Advancing interpretability of machine-learning prediction models

Advancing interpretability of machine-learning prediction models
复制标题

提高机器学习预测模型的可解释性

DOI:
10.1017/eds.2022.13
复制
发表时间:
2022
期刊:
Environmental Data Science
影响因子:
--
通讯作者:
DelSole, Timothy
DelSole, Timothy
中科院分区:
--
文献类型:
--
作者:
Trenary, Laurie;DelSole, Timothy

文献摘要

参考文献

相似文献

本文提出了一种诊断机器学习预测模型技能的方法,该方法基于寻找最小化预测归一化均方误差的变量组合。该技术很有吸引力,因为它将预测模型的积极技能压缩为最少数量的组件。然后可以像主成分一样对所得成分进行分析,包括构建用于调查技能来源的回归图。该技术通过机器学习模型对美国西部冬季地表温度第 3-4 周的预测进行了说明。该技术揭示了至少两种被巧妙预测的大规模温度变化模式。这些模式的可预测性在气候模型模拟和观测之间通常是一致的。可预测性很大程度上取决于太平洋海面温度的变化,特别是与厄尔尼诺-南方涛动相关的地区。这个结果并不令人惊讶,但它从该技术中自然出现的事实表明该技术有助于“解释”机器学习模型中可预测性的来源。
This paper proposes an approach to diagnosing the skill of a machine-learning prediction model based on finding combinations of variables that minimize the normalized mean square error of the predictions. This technique is attractive because it compresses the positive skill of a forecast model into the smallest number of components. The resulting components can then be analyzed much like principal components, including the construction of regression maps for investigating sources of skill. The technique is illustrated with a machine-learning model of week 3–4 predictions of western US wintertime surface temperatures. The technique reveals at least two patterns of large-scale temperature variations that are skillfully predicted. The predictability of these patterns is generally consistent between climate model simulations and observations. The predictability is determined largely by sea surface temperature variations in the Pacific, particularly the region associated with the El Nino-Southern Oscillation. This result is not surprising, but the fact that it emerges naturally from the technique demonstrates that the technique can be helpful in “explaining” the source of predictability in machine-learning models.
DOI: 10.1017/eds.2023.2
发表时间: 2023-02
期刊: Environmental Data Science
影响因子: --
作者:
L. Trenary;T. DelSole
通讯作者: L. Trenary;T. DelSole
DOI: 10.1029/2019ms002002
发表时间: 2019-12
影响因子: 6.8
作者:
B. Toms;E. Barnes;I. Ebert‐Uphoff
通讯作者: B. Toms;E. Barnes;I. Ebert‐Uphoff
DOI: 10.1175/mwr-d-18-0316.1
发表时间: 2019-08-01
影响因子: 3.2
作者:
Gagne, David John, II;Haupt, Sue Ellen;Thompson, Gregory
通讯作者: Thompson, Gregory
气候科学家的统计方法
DOI: --
发表时间: 2022
期刊:
影响因子: --
作者:
T. DelSole;M. Tippett
通讯作者: M. Tippett
DOI: 10.5194/gmd-9-1937-2016
发表时间: 2016-01-01
影响因子: 5.1
作者:
Eyring, Veronika;Bony, Sandrine;Taylor, Karl E.
通讯作者: Taylor, Karl E.