多机器学习方法用于快速和协同逆转地下水污染源,水文参数和边界条件
Chengming Luo1, Xihua Wang2, Y Jun Xu3
1College of Civil Engineering, Tongji University, 1239 Siping Road, Shanghai 200092, China.
Journal of contaminant hydrology
|May 9, 2025
概括
这项研究结合了支持向量回归 (SVR) 和多层感知器 (MLP) 机器学习模型,以准确识别地下水污染源. SVR-MLP方法有效地确定了污染源,水文地质参数和边界条件,改善了整治工作.
科学领域:
- 环境科学 环境科学
- 水文地质学 水文地质学
- 机器学习 机器学习
背景情况:
- 逆转地下水污染是一个关键的环境挑战.
- 现有的机器学习方法在同时识别污染源,水文地质参数和边界条件方面存在局限性.
研究的目的:
- 开发一种协同和快速的方法来识别多个地下水污染逆变量.
- 为了比较不同机器学习模型对此任务的性能.
主要方法:
- 使用多层感知器 (MLP),内核极端学习机器,支持矢量机器 (SVR) 和反向传播神经网络.
- 建立模拟模型输出和输入之间的反向映射.
- 结合SVR和MLP (SVR-MLP) 进行协同识别.
主要成果:
- 在识别液压导电性和边界条件方面,SVR表现出高精度.
- 在确定污染物释放强度方面,MLP表现出很好的准确性.
- 结合SVR-MLP方法显著提高了整体反转精度,平均绝对百分比误差低于4%.
结论:
- SVR-MLP模型为地下水污染逆转提供了一种稳定可靠的方法.
- 这种方法为有效的地下水污染补救和管理策略提供了坚实的基础.
相关概念视频
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
28
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
28
01:30Typical Model Studies
159
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
159