A hybrid particle-ensemble Kalman filter for problems with medium nonlinearity.
A hybrid particle-ensemble Kalman filter for problems with medium nonlinearity.
复制标题
中等非线性问题的混合粒子系综卡尔曼滤波。
DOI：
10.1371/journal.pone.0248266
复制
发表时间：
2021
期刊：
影响因子：
3.7
通讯作者：
Robinson G
中科院分区：
文献类型：
--
作者：
Grooms I;Robinson G
针对中等非高斯性问题，即先验非常非高斯而后验近似高斯的问题，提出了一种混合粒子系综卡尔曼滤波器。例如，当非线性动力学产生非高斯预测，但紧高斯似然导致近高斯后验时，就会出现这种情况。混合滤波器首先分解可能性。首先，粒子滤波器用一个似然因子同化观测值，产生接近高斯的中间先验，然后集合卡尔曼滤波器用剩下的因子完成同化。确定两阶段间的似然分割方式，以保证粒子滤波器避免坍缩，并通过保持均值的随机正交变换打破粒子简并。在一个简单的二维（2D）问题和一个由Lorenz- 96模型驱动的多尺度ode系统中测试了该混合模型。在二维问题中，它优于纯粒子滤波器和纯集合卡尔曼滤波器，在多尺度Lorenz- 96模型中，如果集合大小足够大，它的性能优于纯集合卡尔曼滤波器。
A hybrid particle ensemble Kalman filter is developed for problems with medium non-Gaussianity, i.e. problems where the prior is very non-Gaussian but the posterior is approximately Gaussian. Such situations arise, e.g., when nonlinear dynamics produce a non-Gaussian forecast but a tight Gaussian likelihood leads to a nearly-Gaussian posterior. The hybrid filter starts by factoring the likelihood. First the particle filter assimilates the observations with one factor of the likelihood to produce an intermediate prior that is close to Gaussian, and then the ensemble Kalman filter completes the assimilation with the remaining factor. How the likelihood gets split between the two stages is determined in such a way to ensure that the particle filter avoids collapse, and particle degeneracy is broken by a mean-preserving random orthogonal transformation. The hybrid is tested in a simple two-dimensional (2D) problem and a multiscale system of ODEs motivated by the Lorenz-‘96 model. In the 2D problem it outperforms both a pure particle filter and a pure ensemble Kalman filter, and in the multiscale Lorenz-‘96 model it is shown to outperform a pure ensemble Kalman filter, provided that the ensemble size is large enough.
登录
查看更多内容
影响因子：
8.9
作者：
Ades, M.;van Leeuwen, P. J.
通讯作者：
van Leeuwen, P. J.
DOI：
10.1073/pnas.0909196106
发表时间：
2009-10-13
影响因子：
11.1
作者：
Chorin, Alexandre J.;Tu, Xuemin
通讯作者：
Tu, Xuemin
影响因子：
3.2
作者：
El Gharamti, Mohamad;Raeder, Kevin;Wang, Xuguang
通讯作者：
Wang, Xuguang
影响因子：
2.2
作者：
Grooms, I.;Lee, Y.
通讯作者：
Lee, Y.
影响因子：
3.2
作者：
Anderson, Jeffrey L.
通讯作者：
Anderson, Jeffrey L.