A Sampling Strategy Benchmark for Machine-Learning-Based Seismic Liquefaction Prediction

TL;DR

This paper establishes a comprehensive benchmark for sampling strategies in machine learning models predicting seismic liquefaction, systematically evaluating various configurations and their interactions to optimize predictive accuracy.

Contribution

It introduces the first systematic evaluation of sampling methods and training set configurations, including their interactions, for ML-based seismic liquefaction prediction.

Findings

Ordered systematic sampling performs best across models.

Optimal training set: 200 samples, 80:20 split, class ratio 1-1.5.

Train-test split ratio most impacts performance.

Abstract

Sampling strategy including sampling methods and training set configurations (training set sample size, train-test split ratio, and class distribution) significantly affects machine-learning (ML) model performance in seismic liquefaction prediction. However, existing ML applications in seismic liquefaction prediction remain fragmented: sampling strategies vary widely across studies without a unified benchmark. Moreover, these studies generally optimize the sample set configuration independently, ignoring the interaction among training set configurations. To address these limitations, this study establishes a benchmark that systematically evaluates sampling methods, training set sample sizes, train-test split ratios, class distributions, and training set configurations coupling on seven mainstream ML models performance, and further improves the predictive accuracy of seismic liquefaction-using a database of 250 historical liquefaction events, evaluated by Acc and F1. The results show that ordered systematic sampling yields the best performance across all models. The optimal model can be trained when the training set sample size is 200, the train-test split ratio is 80:20, and the class distribution range is 1-1.5. Among them, the train-test split ratio most significantly influenced performance, followed by the class distribution, with the training set sample size having the least effect. Furthermore, the Random Forest model achieves the highest performance, while the K-Nearest Neighbor model performs the weakest. Importantly, this study systematically identifies and verifies for the first time that there will be an interaction effect among training set configurations, rather than a simple additive effect. This study provides a benchmark for scholars to select the optimal sampling method and training set configurations to obtain high accuracy in ML-based liquefaction prediction.