Data Fusion Model Research Articles

Anomalous wet summers and rising atmospheric CO2 concentrations increase the CO2 sink in a poorly drained forest on permafrost

At the northern high latitudes, rapid warming, associated changes in the hydrological cycle, and rising atmospheric CO2 concentrations, [CO2], are observed at present. Under rapid environmental changes, it is important to understand the current and future trajectories of the CO2 budget in high-latitude ecosystems. In this study, we present the importance of anomalous wet conditions and rising [CO2] on the long-term CO2 budget based on two decades (2003-2022) of quasicontinuous measurements of CO2 flux at a poorly drained black spruce forest on permafrost peat in interior Alaska. The long-term CO2 budget for the black spruce forest was a small sink of -53 ± 63 g C m-2 y-1. The CO2 sink increased from 49 g C m-2 y-1 for the first decade to 58 g C m-2 y-1 for the second decade. The increased CO2 sink was attributed to an 11.3% increase in gross primary productivity (GPP) among which 9% increase in GPP was explained by a recent increase in precipitation. Furthermore, a 3% increase in GPP in response to a 37-ppm increase in [CO2] was estimated from the data-model fusion. Our study shows that understanding the coupling between hydrological and carbon cycles and the CO2 fertilization effect is important for understanding the current and future carbon budgets of high-latitude ecosystems in permafrost regions.

An efficient data fusion model based on Bayesian model averaging for robust water quality prediction using deep learning strategies

Accurate monitoring of dissolved oxygen (DO) levels is critical for stakeholders to effectively safeguard water resources and aquatic ecosystem health. This research presents an innovative data fusion framework based on Bayesian model averaging (BMA) by the combination of several neuroscience models (deep learning methodologies) including multilayer perceptron neural network (MLPNN), recurrent neural network (RNN), convolutional neural network (CNN), gated recurrent unit (GRU), long short-term memory (LSTM), and seasonal autoregressive integrated moving average with exogenous variables (SARIMAX). BMA has the capacity to greatly enhance the results attained by standalone approaches. In this study, two feature selection methods such as mutual information (MI) and recursive feature elimination (RFE) applied to select effective predictors and investigate the importance of each input parameters. The techniques were evaluated based on four different metrics and, finally, to demonstrate the usefulness and effectiveness of the newly implemented strategy, it was applied proficiently at the USGS stations, 01427510 and 02336152 within the USA. The findings from analyzing data based on two stations confirmed that the suggested approach (BMA) outperformed other methods such as MLPNN, RNN, CNN, LSTM, and SARIMAX when it came to predicting the levels of DO on a daily basis. In terms of RMSE, MAE and R2, BMA yielded 0.272 mg/L, 0.216 mg/L, and 0.975 using MI technique and 0.320 mg/L, 0.261 mg/L, and 0.965 using RFE method at 01427510 USGS station, respectively. Similarly, based on RMSE, MAE and R2, BMA produced DO prediction by RMSE = 0.352 mg/L, 0.264 mg/L, and 0.968 by MI approach and RMSE = 0.378 mg/L, 0.282 mg/L, and 0.963 via RFE process at 02336152 USGS station, respectively. After analyzing different combinations of input that obtained from feature selection paradigms, it was observed that the variables with the greatest impact on daily dissolved oxygen levels are the dissolved oxygen levels in the previous time period and the water temperature. On the other hand, the pH and turbidity have minimal influence on the daily DO. Finally, the results of this study confirmed that the BMA tool can be efficiently applied to predict DO concentration based on deep learning model outputs.

A novel approach to the cause of death identification—multi-strategy integration of multi-organ FTIR spectroscopy information using machine learning

Identifying the cause of death has always been a major focus and challenge in forensic practice and research. Traditional techniques for determining the causes of death are time-consuming, labor-intensive, have high professional barriers, and are vulnerable to significant subjective bias. Additionally, most current studies on causes of death are limited to specific organs and single causes. To overcome these challenges, this study utilized simple and rapid fourier transform infrared spectroscopy (FTIR) detection technology, integrating data from six organs—heart, liver, spleen, lung, kidney, and brain. The optimum model for identifying seven different causes of death was determined by evaluating the performance of models developed using the model efficiencies of single-organ (SO), single-organ model fusion (SOMF), multi-organ data fusion (MODF), and multi-organ data model fusion (MODMF) modeling methods. Considering factors such as operational costs, model performance, and model complexity, the MODF artificial neural network (ANN) model was found to be the most suitable choice for constructing a cause of death identification model, with a cross-validation mean accuracy of 0.960 and a test set accuracy of 0.952. The heart and kidney contributed more spectral features to the construction of the cause of death identification model compared to other organs. This study not only demonstrated that data fusion and model fusion are effective strategies for improving model performance but also provided a comprehensive data analysis framework and process for modeling with small sample multi-modal data (multiple organ data). In conclusion, by exploring various approaches, this study offers new solutions for identifying the cause of death.

Remote marine precise point positioning with baseline length and troposphere-constrained models of the receivers for the oceanographic research vessel

ABSTRACT Research vessels are typically equipped with multiple receivers for positioning and attitude measurement; however, there is no data interaction or model fusion to implement the Precise Point Positioning (PPP) for these receivers. Therefore, a Constrained PPP (CPPP) is established by using the baseline length and tropospheric constraints of two receivers to improve the vessel’s remote marine positioning performance. Based on two integrated Real-Time Kinematic (RTK) receivers, marine experiments are conducted at a distance of 300–600 km from land. Compared to the ground environment, the Root Mean Square error (RMS) of the multipath and the STandard Deviation (STD) of the carrier-to-noise ratio in the marine environment are increased by 2.87 and 2.6 times, respectively. The length constraints reduce the RMS of positioning in the East, North, and Up (ENU) directions by about 0.053 (67%), 0.020 (34%), and 0.054 m (34%), respectively, and also rapidly recover positioning after interruptions, achieving positioning with errors in the ENU-directions of 10, 15, and 20 cm, respectively, within 3 minutes. When the baseline length and tropospheric constraints are combined, with or without the addition of the Zenith Wet Delay bias (dZWD), the average STD can be reduced by about 0.060 m (43%) and the accuracy of the up-positioning can be significantly improved. The correlation of dZWD to the up-positioning deviation of du=−2.161*dZWD is obtained by simulation. Since the acquisition of dZWD depends on the PPP accuracy, it is recommended that dZWD be set to compensate for unmodeled receiver errors when the STD of the up-positioning is superior to 0.06 m.

Dynamic numerical calculation of multi-physics fields in IGBT chip layer based on ETM-PINN

The electric-thermal-mechanical (ETM) multi-physics coupling fields commonly exists in power electronic devices such as insulate-gate bipolar transistor (IGBT), which dominates the evolution of key state variables inside the components. Among them, the junction e and electric potential of the chip layer, as the dependent variables of various lifetime physical models, directly affect its remaining service life and health status. Aiming at the problem that the key physical variables inside the IGBT are difficult to monitor and predict, this paper first integrates and establishes the ETM coupling partial differential equations (PDEs) inside the IGBT, then accordingly proposes an accurate numerical calculation method for coupled physical fields based on ETM-physics-informed neural networks (ETM-PINN).Through relevant simulation verification, it can not only realize the numerical calculation of the chip layer junction temperature and electric potential field without data, but also perform multi-physics predictive calculation with reduced accuracy in the absence of the key coefficients in PDEs. In the presence of additional physical field data, it can also perform data-model fusion calculations to further improve the solution accuracy.

Data Fusion for Enhancing Urban Air Quality Modeling using Large-Scale Citizen Science

Rapid urbanization has led to many environmental issues, including poor air quality. With urbanization set to continue, there is an urgent need to mitigate air pollution and minimize its adverse health impacts. This study aims to advance urban air quality management by integrating a dispersion model output with large-scale citizen science data, collected over a 4-week period by 642 participants in Cork City, Ireland. The dispersion model enabled the identification of major sources of NO2 air pollution while also addressing gaps in regulatory monitoring efforts. Integrating the diffusion tube data with the dispersion model output, we developed a data fusion model that captured localized fluctuations in air quality, with increases of up to 22μg/m3 observed at major road intersections. The data fusion model provided a more accurate representation of NO2 concentrations, with estimates within 1.3μg/m3 of the regulatory monitoring measurement at an urban traffic location, an improvement of 11.7μg/m3 from the priori dispersion model. This enhanced accuracy enabled a more precise assessment of the population exposure to air pollution. The data fusion model showed a higher population exposure to NO2 compared to the dispersion model, providing valuable insights that can inform environmental health policies aimed at safeguarding public health.

Modeling of zirconium alloy cladding corrosion behavior based on neural ordinary differential equation

Current zirconium alloy cladding corrosion models are mainly semi-empirical and show significant dispersion when compared to measured data. This study introduces neural ordinary differential equation (neural ODE) to model corrosion behavior, utilizing data-model fusion approach for network training. Initially, a semi-empirical model for zirconium alloy cladding corrosion is established through differential evolution algorithm, generating a large dataset for pre-training the neural network. The network is then fine-tuned using measured data. These methods effectively address the challenges of sparse cladding corrosion data and data available only at fixed time points, resulting in a more accurate model. The results shows that the differential evolution algorithm can identify a set of appropriate parameters for the semi-empirical model, achieving a standard deviation of 0.040. The neural ODE model demonstrates even higher accuracy, reducing the standard deviation to 0.031 and improving accuracy by approximately 25%. Additionally, the model demonstrates excellent generalization capacity on other time points and new power histories.

Multi-Modal Fusion Network with Multi-Head Self-Attention for Injection Training Evaluation in Medical Education

The COVID-19 pandemic has significantly disrupted traditional medical training, particularly in critical areas such as the injection process, which require expert supervision. To address the challenges posed by reduced face-to-face interactions, this study introduces a multi-modal fusion network designed to evaluate the timing and motion aspects of the injection training process in medical education. The proposed framework integrates 3D reconstructed data and 2D images of hand movements during the injection process. The 3D data are preprocessed and encoded by a Long Short-Term Memory (LSTM) network to extract temporal features, while a Convolutional Neural Network (CNN) processes the 2D images to capture detailed image features. These encoded features are then fused and refined through a proposed multi-head self-attention module, which enhances the model’s ability to capture and weigh important temporal and image dynamics in the injection process. The final classification of the injection process is conducted by a classifier module. The model’s performance was rigorously evaluated using video data from 255 subjects with assessments made by professional physicians according to the Objective Structured Assessment of Technical Skill—Global Rating Score (OSATS-GRS)[B] criteria for time and motion evaluation. The experimental results demonstrate that the proposed data fusion model achieves an accuracy of 0.7238, an F1-score of 0.7060, a precision of 0.7339, a recall of 0.7238, and an AUC of 0.8343. These findings highlight the model’s potential as an effective tool for providing objective feedback in medical injection training, offering a scalable solution for the post-pandemic evolution of medical education.

Night Lighting Fault Detection Based on Improved YOLOv5

Night lighting is essential for urban life, and the occurrence of faults can significantly affect the presentation of lighting effects. Many reasons can cause lighting faults, including the damage of lamps and circuits, and the typical manifestation of the faults is that the lights do not light up. The current troubleshooting mainly relies on artificial visual inspection, making detecting faults difficult and time-consuming. Therefore, it is necessary to introduce technical means to detect lighting faults. However, current research on lighting fault detection mainly focuses on using non-visual methods such as sensor data analysis, which has the disadvantages of having a high cost and difficulty adapting to large-scale fault detection. Therefore, this study mainly focuses on solving the problem of the automatic detection of night lighting faults using machine vision methods, especially object detection methods. Based on the YOLOv5 model, two data fusion models have been developed based on the characteristics of lighting fault detection inverse problems: YOLOv5 Channel Concatenation and YOLOv5 Image Fusion. Based on the dataset obtained from the developed automatic image collection and annotation system, the training and evaluation of these three models, including the original YOLOv5, YOLOv5 Channel Concatenation, and YOLOv5 Image Fusion, have been completed. Research has found that applying complete lighting images is essential for the problem of lighting fault detection. The developed Image Fusion model can effectively fuse information and accurately detect the occurrence and area of faults, with a mAP value of 0.984. This study is expected to play an essential role in the intelligent development of urban night lighting.

Enhanced offshore wind resource assessment using hybrid data fusion and numerical models

Wind resource assessments are crucial for pre-construction planning of wind farms, especially offshore. This study proposes a novel hybrid model integrating Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Empirical Wavelet Transform (EWT) for enhanced wind speed forecasting. This secondary decomposition reduces forecasting complexity by processing high-frequency signals. A Bidirectional Long Short-Term Memory (BiLSTM) neural network optimized with the Grey Wolf Optimizer (GWO) is then employed for forecasting. The model’s accuracy is evaluated using simulated wind speeds along the coast of Denmark, combined with lidar measurements through data fusion. This approach demonstrates significant improvements in prediction accuracy, highlighting its potential for offshore wind resource assessment.

A low-power consumption security data fusion model for Industrial Internet of Things

Industrial Internet of Things (IIOT) is an important part of manufacturing industry in the future, and the front-end sensor data acquisition network is the core component of it. Due to the limited energy of IIOT, reducing transmission interaction, energy consumption, and computational complexity in the process of data transmission is the key and difficult point in designing model of IIOT. In this paper, a lightweight green security data fusion model for IIOT is proposed, called LCSDF model, which aims to achieve data security and integrity verifiability by using less energy consumption. The simulation results show that the proposed model can ensure data security and verifiability, and meet the energy consumption requirements of the system. The performance of the algorithm is also satisfactory, reflecting the lightweight, green, and security of the model.

Travel Time Estimation for Urban Arterials Based on the Multi-Source Data

Accurate traffic information, such as travel time, becomes more important since it could help provide more efficient traffic management strategies. This paper presents a method for estimating the travel time of segments on urban arterials by leveraging multi-source data from loop detectors and probe vehicles. Travel time is defined into three distinct sections based on floating car trajectories, i.e., accelerating, constant speed, and decelerating. Considering the traffic flow characteristics, different methods are developed using various data for each section. The proposed methodology is validated using field data collected in Shanghai, China. The results validated the proposed method with absolute percentage errors (APEs) of approximately 5% in constrained traffic flow conditions and 10–20% in less constrained traffic flow. The results also show that the proposed method has better performance than the method with loop detector data and another data fusion model. It is expected that the proposed method could help improve traffic management efficiency, such as traffic signal control, by providing more accurate travel time information.

A comprehensive assessment approach for multiscale regional economic development: Fusion modeling of nighttime lights and OpenStreetMap data

Assessing regional economic development is key for advancing towards the Sustainable Development Goals and ensuring sustainable societal progress. Traditional evaluation methods focus on basic economic metrics like population and capital, which may not fully reflect the complexities of economic activities. Nighttime light (NTL) has been validated as an alternative indicator for regional economic development, yet limitations persist in its evaluation. This study integrates OpenStreetMap (OSM) data and NTL data, providing a novel data integration approach for evaluating economic development. The study uses mainland China as a case, applying Ordinary Least Squares (OLS) and Geographically Weighted Regression (GWR) to evaluate OSM and NTL data across provincial, municipal, and county levels. It compares OSM, NTL, and their combined use, providing key empirical insights for enhancing data fusion models. The study results reveal: (1) NTL data is more accurate for provincial-level economic activity, while OSM data excels at the county level. (2) GWR demonstrates superior capability over OLS in revealing the spatial dynamics of economic development across scales. (3) Through the integration of both datasets, it is observed that, compared to single-data modeling, the performance is enhanced at the city scale and county scale. The study demonstrates that combining OSM and NTL data effectively assesses economic development in both developed and underdeveloped areas at provincial, municipal, and county levels. The study offers a straightforward and efficient approach to data integration. The findings offer new research perspectives and scientific support for sustainable regional economic growth, particularly valuable in data-scarce, underdeveloped areas.

Droplet volume prediction methods in electrohydrodynamic jet printing based on multi-source data fusion

Electrohydrodynamic jet printing technology has garnered significant interest in additive manufacturing due to its advantages in higher resolution printing and greater viscosity material applicability. Nonetheless, the challenges associated with femtoliter-level droplets and the micrometer-scale printing space have rendered traditional optical observation methods for volume calculation impractical for integration into the printing systems. Obtaining the droplet volume accurately has become a formidable challenge in electrohydrodynamic printing. While existing research utilizes machine learning for the end-to-end prediction of process parameters to droplet volume, traditional prediction methods cannot achieve online prediction due to the complex spray states characteristic of electrohydrodynamic jet printing and pose integration difficulties within printing systems. This paper introduces a multi-source data fusion model suitable for electrohydrodynamic printing droplet volume prediction. The model employs the VGG network to extract features from Taylor cone images in the jetting state and synchronously fuse these with process parameter features. The fused features are then correlated with droplet volume labels through the MLP network for comprehensive model training. The performance of the proposed model has improved by 10% in prediction accuracy compared to single modal data. We integrated the prediction method into an electrohydrodynamic jet printing system and experimented with printing pixel-pit substrates. The results indicate that the prediction accuracy of the volume prediction system is over 92%. The printing efficiency has improved approximately 3 times compared to the traditional method, significantly enhancing overall performance.

Exploring the optimal sequences for fusing land surface temperature via spatiotemporal fusion: ‘retrieval-then-fusion’ or ‘fusion-then-retrieval’?

ABSTRACT Due to the limitations inherent in satellite sensor capabilities, it remains a challenge to balance the temporal and spatial resolutions of current remote sensing observations. Spatiotemporal fusion has emerged as a viable approach to address this issue. Many spatiotemporal fusion models have been proposed to fuse surface reflectance initially; however, their adaption for land surface temperature (LST), particularly with the ‘fusion-then-retrieval (FTR)’ or ‘retrieval-then-fusion (RTF)’ strategy, has not yet been comprehensively explored. This paper describes a comparative study of the two strategies within the context of LST fusion using three classic fusion methods including the spatial and temporal adaptive reflectance fusion model (STARFM), the enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM) and the flexible spatiotemporal data fusion model (FSDAF). The findings illuminate nuanced applicability across different models: (1) the FTR strategy is more suitable for STARFM; (2) the strategic applicability for ESTARFM and FSDAF is strongly related to the reference images; (3) the STARFM and FSDAF models are easily affected by the time interval between the predicted date and the reference date. This work is expected to provide practical guidance for synthesizing high spatiotemporal LST data with fusion models.

Developing a new active canopy sensor- and machine learning-based in-season rice nitrogen status diagnosis and recommendation strategy

ContextTraditional critical nitrogen (N) dilution curve (CNDC) construction for N nutrition index (NNI) determination has limitations for in-season crop N diagnosis and recommendation under diverse on-farm conditions. ObjectivesThis study was conducted to (i) develop a new rice (Oryza sativa L.) critical N concentration (Nc) determination approach using vegetation index-based CNDCs; and (ii) develop an N recommendation strategy with this new Nc determination approach and evaluate its reliability and practicality. MethodsFive years of plot and on-farm experiments involving three japonica rice varieties were conducted at fourteen sites in Qixing Farm, Northeast China. Two machine learning (ML) methods, random forest (RF) and extended gradient boosting (XGBoost) regression, were used to fuse multi-source data including genotype, environment, management, growth stage, normalized difference vegetation index (NDVI) and normalized difference red edge (NDRE) from portable active canopy sensor RapidSCAN. The CNDC was established using NDVI and NDRE instead of aboveground biomass (AGB) measured by destructive sampling. A new in-season N diagnosis and recommendation strategy was further developed using direct and indirect NNI prediction using multi-source data fusion and ML models. ResultsThe new CNDC based on NDVI or NDRE explained 94−96 % of Nc variability in the evaluation dataset when it was coupled with environmental and agronomic factors using ML models. The ML-based PNC and NNI prediction models explained 85 % and 21–36 % more variability over simple regression models using NDVI or NDRE in the evaluation dataset, respectively. The new in-season N diagnosis strategy using the NDVI and NDRE-based CNDCs and plant N concentration (PNC) predicted with RF model and multi-source data fusion performed slightly better than direct NNI prediction, explaining 7 % more of NNI variability and achieving 89 % of the areal agreement for N diagnosis across all evaluation experiments. Integrating this new N management strategy into the precision rice management system (as ML_PRM) increased yield, N use efficiency (NUE) and economic benefits over farmer’s practice (FP) by 7–15 %, 11–71 % and 4–16 % (161–596 $ ha−1), respectively, and increased NUE by 11–26 % and economic benefits by 8–97 $ ha−1 than regional optimum rice management (RORM) under rice N surplus status under on-farm conditions. ConclusionsIn-season rice N status diagnosis can be improved using NDVI- and NDRE-based CNDC and PNC predicted by ML modeling with multi-source data fusion. ImplicationsThe active canopy sensor- and ML-based in-season N diagnosis and management strategy is more practical for applications under diverse on-farm conditions and has the potential to improve rice yield and ecological and economic benefits.

Enhanced Kalman filter methods for end pose measurement of parallel kinematic machine considering the error sensitivity

For robust accuracy, this paper proposes a parallel measurement method for parallel kinematic machine (PKM) combining indirect measurement using grating ruler with direct measurement using monocular vision. However, due to differing error sensitivity of two methods, the general Kalman filter (KF) cannot integrate them under the assumption of equal data weighting. Therefore, a novel Enhanced KF data fusion method designed to account for varying data sensitivities is developed.The paper first outlines the principles of parallel measurement approach for PKMs, followed by modeling the error sensitivities associated with each measurement source. Subsequently, an enhanced KF data fusion model is developed, treating these sensitivities as noise, and validated. Compared to the conventional KF method, the root mean squared (RMS) position error is significantly reduced from 0.569 mm to 0.293 mm. This enhanced KF method presents an innovative approach to multi-source data fusion, tailored to the error characteristics of different measurement sources.

Spatial Data Fusion Model Design and Research for an Underground Pipeline in Urban Environment Scene Modeling

Spatial Data Fusion Model Design and Research for an Underground Pipeline in Urban Environment Scene Modeling

Dual Kalman Filter Based on a Single Direction under Colored Measurement Noise for INS-Based Integrated Human Localization

For inertial-based integrated pedestrian navigation, the navigation environment might affect the positioning accuracy in different directions. Meanwhile, complex filtering algorithms can reduce computational efficiency. Therefore, one dual Kalman filter (KF) based on a single direction under a colored measurement noise (CMN) scheme is developed herein to improve the robustness and operational efficiency. The proposed method involves designing a data fusion model for the KF that integrates data from an inertial navigation system (INS) and ultrawideband (UWB). Subsequently, the INS/UWB integrated model-based KF under CMN (cKF) will be derived. Then, two sub-cKFs are proposed to fuse the data in the east and north directions, respectively. The empirical findings highlight the superior performance of the proposed approach over the KF for position estimation accuracy and runtime reduction, demonstrating its effectiveness.

Research on the Construction of a Digital Twin System for the Long-Term Service Monitoring of Port Terminals

Structural damage is a prevalent issue in long-term operations of harbor terminals. Addressing the lack of transparency in terminal infrastructure components, the limited integration of sensor monitoring data, and the insufficient support for feedback on service performance, we propose a novel digital twin system construction methodology tailored for the long-term monitoring of port terminals. This study elaborates on the organization and processing of foundational geospatial data, sensor monitoring information, and oceanic hydrometeorological data essential for constructing a digital twin of the terminal. By mapping relationships between physical and virtual spaces, we developed comprehensive dynamic and static models of terminal facilities. Employing a “particle model” approach, we visually represented oceanic and meteorological elements. Additionally, we developed a multi-source heterogeneous data fusion model to facilitate the rapid creation of data indexes for harbor elements under high concurrency conditions, effectively addressing performance issues related to scene-rendering visualization and real-time sensor data storage efficiency. Experimental validation demonstrates that this method enables the rapid construction of digital twin systems for port terminals and supports practical application in business scenarios. Data analysis and comparison confirm the feasibility of the proposed method, providing an effective approach for the long-term monitoring of port terminal operations.