使用混合密度网络的高效贝叶斯地声逆转 (sa)
Guoli Wu1, Jiahua Zhu2, Jingya Zhang3
1Intelligent Game and Decision Lab, Beijing, 100000, China.
The Journal of the Acoustical Society of America
|March 2, 2026
概括
这项研究引入了混合密度网络 (MDNs) 以实现高效的贝叶斯海底地声逆转. 这种方法模拟了联合概率分布,降低了计算成本,与传统的马尔科夫链蒙特卡洛方法相比,提供了更深入的统计见解.
科学领域:
- 地质物理学 地质物理学
- 海洋声学 海洋声学
- 计算科学 计算科学
背景情况:
- 贝叶斯海底的地球声学倒置对于理解地底的特性至关重要.
- 传统的马尔科夫链蒙特卡洛 (McMC) 方法是计算密集且耗时的.
研究的目的:
- 使用混合密度网络 (MDNs) 开发一种高效的贝叶斯地声逆转方法.
- 模拟所有地声学参数同时的联合后面概率分布.
- 从后方概率密度 (PPD) 分析推断地球声学统计数据.
主要方法:
- 利用混合密度网络 (MDNs) 来建模地球声学参数的联合后面概率分布.
- 采用MDN理论来分析地声统计数据,避免数值集成.
- 在各种场景中,将MDN逆转结果与传统的McMC方法进行比较.
主要成果:
- MDN方法有效地建模了地声学参数的联合后方概率分布.
- 从MDN增强的PPD中分析推断统计数据提供了更深入的见解,并避免了昂贵的计算集成.
- MDN逆转结果显示与McMC趋势有很好的一致性,捕捉了参数之间的相关性和权衡.
结论:
- 混合密度网络为贝叶斯海底地球声学反向问题提供了一种高效而有洞察力的替代方案.
- 这种方法对实时地球声学倒置应用有希望.
- MDN可以有效地捕捉地声学参数之间的复杂关系和权衡.
相关概念视频
Distributions to Estimate Population Parameter
5.3K
The accurate values of population parameters such as population proportion, population mean, and population standard deviation (or variance) are usually unknown. These are fixed values that can only be estimated from the data collected from the samples. The estimates of each of these parameters are sample proportion, the sample mean, and sample standard deviation (or variance). To obtain the values of these sample statistics, data are required that have particular distribution and central...
5.3K
Density
20.2K
Density is an important characteristic of substances, crucial in determining whether an object sinks or floats in a fluid. Its SI unit is kg/m3, and its cgs unit is g/cm3. The density of an object helps in identifying its composition, and also reveals information about the phase of the matter and its substructure. The densities of liquids and solids are roughly comparable, consistent with the fact that their atoms are in close contact. However, gases have much lower densities than liquids and...
20.2K
One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation
1.3K
This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
On...
1.3K
Expected Frequencies in Goodness-of-Fit Tests
8.8K
A goodness-of-fit test is conducted to determine whether the observed frequency values are statistically similar to the frequencies expected for the dataset. Suppose the expected frequencies for a dataset are equal such as when predicting the frequency of any number appearing when casting a die. In that case, the expected frequency is the ratio of the total number of observations (n) to the number of categories (k).
8.8K
Density and Archimedes' Principle
9.0K
When a lump of clay is dropped into water, it sinks. But if the same lump of clay is molded into the shape of a boat, it starts to float. Because of its shape, the clay boat displaces more water than the lump and experiences a greater buoyant force, even though its mass is the same. The same holds true for steel ships. The average density of an object majorly determines if the object will float. If an object's average density is less than that of the surrounding fluid, it will float. The...
9.0K
Uniform Depth Channel Flow: Problem Solving
568
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
568


