Article
Energy & Fuels
Farhana Akter, Syed Imtiaz, Sohrab Zendehboudi, Kamal Hossain
Summary: Ensemble Kalman filter (EnKF) is widely used in reservoir modelling for history matching, but faces challenges when dealing with mismatch between the reservoir and the model. By introducing modifications and conducting sensitivity analysis, improvements in history matching efficiency are possible in cases of high model mismatch and measurement uncertainty.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2021)
Article
Mechanics
Zhiwen Deng, Chuangxin He, Yingzheng Liu
Summary: This paper focuses on the optimal sensor placement strategy based on a deep neural network for turbulent flow recovery within the data assimilation framework of the ensemble Kalman filter. The results demonstrate the effectiveness and robustness of the proposed strategy, showing that RANS models with EnKF augmentation were substantially improved over their original counterparts. The study concludes that the DNN-based OSP with the selection of the five most sensitive sensors can efficiently reduce the number of sensors while achieving similar or better assimilated performance.
Article
Mathematics, Applied
Alexander Wikner, Jaideep Pathak, Brian R. Hunt, Istvan Szunyogh, Michelle Girvan, Edward Ott
Summary: This study discusses the forecasting of chaotic dynamical systems using noisy partial measurements data, with a focus on combining machine learning with knowledge-based models to improve predictions. By assimilating synthetic data and training machine learning models with partial measurements, it shows potential to correct imperfections in knowledge-based models and improve forecasting accuracy.
Article
Engineering, Marine
Shaokun Deng, Zheqi Shen, Shengli Chen, Renxi Wang
Summary: The initial ensemble has an impact on the performance of ensemble-based assimilation techniques. The differences in the initial ensemble affect the convergence rate of assimilation, but all experiments eventually reach convergence. Sea surface height and sea surface salinity are more sensitive to the initial ensemble. The white-noise perturbation scheme has the largest effect, and the influence of different initial ensembles on sea surface height is concentrated in the region of the Antarctic Circumpolar Current.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2022)
Article
Meteorology & Atmospheric Sciences
Eviatar Bach, Michael Ghil
Summary: Data assimilation aims to optimally combine partial and noisy model forecasts and observations. Multi-model data assimilation generalizes the variational or Bayesian formulation of the Kalman filter and is proven to be the minimum variance linear unbiased estimator. In this study, a multi-model ensemble Kalman filter (MM-EnKF) based on this framework is formulated and implemented. The MM-EnKF can combine multiple model ensembles for both data assimilation and forecasting in a flow-dependent manner by providing adaptive model error estimation and matrix-valued weights for the separate models and observations. Numerical experiments using the Lorenz96 model show that the MM-EnKF results in significant error reductions compared to the best model and an unweighted multi-model ensemble in terms of probabilistic and deterministic metrics.
JOURNAL OF ADVANCES IN MODELING EARTH SYSTEMS
(2023)
Article
Astronomy & Astrophysics
Angelica M. Castillo Tibocha, Jana de Wiljes, Yuri Y. Shprits, Nikita A. Aseev
Summary: This study applies ensemble Kalman filter for data assimilation in the radiation belts, developing two new methods and validating their accuracy. The use of split-operator technique allows inclusion of more physical processes in simulations and improves computational efficiency.
SPACE WEATHER-THE INTERNATIONAL JOURNAL OF RESEARCH AND APPLICATIONS
(2021)
Article
Meteorology & Atmospheric Sciences
Troy Arcomano, Istvan Szunyogh, Alexander Wikner, Jaideep Pathak, Brian R. Hunt, Edward Ott
Summary: This paper describes the implementation of a combined hybrid-parallel prediction approach on a low-resolution atmospheric global circulation model. The hybrid model, which combines a physics-based numerical model with a machine learning component, produces more accurate forecasts for various atmospheric variables compared to the host model. Furthermore, the hybrid model exhibits smaller systematic errors and more realistic temporal variability in simulating the climate.
JOURNAL OF ADVANCES IN MODELING EARTH SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Zhuoyu Dai, Feibin Xiang, Chaojie He, Zi Wang, Woyu Zhang, Yi Li, Jinshan Yue, Dashan Shang
Summary: Reservoir computing (RC) is a lightweight machine learning algorithm for edge applications, which has lower computation workload and one-time training process compared to RNN and Transformer. The proposed scalable small-footprint time-space-pipelined architecture for cycle RC paradigm can distribute workload onto configurable number of processing elements (PE) and improve energy efficiency by 12.6 times compared to the state-of-the-art RC accelerator.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2023)
Article
Meteorology & Atmospheric Sciences
Lili Lei, Yangjinxi Ge, Zhe-Min Tan, Yi Zhang, Kekuan Chu, Xin Qiu, Qifeng Qian
Summary: This study evaluates the ensemble Kalman filter (EnKF) combined with the Advanced Research Weather Research and Forecasting model (WRF) for western North Pacific typhoons in 2016. The results show that the WRF/EnKF system provides better ensemble forecasts and higher predictability for typhoon intensity compared to NCEP and ECMWF ensemble forecasts.
ADVANCES IN ATMOSPHERIC SCIENCES
(2022)
Article
Computer Science, Interdisciplinary Applications
Habib Toye, Peng Zhan, Furrukh Sana, Sivareddy Sanikommu, Naila Raboudi, Ibrahim Hoteit
Summary: EnOI is a variant of EnKF that uses a static ensemble to reduce computational cost. A new adaptive EnOI approach is proposed to better represent the time-varying circulation of the Red Sea by adaptively selecting ensemble members at each assimilation cycle.
JOURNAL OF COMPUTATIONAL SCIENCE
(2021)
Article
Computer Science, Interdisciplinary Applications
Habib Toye, Peng Zhan, Furrukh Sana, Sivareddy Sanikommu, Naila Raboudi, Ibrahim Hoteit
Summary: EnOI is a variant of EnKF that reduces computational cost by using a static ensemble to parameterize the background covariance matrix. An adaptive EnOI approach is proposed to better represent the time-varying circulation of the Red Sea, with different schemes for selecting ensemble members tested. Results from assimilating real remote sensing data into a high resolution circulation model of the Red Sea are presented and discussed, demonstrating the relevance of the proposed schemes.
JOURNAL OF COMPUTATIONAL SCIENCE
(2021)
Article
Engineering, Electrical & Electronic
M. A. Gonzalez-Cagigal, J. A. Rosendo-Macias, A. Gomez-Exposito
Summary: This research presents a state estimation approach using Kalman filtering to identify the phase to which single-phase customers are connected in three-phase distribution grids. The study compares different nonlinear formulations of the Kalman filter and shows that the ensemble Kalman filter provides better estimation results as the system size increases. The accuracy, robustness, and limitations of the estimator are also tested with consideration of measurement errors.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2021)
Article
Mathematics, Applied
Theresa Lange
Summary: This paper provides a rigorous derivation of the ensemble Kalman-Bucy filter and the ensemble transform Kalman-Bucy filter in the case of nonlinear, unbounded model and observation operators. It also establishes convergence rates in terms of the discretisation step size. The paper simultaneously establishes the well-posedness and accuracy of both the continuous-time and the discrete-time filtering algorithms.
Article
Meteorology & Atmospheric Sciences
Elias D. Nino-Ruiz, Randy S. Consuegra S. Ortega, Magdalena Lucini
Summary: This paper presents the efficient and practical implementation of sequential data assimilation methods for the SPEEDY Model into climate prediction. The computational implementation of SPEEDY blends the time integrator and the spatial discretization to accelerate algebraic computations. Augmented vector states are used to propagate analysis innovations from positions to velocities.
QUARTERLY JOURNAL OF THE ROYAL METEOROLOGICAL SOCIETY
(2023)
Article
Chemistry, Physical
Lukas Boehler, Daniel Ritzberger, Christoph Hametner, Stefan Jakubek
Summary: This paper presents an alternative approach to extended Kalman filtering for polymer electrolyte membrane fuel cell systems, providing robust real-time state estimations and achieving faster computational speed compared to standard approaches. The method resolves dependencies on operating conditions and offers accurate state estimates even in challenging scenarios, making it a viable option for control and fault detection applications.
INTERNATIONAL JOURNAL OF HYDROGEN ENERGY
(2021)
Article
Computer Science, Interdisciplinary Applications
Yapo Abole Serge Innocent Oboue, Yunfeng Chen, Sergey Fomel, Wei Zhong, Yangkang Chen
Summary: Strong noise can disrupt the recorded seismic waves and negatively impact subsequent seismological processes. To improve the signal-to-noise ratio (S/N) of seismological data, we introduce MATamf, an open-source MATLAB code package based on an advanced median filter (AMF) that simultaneously attenuates various types of noise and improves S/N. Experimental results demonstrate the usefulness and advantages of the proposed AMF workflow in enhancing the S/N of a wide range of seismological applications.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Upkar Singh, P. N. Vinayachandran, Vijay Natarajan
Summary: The Bay of Bengal maintains its salinity distribution due to the cyclic flow of high salinity water and the mixing with freshwater. This paper introduces an advection-based feature definition and algorithms to track the movement of high salinity water, validated through comparison with observed data.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Bijal Chudasama, Nikolas Ovaskainen, Jonne Tamminen, Nicklas Nordback, Jon Engstro, Ismo Aaltonen
Summary: This contribution presents a novel U-Net convolutional neural network (CNN)-based workflow for automated mapping of bedrock fracture traces from aerial photographs acquired by unmanned aerial vehicles (UAV). The workflow includes training a U-Net CNN using a small subset of photographs with manually traced fractures, semantic segmentation of input images, pixel-wise identification of fracture traces, ridge detection algorithm and vectorization. The results show the effectiveness and accuracy of the workflow in automated mapping of bedrock fracture traces.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Ruizhen Wang, Siyang Wan, Weitao Chen, Xuwen Qin, Guo Zhang, Lizhe Wang
Summary: This paper proposes a novel framework to generate a finer soil strength map based on RCI, which uses ensemble learning models to obtain USCS soil classification and predict soil moisture, in order to improve the resolution and reliability of existing soil strength maps.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Zhanlong Chen, Xiaochuan Ma, Houpu Li, Xuwei Xu, Xiaoyi Han
Summary: Simulated terrains are important for landform and terrain research, disaster prediction, rescue and disaster relief, and national security. This study proposes a deep learning method, IGPN, that integrates global information and pattern features of the local terrain to generate accurate simulated terrains quickly.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Daniele Secci, Vanessa A. Godoy, J. Jaime Gomez-Hernandez
Summary: Neural networks excel in various machine learning applications, but lack physical interpretability and constraints, limiting their accuracy and reliability in predicting complex physical systems' behavior. Physics-Informed Neural Networks (PINNs) integrate neural networks with physical laws, providing an effective tool for solving physical problems. This article explores recent developments in PINNs, emphasizing their application in solving unconfined groundwater flow, and discusses challenges and opportunities in this field.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Renguang Zuo, Ying Xu
Summary: This study proposes a hybrid deep learning model consisting of a one-dimensional convolutional neural network (1DCNN) and a graph convolutional network (GCN) to extract joint spectrum-spatial features from geochemical survey data for mineral exploration. The physically constrained hybrid model performs better in geochemical anomaly recognition compared to other models.
COMPUTERS & GEOSCIENCES
(2024)