相关实验视频
Updated: Jan 18, 2026

Image-based Lagrangian Particle Tracking in Bed-load Experiments
Published on: July 20, 2017
EoML-SlideNet:一个轻量级的框架,用于用多源监测数据进行山体滑坡移位预测
Fan Zhang1,2, Yuanfa Ji1, Xiaoming Liu3
1School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China.
本研究介绍了EoML-SlideNet,这是一个轻量级的框架,用于精确地预测边缘设备上的山体滑坡位移. 它为脆弱的地形提供了更快,更响应的早期预警系统.
科学领域:
- 地质科学 地质科学
- 地震工程的工程是地震工程.
- 人工智能的人工智能
背景情况:
- 中国广西的岩地形面临着因降雨而面临的高滑坡风险.
- 现有的山体滑坡预测系统受到边缘设备的延迟和计算需求的影响.
研究的目的:
- 为资源有限的边缘硬件开发一个轻量级的预测框架 (EoML-SlideNet).
- 为提升早期预警系统的山体滑坡位移预测的及时性和准确性.
主要方法:
- 埃奥ML-SlideNet将位移分解为趋势和周期组件.
- 它使用双带拉索增强潜变量 (DBLE-LV) 模块进行特征选择.
- 轻量级的自回归和神经网络模型分别预测趋势和周期组件.
主要成果:
- 与深度学习和基线模型相比,EoML-SlideNet实现了2至4倍低的MAE/RMSE.
- 推理速度是3-30倍快,浮点运算 (FLOP) 显著降低.
- 该框架证明了适用于边缘部署而无需远程服务器依赖的适用性.
结论:
- 低复杂度的模型可以与地震预测的深度网络准确度相匹配或超过.
- 埃奥ML-SlideNet为基于边缘的实时滑坡预警系统提供了一个实用的解决方案.
- 该研究强调了FLOP和运行时间作为实际评估指标的重要性.
更多相关视频
08:09Measuring and Mapping Patterns of Soil Erosion and Deposition Related to Soil Carbonate Concentrations Under Agricultural Management
Published on: September 12, 2017
09:44Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
Published on: October 16, 2018
相关概念视频
Precipitation Gravimetry
In determining nickel by gravimetric analysis, a precipitant of ethanolic dimethylglyoxime is added to a hot nickel salt solution. This is quickly followed by the dropwise addition of dilute ammonia solution until precipitation occurs. A...
Design Example: Analyzing Capacity Contours for Flood Risk Assessment
Applications of GIS: Disaster Management and Emergency Response
Precipitation and Co-precipitation
GIS Software, Hardware, and Sources of GIS Data
Application of Linearization and Approximation