SAE-Xplainers：面向极端地球事件的基于规则的特征解释器
SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events
浏览论文内容
中文总结 AI 辅助
针对极端地球事件分析中SAE模型可解释性不足的问题，提出基于地理位置调制输入的SAE及规则型SAE-Xplainers集成模型，在火灾预测等三类任务上验证了其性能与解释能力。
中文摘要 AI 辅助
大规模天气与气候（W&C）数据集的出现，为使用深度学习建模极端地球事件（ExEE）及其影响提供了新机遇。然而，由于模型可解释性的缺失，这些数据集在业务场景中的应用仍然有限。对于传统的文本和图像模态，稀疏自编码器（SAE）等工具已被证明能有效提取人类可理解的概念，但由于天气与气候数据的特性，将其用于极端地球事件分析仍具挑战性。为解决该问题，本文提出两项改进：一是对SAE输入进行基于地理位置的调制，以捕捉环境模式的局部语义含义；二是构建基于规则的SAE-Xplainers集成模型，用于解释由复杂多模态环境预测因子衍生的高维特征。我们在三类极端地球事件上评估了所提方法：火灾预测、热带气旋检测及大气河流检测。结果表明，SAE输入调制可同时提升重构性能与特征利用率，且SAE-Xplainers能将复杂气候模式拆解为符合科学文献的人类可理解规则，实现可靠解释，同时支持特征吸收的识别。
英文摘要
The emergence of large-scale Weather and Climate (W&C) datasets offers new opportunities for modeling extreme Earth events (ExEE) and their impacts using deep learning. However, their adoption in operational settings remains limited by the lack of models' interpretability. While for conventional text and image modalities, tools such as Sparse Autoencoders (SAEs) have proven effective for extracting human-understandable concepts, their use for the analysis of ExEE remains challenging due to the nature of W&C data. To address this, we introduce (i) a geographic location-based modulation of the inputs of SAE to capture the local semantic meaning of environmental patterns, and (ii) an ensemble of rule-based SAE-Xplainers to interpret the resulting high-dimensional features derived from complex, multi-modal environmental predictors. We evaluate our method on three ExEE types: the prediction of fires, and the detection of tropical cyclones and atmospheric rivers. We show that SAE input modulation improves both reconstruction performance and feature utilization, and that our SAE-Xplainers enable faithful interpretation of complex climatic patterns by unfolding them into human-understandable rules that are consistent with the scientific literature, while also supporting the identification of feature absorption.
