Evolutionary Deep Learning with Extended Kalman Filter for Effective Prediction Modeling and Efficient Data Assimilation

2019 ◽  
Vol 33 (3) ◽  
pp. 04019014 ◽  
Author(s):  
Qiao Li ◽  
Zheng Yi Wu ◽  
Atiqur Rahman
Keyword(s):  
Deep Learning ◽  
Kalman Filter ◽  
Data Assimilation ◽  
Extended Kalman Filter ◽  
Prediction Modeling ◽  
Efficient Data

Evaluation of the observation operator Jacobian for leaf area index data assimilation with an extended Kalman filter

2010 ◽  
Vol 115 (D9) ◽  
Author(s):  
Christoph Rüdiger ◽  
Clément Albergel ◽  
Jean-François Mahfouf ◽  
Jean-Christophe Calvet ◽  
Jeffrey P. Walker
Keyword(s):  
Kalman Filter ◽  
Data Assimilation ◽  
Leaf Area Index ◽  
Leaf Area ◽  
Extended Kalman Filter ◽  
Area Index ◽  
Observation Operator ◽  
Index Data

Data assimilation in stand-level forest inventories

2013 ◽  
Vol 43 (12) ◽  
pp. 1104-1113 ◽  
Author(s):  
Sarah Ehlers ◽  
Anton Grafström ◽  
Kenneth Nyström ◽  
Håkan Olsson ◽  
Göran Ståhl
Keyword(s):  
Kalman Filter ◽  
Data Assimilation ◽  
Extended Kalman Filter ◽  
Large Scale ◽  
Prediction Models ◽  
Quality Data ◽  
Relative Advantage ◽  
Sources Of Information ◽  
Short Intervals ◽  
Forest Inventories

The development of remote sensing methods through research and large-scale application nowadays makes it possible to obtain stand-level estimates of forest variables at short intervals and at low cost. This offers substantial possibilities to forestry practitioners, but it also poses challenges regarding how cost-efficient data acquisition strategies should be developed. For example, should cheap but low-quality data be acquired and discarded whenever new data become available or should investments be made in high-quality data that are continuously updated to last over a longer period of time? We suggest that the solution could be to establish data assimilation (DA) procedures linked to forest inventories to make appropriate use of data from several sources. With DA, old information is updated through growth forecasts and when new information becomes available it is assimilated with the old information; the different sources of information are made use of to the extent motivated by their accuracy. In this study we made a general assessment of the usefulness of DA in connection with stand-level forest inventories and we compared two different methodological approaches, the extended Kalman filter and the Bayesian method. Not surprisingly, the relative advantage of DA was found to be largest for cases where low-precision estimates of growing stock volume were obtained at short intervals and forecasts were made with accurate growth prediction models. The methodological comparison revealed a tendency of the extended Kalman filter to underestimate the variance of the estimates.

Data Assimilation of River Networks Using Extended Kalman Filter

2014 ◽  
Vol 580-583 ◽  
pp. 1923-1927
Author(s):  
Yi Fan Chen ◽  
Jing Lin Qian
Keyword(s):  
Kalman Filter ◽  
Data Assimilation ◽  
Real Time ◽  
Extended Kalman Filter ◽  
River Network ◽  
Measurement Noise ◽  
River Networks ◽  
Network System ◽  
Process Noise ◽  
Measurement Noises

In order to improve the accuracy of river network hydraulic model, extended kalman filter was used for real-time updating model states. In a simulation example of a river network composed of 14 channels, it systematically analyzed the effects of process and measurement noises on state correction. The results show that the extended kalman filter is able to effectively carry out data assimilation of non-linear river network system, and big process noise in combination with relatively small measurement noise is recommended for state correction.

Sign in / Sign up

Export Citation Format

Share Document