Analyzing spatial varying effect is pivotal in geographic analysis. Yet,
accurately capturing and interpreting this variability is challenging due to
the complexity and non-linearity of geospatial data. Herein, we introduce an
integrated framework that merges local spatial weighting scheme, Explainable
Artificial Intelligence (XAI), and cutting-edge machine learning technologies
to bridge the gap between traditional geographic analysis models and general
machine learning approaches. Through tests on synthetic datasets, this
framework is verified to enhance the interpretability and accuracy of
predictions in both geographic regression and classification by elucidating
spatial variability. It significantly boosts prediction precision, offering a
novel approach to understanding spatial phenomena.

分析空间变化效应在地理分析中至关重要，然而由于地理空间数据的复杂性和非线性，准确捕捉和解释这种变异性是具有挑战性的。本文介绍了一个集成框架，将局部空间加权方案、可解释人工智能（XAI）和先进的机器学习技术相结合，以弥合传统地理分析模型和通用机器学习方法之间的差距。通过对合成数据集的测试，验证了该框架在地理回归和分类中通过阐明空间变异性，提高了预测的解释性和准确性。它显著提升了预测精度，为理解空间现象提供了一种新的方法。