Correcting sampling biases via importance reweighting for spatial modeling

TL;DR

This paper presents an importance reweighting method to correct sampling biases in spatial data models, significantly improving error estimation accuracy under distribution shifts.

Contribution

It introduces a novel importance sampling approach combined with kernel density estimation to unbiasedly estimate errors in spatial modeling.

Findings

Error rate reduced from 7% to 2%

Method effectively neutralizes distribution shift

Performance improves with larger sample sizes

Abstract

In machine learning models, the estimation of errors is often complex due to distribution bias, particularly in spatial data such as those found in environmental studies. We introduce an approach based on the ideas of importance sampling to obtain an unbiased estimate of the target error. By taking into account difference between desirable error and available data, our method reweights errors at each sample point and neutralizes the shift. Importance sampling technique and kernel density estimation were used for reweighteing. We validate the effectiveness of our approach using artificial data that resemble real-world spatial datasets. Our findings demonstrate advantages of the proposed approach for the estimation of the target error, offering a solution to a distribution shift problem. Overall error of predictions dropped from 7% to just 2% and it gets smaller for larger samples.