Normalized Root Mean Research Articles

A multi-criteria decision analysis approach for ranking the performance of CMIP6 models in reproducing precipitation patterns over Abaya-Chamo sub-basin, Ethiopia

The most suitable multi-model ensemble set of general circulation models is used to reduce the uncertainty associated with GCM selection and improve the accuracy of the model simulations. This study evaluated the performance of 20 global climate models participating in the Coupled Model Intercomparison Project Phase 6 (CMIP6) in reproducing precipitation patterns over the Abaya-Chamo Sub-basin, Ethiopia. For the validation and selection of the models' capabilities, datasets from the Climate Hazards Infrared Precipitation with Stations (CHIRPS) were used after comparing them with ground observational datasets. The objective was to identify the most suitable multi-model ensemble (MME) of a subset of CMIP6 GCMs to capture the rainfall for the 1981–2014 period over the region. Climate Data Operators (CDOs) were used in climate data processing and extraction, and the Mann-Kendall test and Theil-Sen slope estimator methods were utilized to analyze the trends of the CMIP6 simulations. Four statistical metrics (Nash-Sutcliffe coefficient, percent bias, normalized root mean square error, and Kling-Gupta efficiency) were used to further assess the performance of the models. A multi-criteria decision analysis approach, namely, the technique for order preferences by similarity to an ideal solution (TOPSIS) method, was used to obtain the overall ranks of CMIP6 models and to select the best-performing CMIP6 model in the region. The results indicated that CHIRPS and most of the CMIP6 simulations generally reproduced bimodal precipitation patterns over the region. The CESM2-WACCM, NorESM2-MM, NorESM2-LM, and NorESM2-LM models performed better than the other models in reproducing seasonal patterns for the winter, spring, summer, and autumn seasons, respectively. On the other hand, FGOALS-f3-L revealed the trends of the reference datasets for all seasons. In terms of the NSE, PB, NRMSE, and KGE metrics, EC-Earth3-C, EC-Earth3, EC-Earth3-C, and EC-Earth-C, respectively, were considered good at representing the observed features of precipitation over the region. EC-Earth3-C,EC-Earth3, EC-Earth3-Veg-LR, ACCESS-CM2, MPI-ESM1-2-HR, and CNRM-CM6-1-HR exhibited the best performances in the Abaya-Chamo Sub-basin.

Statistical Downscaling of Remote Sensing Precipitation Estimates Using MODIS Cloud Properties Data over Northeastern Greece

The aim of this study is to spatially downscale the daily precipitation data from the Global Precipitation Measurement (GPM) mission, using the Integrated Multi-satellite Retrievals for GPM (IMERG), utilizing cloud properties from the Moderate Resolution Imaging Spectroradiometer (MODIS) instrument. Cloud optical thickness (COT), cloud effective radius (CER), and cloud water path (CWP) are used to statistically downscale IMERG precipitation estimates from 0.1 to 0.01° spatial resolution, using the Multivariate Linear Regression (MLR) and residual correction methods. The downscaled precipitation estimates were subsequently validated using in situ rain gauge measurements. The residual corrected IMERG downscaled precipitation estimates were found to be more accurate than the downscaled predicted precipitation without the implementation of the residual correction algorithm (up to 37%), with a respective decrease of the Root Mean Square Error (RMSE) (up to 75%), Normalized Root Mean Square Error (NRMSE) (up to 79%), and the Percent Bias (PB) (up to 98%). In addition, the final downscaled product after the MLR method implementation with residual correction was better correlated with the rain gauge observations than the initial IMERG product (up to 20%). Thus, the implementation of the MLR method in conjunction with the residual correction algorithm is an efficient tool for downscaling remote sensing products with a coarse spatial resolution.

Study of the Optical and Structural Properties of Metal-Doped Titanium Dioxide Electrode Prepared by the Sol-Gel Method for Dye-Sensitized Solar Cells

This study presents a strategy to increase the efficiency of dye-sensitized solar cells (DSSCs) by doping titanium dioxide (TiO2) with different magnesium (Mn) concentrations (1, 3, 5, 7, and 9%) generated by the sol-gel process and effectively employed as a photo-anode (the working electrode) for DSSCs. The Doctor Blade method coated the indium-doped tin oxide (ITO) glass with a thin film layer. X-ray diffraction (XRD) was used to evaluate the characteristics of undoped and manganese-doped TiO2, and the results demonstrate that all of the thin films are anatase. The samples were examined using XRD to assess grain size before and after Mn doping. The spectrum of UV-Vis absorption changes; accordingly, as doping increases, the energy gap decreases. The smallest energy gap's value (2.4 eV) is 7% manganese doping. AFM pictures show the average roughness and root mean square of the weight percentage of films doped with 5%. Field effect scanning electron microscope (FE-SEM) studies show that the particle size of thin films gets smaller as more Mn is added, which happens at least as much as 7% Mn doping. The optimal thickness for TiO2 paste over conductive glass is 15 μm, and the cell's power conversion efficiency increased to 0.604074% with an Imax of 4.965 mA, a Vmax of 0.488 V, and a fill factor (FF) of 68.45954%.

Traffic Noise Modeling under Mixed Traffic Condition in Mid-Sized Indian City: A Linear Regression and Neural Network-Based Approach

Noise pollution is a significant concern in urban settings, caused by traffic increases, urban expansion, and industrial activity. The transportation sector is a crucial contributor to overall noise pollution, particularly in India, where different vehicles ply the roads, resulting in highly fluctuating noise levels. Consequently, traffic noise modeling is essential for addressing this severe issue. The present study employs the MLR (Multiple Linear Regression) and Artificial Neural Network (ANN) approach to model and predict traffic-induced noise levels. The ANN approach outperforms the MLR technique. The architecture of the ANN model integrates different vehicle categories and average speeds as input, resulting in precise predictions. Evaluation of the model’s performance reveals an average Root Mean Squared Error (RMSE) of 0.204 and a high Coefficient of determination (R2) value of 0.93, emphasizing its accuracy. Similarly, in the case of MLR model the RMSE for the training and testing dataset are 1.55 and 1.69 dBA, respectively with R2 value of 0.84. Subsequently, sensitivity analysis highlights the substantial impact of 2-wheelers, tractors/trailers, and 3-wheelers on noise predictions. This study contributes valuable insights into noise management, urban planning, and sustainable development. It demonstrates the efficiency of the ANN approach in addressing complex noise pollution challenges, offering a path toward quieter and healthier urban environments.

Enhancing winter wheat prediction with genomics, phenomics and environmental data

In the realm of multi-environment prediction, when the goal is to predict a complete environment using the others as a training set, the efficiency of genomic selection (GS) falls short of expectations. Genotype by environment interaction poses a challenge in achieving high prediction accuracies. Consequently, current efforts are focused on enhancing efficiency by integrating various types of inputs, such as phenomics data, environmental information, and other omics data. In this study, we sought to evaluate the impact of incorporating environmental information into the modeling process, in addition to genomic and phenomics information. Our evaluation encompassed five data sets of soft white winter wheat, and the results revealed a significant improvement in prediction accuracy, as measured by the normalized root mean square error (NRMSE), through the integration of environmental information. Notably, there was an average gain in prediction accuracy of 49.19% in terms of NRMSE across the data sets. Moreover, the observed prediction accuracy ranged from 5.68% (data set 3) to 60.36% (data set 4), underscoring the substantial effect of integrating environmental information. By including genomic, phenomic, and environmental data in prediction models, plant breeding programs can improve selection efficiency across locations.

In-plane testing and hysteretic modeling of steel-spline cross-laminated timber diaphragm connection with self-tapping screws

ABSTRACT This study examines experimentally and numerically the in-plane behavior of a steel-spline Cross-Laminated Timber (CLT) connection with self-tapping screws. Although this connection is a strong, rapid, and cost-effective alternative suitable for CLT diaphragms of tall timber-concrete buildings, no previous cyclic/monotonic testing has been documented. Two specimens were tested under axial and in-plane shear loads, where a ductile failure mode was observed due to bending and withdrawal of screws, and deformation and buckling of the strap. Mechanic properties, such as strength capacity, stiffness, ductility, energy dissipation, equivalent viscous damping, stiffness/strength degradation, and damage index characterize the joint. Furthermore, the yield point and ductility were calculated with the EEEP, CEN, and Yasumura–Kawai methods, the last approach most accurate, with a mean ductility of 7.25 and 5.50 for the axial and in-plane shear tests, respectively. Overstrength factors of about 2.6 and 1.9 were also estimated for respective tests by comparing analytical expressions from timber codes and literature. Finally, three numerical models (SAWS, DowelType, and ASPID) were assessed to measure their epistemic uncertainty, showing an adequate force and dissipated energy history simulation, with a normalized root mean square less than 8.8% and 4.5%, and R 2 over 87% and 97%, respectively.

Bathymetry reconstruction from experimental data using PDE-constrained optimisation

Knowledge of the bottom topography, also called bathymetry, of rivers, seas or the ocean is important for many areas of maritime science and civil engineering. While direct measurements are possible, they are time consuming, expensive and inaccurate. Therefore, many approaches have been proposed how to infer the bathymetry from measurements of surface waves. Mathematically, this is an inverse problem where an unknown system state needs to be reconstructed from observations with a suitable model for the flow as constraint. In many cases, the shallow water equations can be used to describe the flow. While theoretical studies of the efficacy of such a PDE-constrained optimisation approach for bathymetry reconstruction exist, there seem to be few publications that study its application to data obtained from real-world measurements. This paper shows that the approach can, at least qualitatively, reconstruct a Gaussian-shaped bathymetry in a wave flume from measurements of the free surface level at up to three points. Achieved normalised root mean square errors (NRMSE) are in line with other approaches.

Assessment of the accuracy of 3D printed medical models through reverse engineering

The dimensional accuracy of additively manufactured (3D printed) medical models can be affected by various parameters. Although different methods are used to evaluate the accuracy of additively manufactured models, this study focused on the investigation of the dimensional accuracy of the medical model based the combination of reverse engineering (RE) and additive manufacturing (AM) technologies. Human femur bone was constructed from CT images and manufactured, using Fortus 450mc Industrial material extrusion 3D Printer. The additive manufactured femur bone was subsequently 3D scanned using three distinct non-contact 3D scanners. MeshLab was used for mesh analysis, while VX Elements was used for post-processing of the point cloud. A combination of the VX Inspect environment and MeshLab was used to evaluate the scanning performance. The deviation of the 3D scanned 3D models from the reference mesh was determined using relative metrics and absolute measurements. The scanners reported deviations ranging from −0.375 mm to 0.388 mm, resulting in a total range of approximately 0.763 mm with average root mean square (RMS) deviation of 0.22 mm. The results indicate that the additively manufactured model, as measured by 3D scanning, has a mean deviation with an average range of approximately 0.46 mm and an average mean value of around 0.16 mm.

Deep learning-based inversion framework by assimilating hydrogeological and geophysical data for an enhanced geothermal system characterization and thermal performance prediction

Enhanced geothermal systems (EGS), which are developed by creating artificial fractures to enhance the permeability of deep reservoir, show their its advantage in power generation. However, due to the limited wells in deep depth, characterizing fractured geothermal reservoirs with sparse data is difficult and poses challenges for long-term thermal performance prediction. Interpreting observation data through inversion to characterize the fracture aperture and predict EGS long-term thermal performance is a hopeful scheme. Thus, a joint inversion framework, convolutional variational autoencoder-ensemble smoother with multiple data assimilation (CVAE-ESMDA), is proposed with the following aspects: (i) CVAE is trained to parameterize the high-dimensional Non-Gaussian aperture field, (ii) ESMDA is applied to integrate hydrogeological and geophysical data for aperture characterization. Based on the inversion results, the long-term performance is predicted. The normalized root mean square errors (NRMSEs) of inversion results decrease from 27.66 % to 24.52 % after multi-type data are integrated for CVAE-ESMDA. Furthermore, the NRMSEs of long-term thermal prediction of two production wells also decrease to only 2.3 % and 8.2 %. To further exhibit the advantages of CVAE-ESMDA, another joint inversion framework, principal component analysis (PCA)-ESMDA, is also compared. However, PCA is limited in addressing Non-Gaussian aperture field and its long-term thermal prediction performance is unsatisfactory.

An Artificial Intelligence Approach for Estimating the Turbidity of Artisanal Wine and Dosage of Clarifying Agents

Red wine is a beverage consumed worldwide and contains suspended solids that cause turbidity. The study’s purpose was to mathematically model estimated turbidity in artisanal wines concerning the dosage and types of fining agents based on previous studies presenting positive results. Burgundy grape wine (Vitis lambrusca) was made and clarified with ‘yausabara’ (Pavonia sepium) and bentonite at different concentrations. The system was modelled using several machine learning models, including MATLAB’s Neural Net Fitting and Regression Learner applications. The results showed that the validation of the neural network trained with the Levenberg–Marquardt algorithm obtained significant statistical indicators, such as the coefficient of determination (R2) of 0.985, mean square error (MSE) of 0.004, normalized root mean square error (NRSME) of 6.01 and Akaike information criterion (AIC) of −160.12, selecting it as the representative model of the system. It presents an objective and simple alternative for measuring wine turbidity that is useful for artisanal winemakers who can improve quality and consistency.

Measurement and correlation of solubility data for sodium picosulphate in selected pure solvents and mixed-solvent systems from 298.15 K to 328.15 K

An investigation was carried out to determine the solubility of the stimulant laxative drug Sodium Picosulphate (SP). A wide range of pure solvents were studied, including methanol, ethanol, 1-propanol, 1-butanol, dimethyl formamide, dimethyl sulfoxide, acetonitrile, 1,4-dioxane, acetic acid, and water. More to the point, the solubility of the compound was determined using mixed solvent systems; methanol + acetonitrile and water + acetonitrile. Experimental mole fraction solubility of SP was determined by the gravimetric method over a range of temperatures (298.15 K to 328.15 K) under atmospheric pressure (p=0.1MPa). According to experimental results, a temperature-dependent relationship exists between solubility and temperature. Further, we correlated the experimental mole fraction solubility data with theoretical models including Apelblat, Yaws, Van't Hoff, Modified Jouyban-Acree, CNIBS/R-K models. It appears that the results are well in agreement with the experimental results due to the small values of relative average deviation (RAD) and root mean square deviation (RMSD).The solubility data might be useful in the various areas such as modification, production, crystallization, and separation of SP.

Transportation Simulation Modeling and Location-Based Services Data Completion Based on a Data and Model Dual-Driven Approach

The evolving economic and technological landscape has brought about significant changes in travel behaviors and traffic patterns. These changes have led to the emergence of complex, multi-modal travel demands that interact with transportation networks, posing new challenges in transportation analysis and control. The primary objective of this study is to address these challenges by improving transportation modeling and data completeness using advanced modeling tools and transportation big data. We propose a dual-driven simulation model that integrates transportation simulation and big data. The approach begins by utilizing initial Location-Based Services (LBS) data to establish a mesoscopic multi-modal simulation model, which is then calibrated. This calibrated model is then employed to complete the missing trajectories of the LBS data. The innovative aspect of this dual-driven simulation model lies in its novel approach to constructing transportation models and completing LBS data, thereby enhancing both the simulation accuracy and the results of missing path completion. We conduct tests using the urban area of Hangzhou as an example, and the results show that the Normalized Root Mean Square Error (NRMSE) between the average link speeds in the simulation model and in real world observation is reduced to 24.1%. In the LBS data completion process, our proposed method achieves a travel mode identification accuracy of 95.3% for private car travel. Compared to the two baseline methods, the average accuracy of completed trajectories increases by 6.31% and 2.46%, respectively.

Machine learning techniques for estimation of Pc5 geomagnetic pulsations observed at geostationary orbits during solar cycle 23

Pc5 geomagnetic pulsations can accelerate electrons in the radiation belts, which can pose adverse threats to both astronauts and satellites in space. The estimation of Pc5 waves in space is crucial to radiation belt dynamics studies and will help mitigate these challenges. Here, we explore the advantages of the Feed-forward Neural Network (FFNN) and Random Forest (RF) algorithm for effective estimation of Pc5 geomagnetic pulsations observed in space at geostationary orbit during solar cycle 23. The dataset used in this study is the vector magnetic field measurements retrieved from the Geostationary Operational Environmental Satellite-10 (GOES-10) and the solar wind parameters: Bz and Vx component of the solar wind in the Geocentric Solar Ecliptic (GSE) coordinate system, proton density, flow pressure, and plasma beta obtained from the OMNI Web database during part of solar cycle 23. Pc5 geomagnetic pulsations were extracted from the toroidal component of the magnetic field time series using a bandpass Butterworth filter. The continuous wavelet transform (CWT) was utilized to study the characteristics of the extracted wave in the time-frequency domain for its validation. The validated Pc5 events were used as the target in the model's development, with the solar wind parameters as the inputs. In addition to the solar wind parameters, we included an attribute of the magnetic field time series as an input variable in the model. The dataset is carefully divided to ensure effective training and testing of the models. Finally, we trained both models using the same inputs and targets and explored their estimation abilities. The model was tested during the maximum, descending, and minimum phases of solar cycle 23. Both the FFNN and RF models have a similar estimation, with average cross-correlation score (R) values of 0.74 and 0.73 and corresponding average root mean squared error (RMSEs) of 0.16 nT and 0.67 nT, respectively. The model was deployed to investigate the response of Pc5 waves during three storm days in each testing year. The machine learning (ML) model outputs showed good coherence with the observed Pc5 waves. To validate the models, we studied the correlation between the estimated Pc5 events with the Kp index, and a good correlation was seen to exist between both events. This validates the good performance of the developed models. This work will aid in the study of radiation belt dynamics and the construction of electron depletion regions in the radiation belt.

Experimental validation of a PNS-optimized whole-body gradient coil.

Peripheral nerve stimulation (PNS) limits the usability of state-of-the-art whole-body and head-only MRI gradient coils. We used detailed electromagnetic and neurodynamic modeling to set an explicit PNS constraint during the design of a whole-body gradient coil and constructed it to compare the predicted and experimentally measured PNS thresholds to those of a matched design without PNS constraints. We designed, constructed, and tested two actively shielded whole-body Y-axis gradient coil winding patterns: YG1 is a conventional symmetric design without PNS-optimization, whereas YG2's design used an additional constraint on the allowable PNS threshold in the head-imaging landmark, yielding an asymmetric winding pattern. We measured PNS thresholds in 18 healthy subjects at five landmark positions (head, cardiac, abdominal, pelvic, and knee). The PNS-optimized design YG2 achieved 46% higher average experimental thresholds for a head-imaging landmark than YG1 while incurring a 15% inductance penalty. For cardiac, pelvic, and knee imaging landmarks, the PNS thresholds increased between +22% and +35%. For abdominal imaging, PNS thresholds did not change significantly between YG1 and YG2 (-3.6%). The agreement between predicted and experimental PNS thresholds was within 11.4% normalized root mean square error for both coils and all landmarks. The PNS model also produced plausible predictions of the stimulation sites when compared to the sites of perception reported by the subjects. The PNS-optimization improved the PNS thresholds for the target scan landmark as well as most other studied landmarks, potentially yielding a significant improvement in image encoding performance that can be safely used in humans.

FlexDTI: flexible diffusion gradient encoding scheme-based highly efficient diffusion tensor imaging using deep learning

Objective. Most deep neural network-based diffusion tensor imaging methods require the diffusion gradients’ number and directions in the data to be reconstructed to match those in the training data. This work aims to develop and evaluate a novel dynamic-convolution-based method called FlexDTI for highly efficient diffusion tensor reconstruction with flexible diffusion encoding gradient scheme. Approach. FlexDTI was developed to achieve high-quality DTI parametric mapping with flexible number and directions of diffusion encoding gradients. The method used dynamic convolution kernels to embed diffusion gradient direction information into feature maps of the corresponding diffusion signal. Furthermore, it realized the generalization of a flexible number of diffusion gradient directions by setting the maximum number of input channels of the network. The network was trained and tested using datasets from the Human Connectome Project and local hospitals. Results from FlexDTI and other advanced tensor parameter estimation methods were compared. Main results. Compared to other methods, FlexDTI successfully achieves high-quality diffusion tensor-derived parameters even if the number and directions of diffusion encoding gradients change. It reduces normalized root mean squared error by about 50% on fractional anisotropy and 15% on mean diffusivity, compared with the state-of-the-art deep learning method with flexible diffusion encoding gradient scheme. Significance. FlexDTI can well learn diffusion gradient direction information to achieve generalized DTI reconstruction with flexible diffusion gradient scheme. Both flexibility and reconstruction quality can be taken into account in this network.

Integrating gated recurrent unit in graph neural network to improve infectious disease prediction: an attempt.

This study focuses on enhancing the precision of epidemic time series data prediction by integrating Gated Recurrent Unit (GRU) into a Graph Neural Network (GNN), forming the GRGNN. The accuracy of the GNN (Graph Neural Network) network with introduced GRU (Gated Recurrent Units) is validated by comparing it with seven commonly used prediction methods. The GRGNN methodology involves multivariate time series prediction using a GNN (Graph Neural Network) network improved by the integration of GRU (Gated Recurrent Units). Additionally, Graphical Fourier Transform (GFT) and Discrete Fourier Transform (DFT) are introduced. GFT captures inter-sequence correlations in the spectral domain, while DFT transforms data from the time domain to the frequency domain, revealing temporal node correlations. Following GFT and DFT, outbreak data are predicted through one-dimensional convolution and gated linear regression in the frequency domain, graph convolution in the spectral domain, and GRU (Gated Recurrent Units) in the time domain. The inverse transformation of GFT and DFT is employed, and final predictions are obtained after passing through a fully connected layer. Evaluation is conducted on three datasets: the COVID-19 datasets of 38 African countries and 42 European countries from worldometers, and the chickenpox dataset of 20 Hungarian regions from Kaggle. Metrics include Average Root Mean Square Error (ARMSE) and Average Mean Absolute Error (AMAE). For African COVID-19 dataset and Hungarian Chickenpox dataset, GRGNN consistently outperforms other methods in ARMSE and AMAE across various prediction step lengths. Optimal results are achieved even at extended prediction steps, highlighting the model's robustness. GRGNN proves effective in predicting epidemic time series data with high accuracy, demonstrating its potential in epidemic surveillance and early warning applications. However, further discussions and studies are warranted to refine its application and judgment methods, emphasizing the ongoing need for exploration and research in this domain.

Optimizing recombinant antibody fragment production: A comparison of artificial intelligence and statistical modeling.

Maximizing the recombinant protein yield necessitates optimizing the production medium. This can be done using a variety of methods, including the conventional "one-factor-at-a-time" approach and more recent statistical and mathematical methods such as artificial neural network (ANN), genetic algorithm, etc. Every approach has advantages and disadvantages of its own, yet even when a technique has flaws, it is nevertheless used to get the best results. Here, one categorical variable and four numerical parameters, including post-induction time, inducer concentration, post-induction temperature, and pre-induction cell density, were optimized using the 232 experimental assays of the central composite design. The direct and indirect effects of factors on the yield of anti-epithelial cell adhesion molecule extracellular domain fragment antibody were examined using statistical methods. The analysis of variance results indicate that the response surface methodology (RSM) model is effective in predicting the amount of produced single-chain fragment variable (p-value = 0.0001 and R2 = 0.905). For ANN modeling, the evaluation using normalized root mean square error (NRMSE) and R2 values shows a good fit (R2 = 0.942) and accurate predictions (NRMSE = 0.145). The analysis of error parameters and R2 of a dataset, which contained 30 data points randomly selected from the complete dataset, showed that the ANN model had a higher R2 value (0.968) compared to the RSM model (0.932). Furthermore, the ANN model demonstrated stronger predictive ability with a lower NRMSE (0.048vs. 0.064). Induction at the cell density of 0.7 and an isopropyl β-D-1-thiogalactopyranoside concentration of 0.6mM for 32 h at 30°C in BW25113 was the ideal culture condition leading to the protein yield of 259.51mg/L. Under the optimum conditions, the output values predicted by the ANN model (259.83mg/L) were more in line with the experimental data (259.51mg/L) than the RSM (276.13mg/L) expected value. This outcome demonstrated that the ANN model outperforms the RSM in terms of prediction accuracy.

Seismo-ionospheric precursory detection using hybrid Bayesian-LSTM network model with uncertainty-boundaries and anomaly-intensity

Several efforts have been made to understand the complex physical processes involved in a seismic process, but the findings are vague considering prediction capabilities. Nevertheless, recent seismo-ionosphere precursory research has enlightened new pathways toward building an earthquake (EQ) forecasting system. Previously, some conventional mathematical/statistical approaches have been proposed for detecting an anomalous value as a potential precursor. We propose a hybrid Bayesian-based Long Short-Term Memory (B-LSTM) Network model to forecast the Total Electron Content (TEC) data. We applied B-LSTM on different Vertical TEC (VTEC) datasets of two EQs (Mw7.7 Awaran EQ and Mw7.1 Van EQ) by forecasting VTECs with Normalised Root Mean Square Error (NRMSE) scores of 0.15 and 0.10, respectively. We calculated errors and estimated the 99 % confidence interval to extract the VTEC anomalies. The model detects VTEC anomalies successfully but these anomalies may still have some biases and may lead to a false alarm. In order to minimize possible false alarms, we calculated the intensity of each anomaly and found a strong anomaly that occurred 2–3 days before the EQs. To strengthen the relationship of the detected VTEC anomalies with the investigated earthquakes, we examined the state of space weather conditions during and before the event. Our analysis expands the use of deep learning methods in EQ prediction and VTEC forecasting that can be used for various applications e.g. space weather and navigation.

LEO-Enhanced GNSS/INS Tightly Coupled Integration Based on Factor Graph Optimization in the Urban Environment

Precision point positioning (PPP) utilizing the Global Navigation Satellite System (GNSS) is a traditional and widely employed technology. Its performance is susceptible to observation discontinuities and unfavorable geometric configurations. Consequently, the integration of the Inertial Navigation System (INS) and GNSS makes full use of their respective advantages and effectively mitigates the limitations of GNSS positioning. However, the GNSS/INS integration faces significant challenges in complex and harsh urban environments. In recent years, the geometry between the user and the satellite has been effectively improved with the advent of lower-orbits and faster-speed Low Earth Orbit (LEO) satellites. This enhancement provides more observation data, opening up new possibilities and opportunities for high-precision positioning. Meanwhile, in contrast to the traditional extended Kalman filter (EKF) approach, the performance of the LEO-enhanced GNSS/INS tightly coupled integration (TCI) can be significantly improved by employing the factor graph optimization (FGO) method with multiple iterations to achieve stable estimation. In this study, LEO data and the FGO method were employed to enhance the GNSS/INS TCI. To validate the effectiveness of the method, vehicle data and simulated LEO observations were subjected to thorough analysis. The results suggest that the integration of LEO data significantly enhances the positioning accuracy and convergence speed of the GNSS/INS TCI. In contrast to the FGO GNSS/INS TCI without LEO enhancement, the average enhancement effect of the LEO is 22.16%, 7.58%, and 10.13% in the north, east, and vertical directions, respectively. Furthermore, the average root mean square error (RMSE) of the LEO-enhanced FGO GNSS/INS TCI is 0.63 m, 1.21 m, and 0.85 m in the north, east, and vertical directions, respectively, representing an average improvement of 41.91%, 13.66%, and 2.52% over the traditional EKF method. Meanwhile, the simulation results demonstrate that LEO data and the FGO method effectively enhance the positioning and convergence performance of GNSS/INS TCI in GNSS-challenged environments (tall buildings, viaducts, underground tunnels, and wooded areas).

Decision tree-based approach to extrapolate life cycle inventory data of manufacturing processes

Life cycle assessment (LCA) plays a crucial role in green manufacturing to uncover the critical aspects for alleviating the environmental burdens due to manufacturing processes. However, the scarcity of life cycle inventory (LCI) data for the manufacturing processes is a considerable challenge. This paper proposes a novel approach to extrapolate LCI data of manufacturing processes. Taking advantage of LCI data in the Ecoinvent datasets, decision tree-based supervised machine learning models, namely decision tree, random forest, gradient boosting, and adaptive boosting, have been developed to extrapolate the data of GHG emissions, i.e., carbon dioxide, nitrous oxide, methane, and water vapor. Initially, a correlation analysis was conducted to derive the most influential factors on GHG quantities resulting from manufacturing activities. First, the collected data have been preprocessed and split into train and test sets (70% and 30%, respectively). Second, a five-fold cross-validation method was applied to tune the hyperparameters of the models. Then, the models were re-trained using the best hyperparameters and evaluated using the test set. The results reveal that the Gradient Boosting model has a superior predictive performance for extrapolating the GHG emission data, with average coefficients of determination (R2) on the test set <0.95. Moreover, the model predictions involve relatively low values of the average root mean squared error and an average mean percentage of error on the test set. The correlation and feature importance analyses emphasized that the workpiece material and manufacturing technology have a considerable effect on natural resource consumption, i.e., energy, material, and water inflows into the process. Meanwhile, energy consumption, water usage, and raw aluminum depletion were the most influential factors in GHG emissions. Eventually, a case study to extrapolate the inflows and the outflows for new manufacturing activities has been conducted using the validated models. The proposed GraBoost model provides a computational supplementary approach to estimate and extrapolate the GHG emissions for different manufacturing processes when LCI data are incomplete or don't exist within LCI databases.