Carefully Choose the Baseline: Lessons Learned from Applying XAI Attribution Methods for Regression Tasks in Geoscience
Carefully Choose the Baseline: Lessons Learned from Applying XAI Attribution Methods for Regression Tasks in Geoscience
复制标题
仔细选择基准：将 XAI 归因方法应用于地球科学回归任务的经验教训
DOI：
10.1175/aies-d-22-0058.1
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Ebert-Uphoff, Imme
中科院分区：
文献类型：
--
作者：
Mamalakis, Antonios;Barnes, Elizabeth A.;Ebert-Uphoff, Imme
可解释人工智能（XAI）方法用于地球科学应用，以深入了解神经网络（NN）的决策策略，突出输入中的哪些特征对NN预测贡献最大。在这里，我们讨论我们的“经验教训”，即将预测归因于输入的任务没有单一的解决方案。相反，归因结果在很大程度上取决于XAI方法所使用的基准线，这一事实在地球科学文献中被忽视了。基线是一个参考点，与预测进行比较，以便可以理解预测。这个基线可以由用户选择，也可以在方法的算法中通过构造来设置，通常用户并不知道这个选择。我们强调，不同的基线可以导致不同的科学问题的不同见解，因此，应该相应地选择。为了说明基线的影响，我们使用了一个大型的历史和未来气候模拟集合，强制使用共享的社会经济途径3-7.0（SSP 3 -7.0）情景，并训练了一个完全连接的NN来预测集合和全球平均温度（即，强迫全球变暖信号）给出来自单个集合成员的年度温度图。然后，我们使用各种XAI方法和不同的基线将网络预测归因于输入。我们表明，归因在考虑不同的基线时有很大的不同，因为它们对应于回答不同的科学问题。最后，我们讨论了重要的影响和考虑使用基线在XAI research.Significance StatementIn近年来，可解释的人工智能（XAI）的方法已经发现了很大的应用在地球科学的应用，因为它们可以用来属性的神经网络（NN）的预测输入和物理解释它们。在这里，我们强调的属性和物理解释很大程度上取决于基线的选择，一个事实，已被忽视的地球科学文献。我们举例说明了一个特定气候任务的这种依赖性，在这个任务中，神经网络被训练来预测集合和全球平均温度（即，强迫全球变暖信号）给出来自单个集合成员的年度温度图。我们表明，归因在考虑不同的基线时有很大的不同，因为它们对应于回答不同的科学问题。
Methods of explainable artificial intelligence (XAI) are used in geoscientific applications to gain insights into the decision-making strategy of neural networks (NNs), highlighting which features in the input contribute the most to a NN prediction. Here, we discuss our “lesson learned” that the task of attributing a prediction to the input does not have a single solution. Instead, the attribution results depend greatly on the considered baseline that the XAI method utilizes—a fact that has been overlooked in the geoscientific literature. The baseline is a reference point to which the prediction is compared so that the prediction can be understood. This baseline can be chosen by the user or is set by construction in the method’s algorithm—often without the user being aware of that choice. We highlight that different baselines can lead to different insights for different science questions and, thus, should be chosen accordingly. To illustrate the impact of the baseline, we use a large ensemble of historical and future climate simulations forced with the shared socioeconomic pathway 3-7.0 (SSP3-7.0) scenario and train a fully connected NN to predict the ensemble- and global-mean temperature (i.e., the forced global warming signal) given an annual temperature map from an individual ensemble member. We then use various XAI methods and different baselines to attribute the network predictions to the input. We show that attributions differ substantially when considering different baselines, because they correspond to answering different science questions. We conclude by discussing important implications and considerations about the use of baselines in XAI research.Significance StatementIn recent years, methods of explainable artificial intelligence (XAI) have found great application in geoscientific applications, because they can be used to attribute the predictions of neural networks (NNs) to the input and interpret them physically. Here, we highlight that the attributions—and the physical interpretation—depend greatly on the choice of the baseline—a fact that has been overlooked in the geoscientific literature. We illustrate this dependence for a specific climate task, in which a NN is trained to predict the ensemble- and global-mean temperature (i.e., the forced global warming signal) given an annual temperature map from an individual ensemble member. We show that attributions differ substantially when considering different baselines, because they correspond to answering different science questions.