313893684C50644808 @default.
- W4313893684 hasConceptScore W4313893684C519991488 @default.
- W4313893684 hasConceptScore W4313893684C9652623 @default.
- W4313893684 hasFunder F4320306076 @default.
- W4313893684 hasFunder F4320332181 @default.
- W4313893684 hasIssue "2" @default.
- W4313893684 hasLocation W43138936841 @default.
- W4313893684 hasOpenAccess W4313893684 @default.
- W4313893684 hasPrimaryLocation W43138936841 @default.
- W4313893684 hasRelatedWork W2280383998 @default.
- W4313893684 hasRelatedWork W2891993883 @default.
- W4313893684 hasRelatedWork W2979801952 @default.
- W4313893684 hasRelatedWork W4285815787 @default.
- W4313893684 hasRelatedWork W4288754364 @default.
- W4313893684 hasRelatedWork W4308734192 @default.
- W4313893684 hasRelatedWork W4312812851 @default.
- W4313893684 hasRelatedWork W4312831135 @default.
- W4313893684 hasRelatedWork W4312949351 @default.
- W4313893684 hasRelatedWork W1629725936 @default.
- W4313893684 hasVolume "2" @default.
- W4313893684 isParatext "false" @default.
- W4313893684 isRetracted "false" @default.
- W4313893684 workType "article" @default.