XAI中有多少X:在水文和水资源领域负责任地使用 "可解释 "人工智能

IF 3.1 Q2 GEOSCIENCES, MULTIDISCIPLINARY
Holger Robert Maier , Firouzeh Rosa Taghikhah , Ehsan Nabavi , Saman Razavi , Hoshin Gupta , Wenyan Wu , Douglas A.G. Radford , Jiajia Huang
{"title":"XAI中有多少X:在水文和水资源领域负责任地使用 \"可解释 \"人工智能","authors":"Holger Robert Maier ,&nbsp;Firouzeh Rosa Taghikhah ,&nbsp;Ehsan Nabavi ,&nbsp;Saman Razavi ,&nbsp;Hoshin Gupta ,&nbsp;Wenyan Wu ,&nbsp;Douglas A.G. Radford ,&nbsp;Jiajia Huang","doi":"10.1016/j.hydroa.2024.100185","DOIUrl":null,"url":null,"abstract":"<div><p>Explainable Artificial Intelligence (XAI) offers the promise of being able to provide additional insight into complex hydrological problems. As the “<em>new kid on the block</em>”, these methods are embraced enthusiastically and often viewed as offering something radically new and different. However, upon closer inspection, many XAI approaches are very similar to more “<em>traditional</em>” methods of “<em>interrogating</em>” existing models, such as sensitivity or break-even analysis. In fact, the approach of developing data-driven models to obtain a better understanding of hydrological processes to inform the development of more physics-based models is as old as hydrology itself. Consequently, rather than being considered a new approach, XAI should be viewed as part of a long-standing tradition, and XAI methods part of an ever-expanding hydrological modelling toolkit, rather than a silver bullet. Critically, there needs to be shift from focusing on how to best <em>eXplain</em> what AI models have learnt (i.e., the X component of XAI) to developing models that are able to capture relationships that are contained within the data in a robust and reliable fashion (i.e., the AI component of XAI), as there is little value in explaining AI-derived relationships if these do not reflect underlying hydrological processes. However, this is often not the case due to a focus on maximising the predictive ability of AI models “<em>at all costs</em>”, not uncommonly resulting in large models that often have thousands or even millions of parameters that are not well defined. Consequently, these models generally <em>do not</em> capture underlying hydrological processes in a robust and reliable fashion. Finally, there is also a need to stop thinking about XAI as a purely technical approach, but a socio-technical approach that views XAI as a process that can assist with solving problems that are situated within broader social and political contexts.</p></div>","PeriodicalId":36948,"journal":{"name":"Journal of Hydrology X","volume":null,"pages":null},"PeriodicalIF":3.1000,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589915524000154/pdfft?md5=a863cf9a0b87f3655a76e2ff3d7113af&pid=1-s2.0-S2589915524000154-main.pdf","citationCount":"0","resultStr":"{\"title\":\"How much X is in XAI: Responsible use of “Explainable” artificial intelligence in hydrology and water resources\",\"authors\":\"Holger Robert Maier ,&nbsp;Firouzeh Rosa Taghikhah ,&nbsp;Ehsan Nabavi ,&nbsp;Saman Razavi ,&nbsp;Hoshin Gupta ,&nbsp;Wenyan Wu ,&nbsp;Douglas A.G. Radford ,&nbsp;Jiajia Huang\",\"doi\":\"10.1016/j.hydroa.2024.100185\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Explainable Artificial Intelligence (XAI) offers the promise of being able to provide additional insight into complex hydrological problems. As the “<em>new kid on the block</em>”, these methods are embraced enthusiastically and often viewed as offering something radically new and different. However, upon closer inspection, many XAI approaches are very similar to more “<em>traditional</em>” methods of “<em>interrogating</em>” existing models, such as sensitivity or break-even analysis. In fact, the approach of developing data-driven models to obtain a better understanding of hydrological processes to inform the development of more physics-based models is as old as hydrology itself. Consequently, rather than being considered a new approach, XAI should be viewed as part of a long-standing tradition, and XAI methods part of an ever-expanding hydrological modelling toolkit, rather than a silver bullet. Critically, there needs to be shift from focusing on how to best <em>eXplain</em> what AI models have learnt (i.e., the X component of XAI) to developing models that are able to capture relationships that are contained within the data in a robust and reliable fashion (i.e., the AI component of XAI), as there is little value in explaining AI-derived relationships if these do not reflect underlying hydrological processes. However, this is often not the case due to a focus on maximising the predictive ability of AI models “<em>at all costs</em>”, not uncommonly resulting in large models that often have thousands or even millions of parameters that are not well defined. Consequently, these models generally <em>do not</em> capture underlying hydrological processes in a robust and reliable fashion. Finally, there is also a need to stop thinking about XAI as a purely technical approach, but a socio-technical approach that views XAI as a process that can assist with solving problems that are situated within broader social and political contexts.</p></div>\",\"PeriodicalId\":36948,\"journal\":{\"name\":\"Journal of Hydrology X\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.1000,\"publicationDate\":\"2024-09-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2589915524000154/pdfft?md5=a863cf9a0b87f3655a76e2ff3d7113af&pid=1-s2.0-S2589915524000154-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Hydrology X\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2589915524000154\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"GEOSCIENCES, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Hydrology X","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2589915524000154","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

摘要

可解释人工智能(XAI)有望为复杂的水文问题提供更多洞察力。作为 "新生事物",这些方法受到热烈欢迎,往往被视为提供了全新的、与众不同的东西。然而,仔细观察,许多 XAI 方法与 "询问 "现有模型的更 "传统 "的方法非常相似,例如灵敏度或盈亏平衡分析。事实上,开发数据驱动模型以更好地了解水文过程,从而为开发更多基于物理的模型提供信息的方法与水文学本身一样古老。因此,XAI 不应被视为一种新方法,而应被视为悠久传统的一部分,XAI 方法是不断扩展的水文建模工具包的一部分,而不是灵丹妙药。至关重要的是,需要从关注如何最好地解释人工智能模型所学到的知识(即 XAI 的 X 部分),转向开发能够以稳健可靠的方式捕捉数据中包含的关系的模型(即 XAI 的人工智能部分),因为如果人工智能得出的关系不能反映潜在的水文过程,那么解释这些关系就没有什么价值。然而,由于 "不惜一切代价 "将人工智能模型的预测能力最大化作为重点,这往往会导致大型模型中往往有数千甚至数百万个未明确定义的参数。因此,这些模型通常无法以稳健可靠的方式捕捉潜在的水文过程。最后,还需要停止将 XAI 视为一种纯粹的技术方法,而应将其视为一种社会技术方法,将 XAI 视为一种可协助解决更广泛的社会和政治背景下的问题的过程。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
How much X is in XAI: Responsible use of “Explainable” artificial intelligence in hydrology and water resources

Explainable Artificial Intelligence (XAI) offers the promise of being able to provide additional insight into complex hydrological problems. As the “new kid on the block”, these methods are embraced enthusiastically and often viewed as offering something radically new and different. However, upon closer inspection, many XAI approaches are very similar to more “traditional” methods of “interrogating” existing models, such as sensitivity or break-even analysis. In fact, the approach of developing data-driven models to obtain a better understanding of hydrological processes to inform the development of more physics-based models is as old as hydrology itself. Consequently, rather than being considered a new approach, XAI should be viewed as part of a long-standing tradition, and XAI methods part of an ever-expanding hydrological modelling toolkit, rather than a silver bullet. Critically, there needs to be shift from focusing on how to best eXplain what AI models have learnt (i.e., the X component of XAI) to developing models that are able to capture relationships that are contained within the data in a robust and reliable fashion (i.e., the AI component of XAI), as there is little value in explaining AI-derived relationships if these do not reflect underlying hydrological processes. However, this is often not the case due to a focus on maximising the predictive ability of AI models “at all costs”, not uncommonly resulting in large models that often have thousands or even millions of parameters that are not well defined. Consequently, these models generally do not capture underlying hydrological processes in a robust and reliable fashion. Finally, there is also a need to stop thinking about XAI as a purely technical approach, but a socio-technical approach that views XAI as a process that can assist with solving problems that are situated within broader social and political contexts.

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
Journal of Hydrology X
Journal of Hydrology X Environmental Science-Water Science and Technology
CiteScore
7.00
自引率
2.50%
发文量
20
审稿时长
25 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信