识别地球科学人工智能/ML 中的偏差并进行分类

IF 6.9 1区地球科学 Q1 METEOROLOGY & ATMOSPHERIC SCIENCES

Bulletin of the American Meteorological Society Pub Date : 2024-01-22 DOI:10.1175/bams-d-23-0196.1

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

{"title":"识别地球科学人工智能/ML 中的偏差并进行分类","authors":"Amy McGovern, Ann Bostrom, Marie McGraw, Randy J. Chase, David John Gagne, Imme Ebert-Uphoff, Kate D. Musgrave, Andrea Schumacher","doi":"10.1175/bams-d-23-0196.1","DOIUrl":null,"url":null,"abstract":"Abstract Artificial Intelligence (AI) can be used to improve performance across a wide range of Earth System prediction tasks. As with any application of AI, it is important for AI to be developed in an ethical and responsible manner to minimize bias and other effects. In this work, we extend our previous work demonstrating how AI can go wrong with weather and climate applications by presenting a categorization of bias for AI in the Earth Sciences. This categorization can assist AI developers to identify potential biases that can affect their model throughout the AI development life-cycle. We highlight examples from a variety of Earth System prediction tasks of each category of bias.","PeriodicalId":9464,"journal":{"name":"Bulletin of the American Meteorological Society","volume":"58 1","pages":""},"PeriodicalIF":6.9000,"publicationDate":"2024-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Identifying and Categorizing Bias in AI/ML for Earth Sciences\",\"authors\":\"Amy McGovern, Ann Bostrom, Marie McGraw, Randy J. Chase, David John Gagne, Imme Ebert-Uphoff, Kate D. Musgrave, Andrea Schumacher\",\"doi\":\"10.1175/bams-d-23-0196.1\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract Artificial Intelligence (AI) can be used to improve performance across a wide range of Earth System prediction tasks. As with any application of AI, it is important for AI to be developed in an ethical and responsible manner to minimize bias and other effects. In this work, we extend our previous work demonstrating how AI can go wrong with weather and climate applications by presenting a categorization of bias for AI in the Earth Sciences. This categorization can assist AI developers to identify potential biases that can affect their model throughout the AI development life-cycle. We highlight examples from a variety of Earth System prediction tasks of each category of bias.\",\"PeriodicalId\":9464,\"journal\":{\"name\":\"Bulletin of the American Meteorological Society\",\"volume\":\"58 1\",\"pages\":\"\"},\"PeriodicalIF\":6.9000,\"publicationDate\":\"2024-01-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Bulletin of the American Meteorological Society\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.1175/bams-d-23-0196.1\",\"RegionNum\":1,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"METEOROLOGY & ATMOSPHERIC SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bulletin of the American Meteorological Society","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1175/bams-d-23-0196.1","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"METEOROLOGY & ATMOSPHERIC SCIENCES","Score":null,"Total":0}

引用次数: 0

摘要

摘要人工智能（AI）可用于提高各种地球系统预测任务的性能。与人工智能的任何应用一样，重要的是要以道德和负责任的方式开发人工智能，以尽量减少偏见和其他影响。在这项工作中，我们通过对地球科学领域的人工智能偏差进行分类，扩展了之前的工作，展示了人工智能在天气和气候应用中可能出现的问题。这种分类可以帮助人工智能开发人员在整个人工智能开发生命周期中识别可能影响其模型的潜在偏差。我们重点介绍了地球系统预测任务中各类偏差的实例。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Identifying and Categorizing Bias in AI/ML for Earth Sciences

Abstract Artificial Intelligence (AI) can be used to improve performance across a wide range of Earth System prediction tasks. As with any application of AI, it is important for AI to be developed in an ethical and responsible manner to minimize bias and other effects. In this work, we extend our previous work demonstrating how AI can go wrong with weather and climate applications by presenting a categorization of bias for AI in the Earth Sciences. This categorization can assist AI developers to identify potential biases that can affect their model throughout the AI development life-cycle. We highlight examples from a variety of Earth System prediction tasks of each category of bias.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Bulletin of the American Meteorological Society 地学-气象与大气科学

CiteScore

9.80

自引率

6.20%

发文量

231

审稿时长

6-12 weeks

期刊介绍： The Bulletin of the American Meteorological Society (BAMS) is the flagship magazine of AMS and publishes articles of interest and significance for the weather, water, and climate community as well as news, editorials, and reviews for AMS members.