State-space Model Research Articles

Estimation of true dates of various flowering stages at a centennial scale by applying a Bayesian statistical state space model.

Evaluation of long-term detailed cherry flowering phenology is required for a deep understanding of the sensitivity of spring phenology to climate change and its effect on cultural ecosystem services. Neodani Usuzumi-zakura (Cerasus itosakura) is a famous cherry tree in Gifu, Japan. On the basis of detailed decadal flowering phenology information published on the World Wide Web, we estimated the probability distributions of the year-to-year variability of the true dates of first flowering (FFL), first full bloom (FFB), last full bloom (LFB), and last flowering (LFL) from 1924 to 2024 by applying a Bayesian statistical state space model explained by air temperature data. We verified the estimated values against flowering phenology records of the tree from the literature and a private collection. The true dates of FFL and FFB could be explained by means of daily minimum air temperature from 1 December to 28/29 February and that of daily mean air temperature from 1 to 31 March, and those of LFB and LFL by means of daily mean air temperature from 1 to 10 April. Results were similar when we used air temperature data recorded at weather stations both 1 km and 29 km from the tree. These results indicated that our proposed Bayesian statistical state space model can estimate cherry flowering phenology that takes into account centennial-scale air temperature data recorded at a nearby weather station with a coarse temporal resolution.

Voltage Distribution on Transformer Windings Subjected to Lightning Strike Using State-Space Method

Transient analysis in power systems is essential for identifying deficiencies in the system, as well as for the protection and design of equipment. Transients can arise from natural events or network operations; in either case, they have the potential to cause significant damage to transmission lines, protection devices, generators, or transformers. This study examines a 20 kA, 1.2/50 µs lightning strike on a distributed-parameter transmission line connected to a power transformer. The voltage distributions across the winding sections on the neutral grounded high-voltage side of a disc-structured power transformer were obtained using the state-space method. An equivalent circuit for the state-space model was also developed in the Alternative Transients Program–Electromagnetic Transients Program (ATP-EMTP), and the results from both methods were compared. Both approaches revealed that the voltage waveforms in the transformer’s winding sections were consistent, with the voltage distribution decreasing linearly. Additionally, the voltage–current waves reached the transformer with a specific delay, depending on the characteristics of the transmission line and the location of the lightning strike. The impact of an increase in the grounding resistance value on the high-voltage side of the transformer on voltage distribution and peak voltage levels was examined. The proposed method effectively captures the voltage–current behavior of the transmission line and transformer windings during transient conditions. It is concluded that the state-space method serves as a viable alternative for transient analysis in power systems and can enhance the design of protection equipment and winding insulation studies.

Online Cell-by-Cell Calibration Method to Enhance the Kalman-Filter-Based State-of-Charge Estimation

Kalman filter (KF) is an effective way to estimate the state-of-charge (SOC), but its performance is heavily dependent on the state-space model parameters. One of the factors that causes the model parameters to change is battery aging, which is individually and non-uniformly experienced by the cells inside the battery pack. To mitigate this issue, this paper proposes an online calibration method considering the impact of cell aging and cell inconsistency. In this method, the state-of-health (SOH) levels of the individual cells are estimated using the deep learning method, and the historical parameter loop-up table is constructed to update the state-space model. The proposed calibration framework provides enhanced accuracy for cell-by-cell SOC estimation by lightweight computing devices. The SOC estimation errors of the calibrated EKF reduce to 1.81% compared to 12.1% of the uncalibrated algorithms.

Augmentation message design for LEO-enhanced precise positioning: In-orbit performance assessment

Recent advancements in low earth orbit (LEO) navigation augmentation systems, such as the CENTISPACETM system developed by Beijing Future Navigation Tech Co., Ltd, have significantly reduced the convergence time of GNSS precise point positioning (PPP). To facilitate LEO-enhanced precise positioning, we developed a comprehensive set of LEO augmentation messages, including GNSS/LEO state-space representation (SSR) parameters. These messages were validated through onboard tests using real LEO augmentation observations. To expedite cold start times, the GNSS orbit SSR is based on a polynomial model, while LEO orbits are modeled using classic GNSS broadcast ephemeris with additional perturbation parameters. GNSS and LEO clock are predicted by a linear model. The designed LEO augmentation messages were validated by LEO-augmented PPP calculations. The average convergence time with LEO SSR messages was 4.8 min, revealing an improvement of 71.3 % over GNSS PPP and aligning closely with the 5.1 min achieved through post-processing.

GASSM: Global attention and state space model based end-to-end hyperspectral change detection

GASSM: Global attention and state space model based end-to-end hyperspectral change detection

Koopman-Constrained Hierarchical Deep State Space Model for Industrial Quality Prediction via Cloud-Edge Collaborative Framework

Koopman-Constrained Hierarchical Deep State Space Model for Industrial Quality Prediction via Cloud-Edge Collaborative Framework

Predicting hospital admissions due to COVID-19 in Denmark using wastewater-based surveillance.

Wastewater surveillance has become a fundamental tool to monitor the circulation of SARS-CoV-2 in order to prepare timely public health responses. In this study we integrate available clinical data on hospital admissions with wastewater surveillance data and investigate if predictions of the number of hospital admissions due to COVID-19 in Danish hospitals are improved by including wastewater concentrations of SARS-CoV-2. We implement state space models to describe the relationship between the number of hospital admissions due to COVID-19, available with a three-week classification delay, and more recent numbers of total hospital admissions with COVID-19. Including wastewater concentrations of SARS-CoV-2, we consider five-week predictions of the number of hospital admissions due to COVID-19. As a result of the three-week classification delay, the predictions translate into two hindcasts, one nowcast and two forecasts. The predicted values for all time frames follow the observed numbers well. We find that log likelihood values are higher when including wastewater concentrations (across all horizons) and that lagging the wastewater observations to investigate whether changes in wastewater concentrations occur before changes in hospital admissions does not result in further improvements. Our study shows that including wastewater concentrations improve estimates of the number of hospital admissions due to COVID-19, implying that wastewater concentrations add valuable information about the underlying transmission and that the imminent development of the near-future disease burden from COVID-19 is better informed when carefully including wastewater concentrations.

Integrating Python and MATLAB for Digital Twin Applications in Aeroservoelasticity

The development of Digital Twin (DT) applications in intricate engineering areas has been greatly accelerated by the incorporation of sophisticated computational tools like Python and MATLAB. The goal of this research is to model, simulate, and analyze aeroservoelastic systems for Digital Twin implementations by utilizing the combined powers of Python and MATLAB. In order to achieve the real-time predictive skills needed for Digital Twins, aeroservoelasticity—which involves the coupled interplay of aerodynamic, structural, and control forces—presents special obstacles. This work successfully tackles these issues by fusing MATLAB's strong numerical and control system capabilities with Python's adaptability and library ecosystem. Using real-time sensor data streaming, and feedback control system implementation is used in this work. High-fidelity state-space modeling, sophisticated control design (such as PID and state feedback controllers), and system dynamics visualization are all done concurrently with MATLAB. In order to simulate and stabilize a highly flexible aeroelastic system, a continuous feedback loop was modeled in both environments, highlighting the platforms' complimentary advantages. Through the MATLAB Engine API for Python, the integrated method facilitates smooth data transmission between Python and MATLAB, guaranteeing real-time communication and model parameter synchronization. The efficiency of this dual-platform system is demonstrated by case studies on wing flutter suppression, limit cycle oscillation (LCO) mitigation, and control input optimization. The method is well suited for the dynamic needs of aeroservoelastic Digital Twins because of the results, which demonstrate a shorter error convergence time, improved stability, and computational economy. By utilizing MATLAB and Python's interoperability, this work establishes the groundwork for scalable, real-time Digital Twin solutions in aeronautical engineering. It highlights how crucial hybrid computational ecosystems are for bridging the gap between high- fidelity simulations and real-time predictive capabilities, opening the door for improvements in fault prediction, control optimization, and aeronautical system monitoring.

Advanced model predictive control strategy for thermal management in multi-zone buildings with energy storage and dynamic pricing

In this study, we propose a modified model predictive control (MPC) strategy for managing the thermal load in buildings, aimed at creating a fine-tuned balance between indoor thermal comfort and electricity cost reduction. Here, the multi-zone building’s state-space model is employed to dynamically manage energy consumption while preserving occupant comfort. The key contributions of this work include the development of a novel economic MPC strategy tailored for multi-zone heating, ventilation, and air conditioning (HVAC) systems, integrating thermal energy storage to optimise energy usage and occupant comfort. Additionally, we introduce an enhanced multi-objective optimisation framework that transforms the conflicting objectives of energy efficiency and occupant comfort into a single-objective problem for improved computational efficiency. The control strategy also incorporates dynamic electricity pricing, enabling cost-effective operation by shifting energy consumption to lower-cost periods. The proposed control method reduces fluctuations in indoor air temperature, extending the operational life of HVAC system actuators. Beyond reducing costs and consumption, this approach alleviates energy production strain and peak demand on the smart grid. The optimisation process incorporates user-defined temperature preferences for each zone, ensuring tailored comfort conditions. Simulation results show that this method maintains indoor air temperature within the desired comfort range, outperforming traditional methods prone to fluctuations. Furthermore, the proposed MPC strategy effectively shifts the peak load to periods of lower electricity prices, achieving an 18.58% reduction in overall energy costs.

MUNet: a novel framework for accurate brain tumor segmentation combining UNet and mamba networks

Brain tumors are one of the major health threats to humans, and their complex pathological features and anatomical structures make accurate segmentation and detection crucial. However, existing models based on Transformers and Convolutional Neural Networks (CNNs) still have limitations in medical image processing. While Transformers are proficient in capturing global features, they suffer from high computational complexity and require large amounts of data for training. On the other hand, CNNs perform well in extracting local features but have limited performance when handling global information. To address these issues, this paper proposes a novel network framework, MUNet, which combines the advantages of UNet and Mamba, specifically designed for brain tumor segmentation. MUNet introduces the SD-SSM module, which effectively captures both global and local features of the image through selective scanning and state-space modeling, significantly improving segmentation accuracy. Additionally, we design the SD-Conv structure, which reduces feature redundancy without increasing model parameters, further enhancing computational efficiency. Finally, we propose a new loss function that combines mIoU loss, Dice loss, and Boundary loss, which improves segmentation overlap, similarity, and boundary accuracy from multiple perspectives. Experimental results show that, on the BraTS2020 dataset, MUNet achieves DSC values of 0.835, 0.915, and 0.823 for enhancing tumor (ET), whole tumor (WT), and tumor core (TC), respectively, and Hausdorff95 scores of 2.421, 3.755, and 6.437. On the BraTS2018 dataset, MUNet achieves DSC values of 0.815, 0.901, and 0.815, with Hausdorff95 scores of 4.389, 6.243, and 6.152, all outperforming existing methods and achieving significant performance improvements. Furthermore, when validated on the independent LGG dataset, MUNet demonstrated excellent generalization ability, proving its effectiveness in various medical imaging scenarios. The code is available at https://github.com/Dalin1977331/MUNet.

Weamba: Weather-Degraded Remote Sensing Image Restoration with Multi-Router State Space Model

Adverse weather conditions, such as haze and raindrop, consistently degrade the quality of remote sensing images and affect subsequent vision-based applications. Recent years have witnessed advancements in convolutional neural networks (CNNs) and Transformers in the field of remote sensing image restoration. However, these methods either suffer from limited receptive fields or incur quadratic computational overhead, leading to an imbalance between performance and model efficiency. In this paper, we propose an effective vision state space model (called Weamba) for remote sensing image restoration by modeling long-range pixel dependencies with linear complexity. Specifically, we develop a local-enhanced state space module to better aggregate rich local and global information, both of which are complementary and beneficial for high-quality image reconstruction. Furthermore, we design a multi-router scanning strategy for spatially varying feature extraction, alleviating the issue of redundant information caused by repeated scanning directions in existing methods. Extensive experiments on multiple benchmarks show that the proposed Weamba performs favorably against state-of-the-art approaches.

HMCNet: A Hybrid Mamba–CNN UNet for Infrared Small Target Detection

Using infrared technology to accurately detect small weak targets is crucial in various fields, such as reconnaissance and security. However, the infrared detection of small weak targets is challenged by complex backgrounds, tiny target sizes, and low signal-to-noise ratios, which significantly increase the difficulty of detection. Early studies in this domain typically utilized manually designed feature-extraction methods that performed inadequately in the presence of complex backgrounds. While advancements in deep learning have spurred rapid progress in this field, with CNN models effectively enhancing the detection performance, the problem of small weak target features being lost persists. HMCNet, which employs a hybrid architecture combining a state space model and a CNN, is proposed in this paper; its hybrid architecture demonstrates the capacity to extract the local features and model the global context, facilitating superior suppression of complex backgrounds and detection of small weak targets. Our experimental results on the public IRSTD-1k dataset and our own MISTD dataset indicate that, compared to the current mainstream methods, the method proposed achieves better detection accuracy while maintaining high-speed inference capabilities, thus validating the rationality and effectiveness of this research.

Linear and Non-Linear Optimal Control Methods to Determine the Best Chemotherapy Schedule for Most Effectively Inhibiting Tumor Growth

Background/Objectives: Cancer is a dynamic and complex disease that remains largely untreated despite major advances in oncology and treatment. In this context, we aimed here to investigate optimal control techniques in the management of tumor growth inhibition, with a particular focus on cancer chemotherapy treatment strategies. Methods: Using both linear autoregressive with exogenous inputs (ARX) and advanced non-linear tumor growth inhibition (TGI) modeling approaches, we investigated various single-agent treatment protocols, including continuous, periodic, and intermittent chemotherapy schedules. By integrating advanced mathematical modeling with optimal control theory and methods, namely the Linear Quadratic Regulator (LQR) and the “pseudo-linear” state-space equivalent representation and suboptimal control of a non-linear dynamic system known as the State-Dependent Riccati Equation (SDRE) approach, this work explores and evaluates successfully, more effective chemotherapy treatment strategies at the computer simulation level, using real preclinical data which increases the expectation to be applied in the clinical practice of oncology. Results: The integration of these methods provides insights into how different drug administration schedules may affect tumor response at the preclinical level. This work uses mathematical modeling to evaluate the efficacy of various periodic and intermittent chemotherapy treatment strategies, with a focus on optimizing drug doses while minimizing the potential side effects of chemotherapy due to the administration of less effective chemotherapeutic doses. Conclusions: The treatment scenarios tested in this study could effectively stop tumor growth or even lead to tumor regression to a negligible or near-zero size. This approach highlights the importance of computational tools for more effective treatment strategies in chemotherapy and offers a promising direction for future research and more efficient clinical applications in oncology as part of a more individualized approach.

Using the state-space separable cohort model modification for assessment of Pacific cod Gadus macrocephalus (Gadidae) stocks in the Petropavlovsk-Komandorskaya subzone

Results of using a state-space cohort model with smoothing unscented Kalman filter for assessment of Pacific cod stock abundance and the other population parameters in the Petropavlovsk-Komandorskaya Subzone are presented. Series of numerical experiments were carried out with various variants of the recruitment model. The results of the work performed can be used in preparing forecasts of the TAC of marine commercial fish in terms that the observational data allow the use of age-structured models in the state space.

Towards an Efficient Remote Sensing Image Compression Network with Visual State Space Model

In the past few years, deep learning has achieved remarkable advancements in the area of image compression. Remote sensing image compression networks focus on enhancing the similarity between the input and reconstructed images, effectively reducing the storage and bandwidth requirements for high-resolution remote sensing images. As the network’s effective receptive field (ERF) expands, it can capture more feature information across the remote sensing images, thereby reducing spatial redundancy and improving compression efficiency. However, the majority of these learned image compression (LIC) techniques are primarily CNN-based and transformer-based, often failing to balance the global ERF and computational complexity optimally. To alleviate this issue, we propose a learned remote sensing image compression network with visual state space model named VMIC to achieve a better trade-off between computational complexity and performance. Specifically, instead of stacking small convolution kernels or heavy self-attention mechanisms, we employ a 2D-bidirectional selective scan mechanism. Every element within the feature map aggregates data from multiple spatial positions, establishing a globally effective receptive field with linear computational complexity. We extend it to an omni-selective scan for the global-spatial correlations within our Channel and Global Context Entropy Model (CGCM), enabling the integration of spatial and channel priors to minimize redundancy across slices. Experimental results demonstrate that the proposed method achieves superior trade-off between rate-distortion performance and complexity. Furthermore, in comparison to traditional codecs and learned image compression algorithms, our model achieves BD-rate reductions of −4.48%, −9.80% over the state-of-the-art VTM on the AID and NWPU VHR-10 datasets, respectively, as well as −6.73% and −7.93% on the panchromatic and multispectral images of the WorldView-3 remote sensing dataset.

Automated Test Case Generation for Chip Verification Using Deep Reinforcement Learning

This paper presents a novel automated test case generation framework leveraging deep reinforcement learning (DRL) for chip verification. The framework addresses the growing complexity in modern chip designs where traditional verification methods must help achieve comprehensive coverage efficiently. Our approach implements a custom deep Q-network architecture optimized for processing coverage feedback and generating test vectors, incorporating an innovative reward mechanism that balances coverage optimization with simulation efficiency. The proposed system features a hierarchical state space representation scheme that captures temporal and spatial aspects of coverage progression, combined with an adaptive training strategy that dynamically adjusts to verification requirements. The framework is evaluated on multiple industrial-scale benchmark designs, demonstrating significant improvements over conventional methods, achieving up to 98.5% functional coverage with a 45% reduction in verification time. The distributed implementation demonstrates near-linear scaling across multiple GPU nodes while maintaining high resource utilization efficiency. Experimental results show that the DRL-based approach outperforms traditional constrained-random and coverage-driven test generation methods across various metrics, including coverage rate, corner case detection, and simulation efficiency. The framework's integration with existing verification workflows and its ability to handle complex design scenarios make it particularly suitable for modern chip verification challenges.

A Systematic Review on Reinforcement Learning for Industrial Combinatorial Optimization Problems

This paper presents a systematic review on reinforcement learning approaches for combinatorial optimization problems based on real-world industrial applications. While this topic is increasing in popularity, explicit implementation details are not always available in the literature. The main objective of this paper is characterizing the agent–environment interactions, namely, the state space representation, action space mapping and reward design. Also, the main limitations for practical implementation and the needed future developments are identified. The literature selected covers a wide range of industrial combinatorial optimization problems, found in the IEEE Xplore, Scopus and Web of Science databases. A total of 715 unique papers were extracted from the query. Then, out-of-scope applications, reviews, surveys and papers with insufficient implementation details were removed. This resulted in a total of 298 papers that align with the focus of the review with sufficient implementation details. The state space representation shows the most variety, while the reward design is based on combinations of different modules. The presented studies use a large variety of features and strategies. However, one of the main limitations is that even with state-of-the-art complex models the scalability issues of increasing problem complexity cannot be fully solved. No methods were used to assess risk of biases or automatically synthesize the results.

Model predictive control for risk-based inspection and maintenance planning of offshore wind turbines

ABSTRACT Offshore wind turbines (OWTs) are highly susceptible to fatigue deterioration under extreme environmental conditions, making optimal inspection and maintenance (I&M) planning critical for their safe and sustainable operation. The dynamic nature of weather and complex deterioration processes challenge the long-term effectiveness of maintenance strategies. Moreover, I&M policies often become outdated when deterioration models are updated. Unlike traditional approaches that rely on a fixed life-span horizon, effective I&M planning must adapt to evolving conditions and varying planning horizons. This paper introduces a model predictive control (MPC) method for adaptive, risk-based I&M planning of OWTs. The closed-loop MPC approach provides flexibility by dynamically adjusting inspection and maintenance strategies based on evolving fatigue risks. We propose an augmented state-space model that captures the impact of probabilistic I&M actions on fatigue failure risks over time. A finite-horizon optimal control problem is then formulated to derive the MPC controller, which balances fatigue risk and I&M costs over the planning horizon. The proposed method is demonstrated using a fatigue-prone OWT component. Results show that the MPC controller effectively manages the trade-off between fatigue risk and maintenance costs while remaining adaptable to different planning horizons and decision-making preferences.

Iterative Learning Control Applied to Interconnected RGB Light Strip

In this paper, an iterative learning control scheme is applied to the interconnected RGB light strip modeled with so-called spatially interconnected systems. The proposed strategy starts with formulating a set of Kirchhoff equalities, which lead to the 2D state-space model. In the next step, the system model is transformed into its 1D equivalent using the so-called lifting approach. Subsequently, the ILC design strategy is proposed. Due to the fact that it eventually takes the form of a differential linear repetitive process, the well-established stability theory along the trial is applied. This enables the application of computationally efficient stability tests, which employ linear matrix inequalities. Such a strategy ensures a numerically tractable design procedure. The application of this strategy ensures the convergence of the output signal to the desired reference. It is important to emphasize that the considered system can be affected by disturbances, and hence, it reflects practical situations that are inevitable in engineering practice. The effectiveness of the proposed approach is illustrated with a comprehensive simulation study.

An Enhanced Time Delay Smith Predictor of Sliding Mode Structural Vibration Controller Based on Extended State Observer

Considering the total disturbances such as system time delay, model uncertainty, actuator effect and dynamic nonlinearities, a composite control strategy is proposed to suppress vibrations in an all-clamped plate structure, which combines sliding mode control based on extended state observer with time delay compensation (TDCSMCESO). First, a second-order state-space representation of the all-clamped plate, equipped with an inertial actuator, is formulated through the analysis of the dynamic partial differential equation and the physical model of the thin plate. Second, due to the inevitable system time delay and the noise amplification of the traditional differentiator, an enhanced differentiator is proposed to make the system without time delay. Additionally, a sliding mode control approach based on extended state observer (SMCESO) is designed to estimate and compensate for the total disturbance through a feedforward mechanism. Third, the closed-loop system’s stability is established through the application of the Lyapunov stability method. Finally, a semi-physical experimental platform utilizing an NI-PCIe6343 acquisition card and Matlab/Simulink environment is constructed to assess and compare the effectiveness of the proposed TDCSMCESO with SMCESO and traditional predictor-based SMCESO (PSMCESO). Comparative experiments show that the TDCSMCESO controller exhibits improved disturbance resistance and vibration reduction capabilities.