<b>Code and Data for </b><b><i>"Quantifying Uncertainty in Geospatial Explanations from Explainable AI"</i></b>

<b>Code and Data for </b><b><i>"Quantifying Uncertainty in Geospatial Explanations from Explainable AI"</i></b>This repository contains the code and data used in our submitted work <i>“Quantifying Uncertainty in Geospatial Explanations from Explainable AI.”</i>In this study, we propose <b>GeoXCP</b>, a <b>model-agnostic framework</b> for quantifying uncertainty in geospatial explanations derived from explainable AI methods.We validate the effectiveness of GeoXCP through a case study on housing price prediction. The provided files are organized as follows:<br>📁<b> 1-model</b>Contains the core implementation of <b>GeoXCP</b>, including the following modules:GeoConformalGeoConformalizedExplainer<br>📁<b> 2-data_Housing_price</b>Includes the housing price dataset for Seattle:seattle_sample_3k.csv<br>📁<b> 3-codes_Housing_price</b>Contains code used for applying GeoXCP to the housing price prediction task:SeattleHomeSaleUncertaintyGeoX.ipynb: End-to-end implementation for uncertainty quantification using GeoXCP. All results from the main experiment can be reproduced here.seattle_house_price_coverage_bootstrap.ipynb: Demonstrates how GeoXCP achieves reliable coverage through bootstrap-based validation.<br>