预测土壤液化易感性的进展:综合和深度学习方法的全面分析
Divesh Ranjan Kumar1, Warit Wipulanusat2
1Research Unit in Data Science and Digital Transformation, Department of Civil Engineering, Faculty of Engineering, Thammasat School of Engineering, Thammasat University, Pathumthani, Thailand.
Scientific reports
|July 21, 2025
概括
这项研究评估了深度学习 (DL) 和集体学习模型,用于评估土壤液化易感性. 该BI-LSTM模型展示了最高的准确性,为地震风险减轻提供了可靠的预测.
科学领域:
- 地质技术工程 地质技术工程
- 地震工程的工程是地震工程.
- 机器学习应用 机器学习应用
背景情况:
- 液化,由于孔隙水压增加而导致土壤强度的损失,造成了重大地震风险.
- 精确评估液化易感性对于施工现场安全和减轻地震危险至关重要.
- 传统方法可能无法完全捕捉影响液化过程的复杂因素.
研究的目的:
- 调查深度学习 (DL) 和集体学习模型的有效性,以评估土壤液化易感性.
- 通过使用圆透测试 (CPT) 数据和历史地震观测数据的全面数据库,比较各种机器学习模型的性能.
- 确定最可靠的模型来预测液化潜力.
主要方法:
- 利用了大量的圆穿透测试 (CPT) 测量数据库和现场液化性能观测.
- 开发和评估深度学习 (DL) 模型,包括BI-LSTM和LSTM,以及像XGBoost和随机森林 (RF) 这样的集体学习模型.
- 使用多个指标评估模型性能:准确性,验证损失,精度,回忆,F1分数,MCC,BA,ROC曲线分析和AUC.
主要成果:
- 该BI-LSTM模型实现了最高的准确性 (0.9791培训,0.8889测试),表明强大的预测能力和通用性.
- LSTM和XGBoost也表现出强的表现,分别的精度为0.9433/0.8750和0.9194/0.8750.
- 随机森林 (RF) 模型显示了训练 (0.9373) 和测试 (0.8681) 准确度之间的显著差异.
结论:
- BI-LSTM是评估液化潜力的最可靠模型,紧随其后的是LSTM和XGBoost.
- DL模型 (BI-LSTM,LSTM) 擅长捕获顺序依赖关系,而组合模型 (XGBoost,RF) 从结构化数据提供了强大的结果.
- 这项研究为液化危险评估提供了先进的工具,改善了地震风险减轻策略.
相关概念视频
01:16Dynamic Modulus of Elasticity of Concrete
549
The dynamic modulus of elasticity assesses how a concrete structure deforms under impact or dynamic loads. It is typically higher than the static modulus of elasticity, measured under slow, steady loading conditions.
The sonic test is a common method to determine the dynamic modulus. In this test, a concrete beam, sized either 6 x 6 x 30 inches or 4 x 4 x 20 inches, is clamped at its center. Vibrations are initiated at one end of the beam by an electromagnetic exciter unit powered by...
The sonic test is a common method to determine the dynamic modulus. In this test, a concrete beam, sized either 6 x 6 x 30 inches or 4 x 4 x 20 inches, is clamped at its center. Vibrations are initiated at one end of the beam by an electromagnetic exciter unit powered by...
549
01:20Elasticity in Concrete
151
Upon subjecting concrete to moderate or high uniaxial compressive or tensile stresses, the strain response is non-linear relative to the stress applied. As the stress is removed, the resulting stress-strain curve deviates from the original path traced during loading, creating a hysteresis loop, indicative of the concrete's non-linear and non-elastic properties. Typically, a material's modulus of elasticity, which is a measure of the material's stiffness, is inferred from the linear...
151