Layer-wise relevance propagation (LRP) is a widely used and powerful technique to reveal insights into various artificial neural network (ANN) architectures. LRP is often used in the context of image classification. The aim is to understand, which parts of the input sample have highest relevance and hence most influence on the model prediction. Relevance can be traced back through the network to attribute a certain score to each input pixel. Relevance scores are then combined and displayed as heat maps and give humans an intuitive visual understanding of classification models. Opening the black box to understand the classification engine in great detail is essential for domain experts to gain trust in ANN models. However, there are pitfalls in terms of model-inherent artifacts included in the obtained relevance maps, that can easily be missed. But for a valid interpretation, these artifacts must not be ignored. Here, we apply and revise LRP on various ANN architectures trained as classifiers on geospatial and synthetic data. Depending on the network architecture, we show techniques to control model focus and give guidance to improve the quality of obtained relevance maps to separate facts from artifacts.

翻译：层级相关性传播（LRP）是一种广泛使用且功能强大的技术，用于揭示多种人工神经网络（ANN）架构的内在机制。LRP常用于图像分类领域，其目标是理解输入样本的哪些部分具有最高相关性，从而对模型预测产生最大影响。通过反向追溯网络中的相关性，可为每个输入像素分配特定得分。这些相关性得分随后被组合并以热力图形式呈现，为人类提供对分类模型的直观视觉理解。打开“黑箱”以深入理解分类引擎的运作细节，对于领域专家建立对ANN模型的信任至关重要。然而，相关性图中可能包含模型固有的伪影，这些伪影容易被忽视，但在有效解释中却不可忽略。本文在地理空间与合成数据上，对多种作为分类器训练的ANN架构应用并修正了LRP方法。我们根据不同网络架构，展示了控制模型聚焦点的技术，并提供了提升相关性图质量以区分事实与伪影的指导建议。