Average Relative Root Mean Research Articles

Assimilation of Satellite-Derived Reservoir Storage Data to Improve Global Hydrodynamic Modeling

In this study, we explore the potential of assimilating satellite-derived reservoir storage data into the global-scale hydrodynamic model CaMa-Flood, focusing on the Yangtze River basin. We evaluated three data assimilation (DA) methods: direct assimilation (DIR), anomaly based assimilation (ANO), and normalized assimilation (NOM). Our results show that the DIR method achieved the most significant improvements in reservoir storage and downstream discharge simulations. DIR reduced the average relative root mean square error (rRMSE) of reservoir storage estimates by 80.5%, and increased discharge correlation (ΔCC) by 78.6% in the 14 validated discharge stations. ANO, while effective in certain cases, led to mixed results, with 56.4% of the 39 assimilated dams showing improved storage estimates and a modest 7.8% reduction in average RMSE. NOM had minimal impact, with negligible changes in RMSE or discharge correlation (ΔCC). The direct assimilation method (DIR) consistently outperformed the others, improving both reservoir storage and downstream discharge estimates. However, the magnitude of improvement varied across locations, highlighting the need for the further refinement of DA techniques and input data, especially for regions with complex reservoir operations. Our findings enhance reservoir representation in global hydrodynamic models and improve the predictability of river dynamics and water resource management.

Design and Testing of a 2-DOF Adaptive Profiling Header for Forage Harvesters

The existing forage harvester header cannot automatically adjust the height and inclination during operation, resulting in uneven stubble height of forage, which, in turn, affects the efficiency of harvesting and the quality of forage regeneration. To address this issue, this study conducted the design and experimentation of a 2-degrees-of-freedom (DOF) profiling header. Firstly, this study designed an adaptive profiling header with 2-DOF adjustment, which was realized by the height adjustment mechanism and the tilt angle adjustment mechanism. The relationship model between the profiling device and the attitude of the header was established so that the header can acquire ground undulation in real time through the angle sensor of the profiling device. In order to verify the rationality of the header design, a co-simulation model of ADAMS and MATLAB/Simulink was built, and the header attitude control system was designed based on the fuzzy PID algorithm. The co-simulation results show that the header height (H) is always kept around 150 mm during the forwarding process of the harvester, with a maximum error of 5.8 mm, and the average relative error (REH) and root mean square error (RMSEH) were 1.4% and 2.6 mm, respectively, and the maximum error of the tilt angle (γ) of the header is 0.53° and the RMSEγ is 0.22°, which indicates that the header profiling mechanism can accurately reflect the undulation of the terrain and the header attitude control system has good robustness. Finally, the test platform was built and tested in a grassland. The test results show that the average height of the header is 149.8 mm, the maximum error is 7.5 mm, and the REH and RMSEH are 3.4% and 5.3 mm, respectively. The average error of the header inclination is 0.34°, and the maximum error is 0.57°. The test results indicate that the header can realize the adaptive adjustment of height and inclination, and the control system has high precision, stability and reliability, meeting the demand of automatic regulation of header attitude of a forage harvester.

Determination of Gas–Oil minimum miscibility pressure for impure CO2 through optimized machine learning models

Minimum miscibility pressure (MMP) is one of the most important parameters for designing CO2 enhanced oil recovery (EOR) and associated storage in depleted oil reservoirs. The injection gas stream often contains a certain concentration of impurities such as N2, H2S, and CH4 depending on the source of CO2. These impurities have different effects on CO2 MMP, but there is a lack of widely accepted approaches to account for these effects on MMP calculation. In this study, a series of activities were conducted to develop a machine learning (ML)-based methodology for determining MMP for CO2 with various impurities. A database containing 234 CO2 MMP test sets with around 5000 data points was built based on the reported experimental measurements in the public domain. The database was then subgrouped by three specific criteria: CO2 concentration in the injection gas, type of impurities in the injection gas, and heavier hydrocarbon content in the oil. This subgrouping was essential to capture the impact of different factors on CO2 MMP. An ensemble ML approach with seven ML models, including random forest, adaptive boosting, light gradient boosting machine, extreme gradient boosting (XGBoost), stacking, artificial neural network, and voting regressor, was employed to calculate MMP based on the subgrouped database. The hyperparameters of these ML models were optimized by the grid search technique to minimize the relative errors between calculated and measured MMP values. The performance of each algorithm was assessed using three regression metrics: average absolute relative error (AARE), R-squared score (R2), and root mean square error (RMSE). All of these metrics exhibited satisfactory values for the optimized ML models. The average values of R2, RMSE, and AARE were 0.962, 1.571, and 4.55%, respectively, for the three subgroups, indicating a high accuracy of MMP calculations using the optimized ML models. The XGBoost model emerged as the top performer across the three metrics, with an R2 of 0.979, an AARE of 2.835%, and an RMSE of 1.183 for a dataset with 190 cases. The overall high level of accuracy confirmed the reliability of these ML models in calculating MMP for CO2 with different impurities as well as the importance of optimization in the modeling process.

The solvation thermodynamics of rose acetate in four mixed solvents: Molecular dynamics simulation, molecular conformation analysis, machine learning and solubility prediction

The solubility of rose acetate (alpha-(trichloromethyl) benzyl acetate) in four binary solvent mixtures was measured by static gravimetric method at the temperature ranging from 288.15 K to 328.15 K under atmosphere pressure. The dissolution behavior and solubility prediction were performed through simulations and calculations, using Materials Studio software and Back Propagation Neural Network. The modified Apelblat equation, λh model, Van’t Hoff equation, and NRTL model were employed to correlate the solubility data respectively. And the modified Apelblat equation provided the best fitting performance, corresponding to the lowest average value of average relative deviation and root mean square deviation. After analyzing the solvent properties, it was obsersved that the solubility of rose acetate in selected solvents was influenced by the polarity of the solvent. The mixing thermodynamic properties including ΔmixH, ΔmixS and ΔmixG indicated that the dissolution process of rose acetate was exothermic and spontaneous.Molecular dynamics (MD) simulations were utilized to analyze the interaction mechanism between rose acetate and binary solvent mixtures. The results revealed that the hydrogen bonding interaction played an insignificant role in the dissolution process. Moreover, the solute molecules were characterized in both crystal and solution state based on their conformation and molecular energies. A back-propagation (BP) neural network was constructed to predict the solubility of rose acetate, and the predicted data exhibited good agreement with the measured valuses.

A flue gas velocimeter based on the hyperbolic chirp modulation method of acoustic source signal

Accurate measurement of flue gas velocity is of great significance for the safe production, energy saving, and emission reduction of coal-fired power plants. In this paper, a method of flue gas velocimetry based on a hyperbolic chirp-modulating acoustic source was proposed, and its superiority was verified by numerical simulations and field experiments. For an acoustic velocimeter, it is crucial to ensure the accuracy of the acoustic Time-of-Flight (TOF), which directly affects the flue gas velocity measurements. The improvement of the accuracy of estimation of the TOF directly determines the accuracy of the flue gas velocity measurement. Simulation on the different types of acoustic sources at different signal-to-noise ratios (SNRs) was conducted, and the results proved that the hyperbolic chirp signal is more accurate in the measurement of TOF. In the strong noise range of − 10 dB to − 20 dB, the average relative root mean square error (RRMSE) obtained using this hyperbolic chirp modulating acoustic source is 0.60 dB and 0.36 dB lower than obtained using the linear and logarithmic modulating modes, respectively. The average relative error (RE) is approximately 0.87 times that of the linear chirp. Power plant flue field experiments show that the measurement error using this hyperbolic modulating mode is about 0.52 times and 0.74 times that of using linear and logarithmic modulating modes, respectively. In harsh measurement environments with strong noise, the proposed acoustic source modulation scheme can significantly improve the measurement SNR and effectively enhance the accuracy and robustness of flue gas velocimetry.

Experimental study and machine learning modeling of water removal efficiency from crude oil using demulsifier

This study deals with the investigation of the water removal efficiency (WRE) from crude oil using a commercial demulsifier. The impacts of time, demulsifier concentration, and temperature on WRE were experimentally studied. The results implied the fact that temperature plays a substantial role in the demulsification and has a direct correlation with WRE. In addition, while increasing the concentration up to 40 ppm contributed to reaching a higher WRE, it did not have positive effects on efficiency at higher concentrations (overdose) and just led to more demulsifier consumption. The concentration dependence of WRE was also diminished at high temperatures. At higher levels of temperature and concentration, the time required to reach a high WRE was noticeably reduced. In order to generalize the findings of this study, the measured experimental data were employed to design predictive methods for WRE based on two smart soft-computing paradigms, including Multilayer perceptron (MLP) and Gaussian process regression (GPR). Despite the high accuracy of both models, the MLP model presented the best consistencies with experimental data with average absolute relative error and relative root mean squared error of 0.84%, and 0.01%, respectively during the testing (validation) step. Also, a visual description through the contour diagram confirmed the capability of the recently proposed models to describe the physical variations of WRE under various operating conditions. Ultimately, a sensitivity analysis based on the MLP model was undertaken to shed light on the order of significance of operational factors in controlling WRE. Overall, the findings of the current research, in turn, have a satisfactory contribution to the efficient design of the water removal process from crude oil based on demulsifiers.

Measurements of density and viscosity of carbon dioxide-loaded and -unloaded nano-fluids: Experimental, genetic programming and physical interpretation approaches

In the present study, the density and viscosity of the CO2-loaded and –unloaded base solution and nano-fluid were experimentally measured and investigated from an intermolecular point of view. Nano-fluids are composed of nano-particles such as Al2O3 (0.1 wt.%), Silica-2-methylimidazole, zinc salt (Si-ZIF-8) (0.02 wt.%), and super activated carbon (SAC) (0.1 wt.%) dispersed in aqueous and hybrid Methyl diethanolamine context (MDEA, 40 wt.%) +Sulfolane (SFL), 30 wt.%) +H2O) Experimental measurements were carried out at the low-temperature ranges 303.15–315.15 K, atmospheric pressure, and three different CO2 loadings. The results show that nanomaterials do not have a significant effect on the density and viscosity of the unloaded suspension; however, the density and viscosity of loaded suspensions and base solvent become more by increasing CO2 concentration. In the case of CO2-loaded fluids, the comparison of the results in the presence and absence of nanoparticles shows that the density of the solution is not much different in the two cases, but the viscosity of CO2-loaded in Si-ZIF-8, SAC, and γ-Al2O3 base nano-fluids in comparison with base solvent shows an increase of 35 % in high CO2 loading, ∼0.3 mol CO2 per mol MDEA. Density and viscosity experimental data were modeled using the Genetic Programming approach. The highest values of absolute average relative deviation (AARD) and root mean square error (RMSE) parameters obtained for modeling data are 3.04 and 0.317, respectively, and the lowest value of regression coefficient (R2) is 0.995, which indicates the appropriate fitting of the results.

Prediction of Energy Consumption in a Coal-Fired Boiler Based on MIV-ISAO-LSSVM

Aiming at the problem that the energy consumption of the boiler system varies greatly under the flexible peaking requirements of coal-fired units, an energy consumption prediction model for the boiler system is established based on a Least-Squares Support Vector Machine (LSSVM). First, the Mean Impact Value (MIV) algorithm is used to simplify the input characteristics of the model and determine the key operating parameters that affect energy consumption. Secondly, the Snow Ablation Optimizer (SAO) with tent map, adaptive t-distribution, and the opposites learning mechanism is introduced to determine the parameters in the prediction model. On this basis, based on the operation data of an ultra-supercritical coal-fired unit in Xinjiang, China, the boiler energy consumption dataset under variable load is established based on the theory of fuel specific consumption. The proposed prediction model is used to predict and analyze the boiler energy consumption, and a comparison is made with other common prediction methods. The results show that compared with the LSSVM, BP, and ELM prediction models, the average Relative Root Mean Squared Errors (aRRMSE) of the LSSVM model using ISAO are reduced by 2.13%, 18.12%, and 40.3%, respectively. The prediction model established in this paper has good accuracy. It can predict the energy consumption distribution of the boiler system of the ultra-supercritical coal-fired unit under variable load more accurately.

Study on the Constitutive Modeling of (2.5 vol%TiB + 2.5 vol%TiC)/TC4 Composites under Hot Compression Conditions.

The hot deformation behavior of titanium matrix composites plays a crucial role in determining the performance of the formed components. Therefore, it is significant to establish an accurate constitutive relationship between material deformation parameters and flow stress. In this study, hot compression experiments were conducted on a (2.5 vol%TiB + 2.5 vol%TiC)/TC4. The experiments were performed under temperatures ranging from 1013.15 to 1133.15 K and strain rates ranging from 0.001 to 0.1 s-1. Based on the stress-strain data obtained from the experiment, the constitutive models were established by using the Arrhenius model and the BP neural network algorithm, respectively. Considering the relationship between strain rate, hot working temperature, and flow stress, a comparative analysis was conducted to evaluate the prediction accuracy of two different constitutive models. The research results indicate that the flow stress of (2.5 vol%TiB + 2.5 vol%TiC)/TC4 increases with decreasing temperature and increasing strain rate, and the stress-strain curve shows obvious work hardening and softening behaviors. Both the Arrhenius model and the BP neural network algorithm are effective in predicting the hot compression flow stress of (2.5 vol%TiB + 2.5 vol%TiC)/TC4, but the average relative error and root mean square error of the BP neural network algorithm are smaller and the correlation coefficient is higher, thus possessing higher accuracy and reliability.

Short-term PV power prediction based on VMD-CNN-IPSO-LSSVM hybrid model

Abstract This article discusses the significance and obstacles of short-term power prediction in photovoltaic systems and introduces a hybrid model for photovoltaic short-term power prediction technology based on variational mode decomposition (VMD), convolutional neural network (CNN), improved particle swarm optimization (IPSO) and least squares support vector machine (LSSVM). In the initial stage, the photovoltaic generation signal is decomposed into multiple Intrinsic mode functions (IMFs) using VMD to enhance the extraction of signal time–frequency characteristics. Subsequently, CNN is utilized for feature learning and extraction of each IMF, modeling the nonlinear and non-stationary features. Following this, the IPSO-LSSVM optimization algorithm is employed to establish and optimize multiple LSSVM models, predicting power fluctuations at different time scales. Finally, the predictions from each model are synthesized to obtain the final photovoltaic short-term power forecast. Through validation with actual photovoltaic generation data, this hybrid model demonstrates high accuracy and reliability in short-term power prediction, showing an average relative error and root mean square error reduction of 15.23 and 53.60%, respectively, compared to a certain comparative model. This proposed method based on VMD-CNN-IPSO-LSSVM hybrid model for photovoltaic power prediction holds promising prospects and practical value in the operation and scheduling of photovoltaic generation systems.

Consumer-priced wearable sensors combined with deep learning can be used to accurately predict ground reaction forces during various treadmill running conditions.

Ground reaction force (GRF) data is often collected for the biomechanical analysis of running, due to the performance and injury risk insights that GRF analysis can provide. Traditional methods typically limit GRF collection to controlled lab environments, recent studies have looked to combine the ease of use of wearable sensors with the statistical power of machine learning to estimate continuous GRF data outside of these restrictions. Before such systems can be deployed with confidence outside of the lab they must be shown to be a valid and accurate tool for a wide range of users. The aim of this study was to evaluate how accurately a consumer-priced sensor system could estimate GRFs whilst a heterogeneous group of runners completed a treadmill protocol with three different personalised running speeds and three gradients. Fifty runners (25 female, 25 male) wearing pressure insoles made up of 16 resistive sensors and an inertial measurement unit ran at various speeds and gradients on an instrumented treadmill. A long short term memory (LSTM) neural network was trained to estimate both vertical and anteroposterior force traces using leave one subject out validation. The average relative root mean squared error (rRMSE) was 3.2% and 3.1%, respectively. The mean rRMSE across the evaluated participants ranged from 0.8% to 8.8% and from 1.3% to 17.3% in the estimation. The findings from this study suggest that current consumer-priced sensors could be used to accurately estimate two-dimensional GRFs for a wide range of runners at a variety of running intensities. The estimated kinetics could be used to provide runners with individualised feedback as well as form the basis of data collection for running injury risk factor studies on a much larger scale than is currently possible with lab based methods.

Study on the influence of dust accumulation on the optical performance of trough solar concentrator under different rainfall intensities based on alpine areas

Aiming at the typical characteristics of natural rainfall in alpine areas and the structure of the concentrator surface, based on the design scheme of the trough system test platform, the optical performance and cleaning characteristics of the mirror with rainfall intensity and concentrator tilt angle as variables are studied experimentally. The results show that small-scale rainfall has a critical tilt angle of positive and negative cleaning effect on transverse region1. Lower than this tilt angle causes pollution to the mirror surface. Rainfall above medium intensity has a positive cleaning effect on all mirror regions. The cleaning ability is the highest under the rainfall of 60° tilt angle of 38.9 mm. The bottom-up enhanced cleaning law in the transverse region is more significant under high-intensity rainfall, and the concentrator tilt angle is more sensitive to dust desorption than rainfall intensity. The average relative error and average root mean square error of the predicted reflectivity of the global mirror are 3.82% and 0.061 respectively, and the fitting accuracy is high. It provides theoretical guidance for the application of dust removal schemes and prediction of the optical performance of trough solar system in alpine areas.

Comparative studies of Markov chain-based driving cycles for light-duty vehicles

ABSTRACT With the massive ongoing efforts to mitigate climate change and reduce emission factors in the transportation sector, driving cycles (DCs) are becoming an essential tool for the testing and certification of distinct types of vehicles. Nevertheless, the open literature lacks careful comparative studies on the impact of different approaches in the development of Markov chain (MC)-based DCs, as well as DCs, developed specifically for the developing and highly congested urban areas in the Middle East and North Africa. Using a large dataset of 43 light-duty vehicles, driven over different areas in Greater Cairo, Egypt, this study aims to develop, compare, and benchmark 24 candidate MC-based DCs, against two clustering-based DCs, as well as four cycles used widely in the US and Europe. These 24 DCs differ in terms of the clustering algorithm (K-medoids and K-means), clustering parameters (different combinations of vehicle’s speed, acceleration, specific power, and percentage idling time), and definitions of microtrips (start-stop and fixed distance). The results show that the MC method outperforms random chaining of microtrips, with average relative root mean square errors (RRMSEs) of 15.8% and 23.6%, respectively. Clustering 350 m fixed distance-based microtrips using the vehicle’s speed, acceleration, and percentage idling time shows the least RRMSE of 8.207%. Defining microtrips based on fixed distance is also better than starts/stops for most vehicle types. The reference cycles (WLTP, NEDC, UDDS, and FTP-17) showed poor representativeness of the real-world data, with an average RRMSE of 76.8%. The same inferior performance of reference cycles, compared to the newly proposed ones, was also highlighted in the estimation of fuel consumption and emission factors. Hence, the proposed cycles and the reported comparative studies can be valuable tools for the assessment of emissions and fuel consumption in such developing metropolitan areas.

Research on the Prediction of Wax Deposition Thickness on Pipe Walls Based on the Optimal Weighted Combination Model

Wax deposition seriously affects the safe and economic operation of pipelines. Mastering the variation laws of wax deposition thickness is the premise of formulating reasonable pigging schemes. Although the GM (1,1) model (a kind of gray model) is an effective method for predicting wax deposition thickness on pipe walls, its prediction accuracy is easily affected by the smoothness of the original sequence. The improved GM (1,1) was established by introducing the idea of translation transformation, and an optimal weighted combination model based on the traditional gray model and a logarithmic function model was proposed. The differences in the predicted results of the established models were compared and analyzed through indoor wax deposition experimental data. The research results indicate that the optimal weighted combination model has the highest fitting accuracy, followed by the logarithmic function model and the improved GM (1,1), while the fitting accuracy of the traditional gray model is poor. When the number of modeling samples is five, the average relative error and root mean square error of the prediction results of the optimal weighted combination model are 1.313% and 0.021, respectively, which shows the highest prediction accuracy. When the number of modeling samples is six, the average relative error and root mean square error of the optimal weighted combination model are 2.143% and 0.031, respectively, and its prediction accuracy is still the highest. Overall, the optimal weighted combination model has the advantages of high accuracy and easy implementation, and has strong promotion and application value.

Multi-target regression via target combinations using principal component analysis

Data-driven methods have become increasingly widespread in the chemical industry; however, these methods require sufficient data for effective implementation. Moreover, collecting sufficient data can be challenging for new processes, products, batch processes, and other scenarios. To address this limitation, we propose a novel method called the principal component analysis target combination method, combining the Random Linear Target Combinations (RLC) and Principal Component Analysis. The proposed method utilizes the relationships of multiple inspections obtained in a single production cycle to improve the prediction accuracy using the Multi-Target Regression (MTR) approach. Although collecting multiple samples can be time-consuming and expensive, conducting several inspections on a single sample is relatively easy. In chemical products, multiple inspections are usually performed, and relationships, such as trade-offs, between these inspections exist. We first evaluated the effectiveness of the proposed method using 12 diverse real-world benchmark datasets frequently used in MTR tasks. The results show that the proposed method improves the average Relative Root Mean Squared Error by 3.16 % compared to single-target regression (Gradient Boosting) and improves by 2.0 % compared to RLC, upon which the proposed method relies. Subsequently, we evaluated the method on a real dataset from our company comprising formulation-design data for developing new elastic sealant products. The proposed method outperformed the other methods, confirming its effectiveness and ability to utilize multiple inspection data in chemical plants.

Composite property price index forecasting with neural networks

PurposeThe Chinese housing market has gone through rapid growth during the past decade, and house price forecasting has evolved to be a significant issue that draws enormous attention from investors, policy makers and researchers. This study investigates neural networks for composite property price index forecasting from ten major Chinese cities for the period of July 2005–April 2021.Design/methodology/approachThe goal is to build simple and accurate neural network models that contribute to pure technical forecasts of composite property prices. To facilitate the analysis, the authors consider different model settings across algorithms, delays, hidden neurons and data spitting ratios.FindingsThe authors arrive at a pretty simple neural network with six delays and three hidden neurons, which generates rather stable performance of average relative root mean square errors across the ten cities below 1% for the training, validation and testing phases.Originality/valueResults here could be utilized on a standalone basis or combined with fundamental forecasts to help form perspectives of composite property price trends and conduct policy analysis.

A physics-guided modelling method of artificial neural network for multiaxial fatigue life prediction under irregular loading.

To improve the generalization of the artificial neural network (ANN) model on the prediction of multiaxial irregular cases, a physics-guided modelling method is proposed with inspiration from the Basquin-Coffin-Manson equation. The method suggested using two neurons in the last hidden layer of the ANN model and constraining the sign of weight and bias value. In this way, the prior physical knowledge of fatigue life distribution is introduced into the ANN model, which resulted in a satisfactory performance on the life prediction of multiaxial loading cases and better extrapolation ability. Furthermore, the physics-guided ANN model can also provide satisfactory prediction on irregular cases with the training of only regular cases. Compared with the conventional model, the average relative error and root mean squared error (RMSE) of prediction decreased by 33.29% and 44.29%, respectively. It greatly broadens the application scenarios of neural networks on multiaxial fatigue life prediction. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 1)'.

Smart Approaches for Evaluating Photosynthetically Active Radiation at Various Stations Based on MSG Prime Satellite Imagery

Photosynthetically active radiation (PAR) is the 400–700 nm portion of the solar radiation spectrum that photoautotrophic organisms including plants, algae, and cyanobacteria use for photosynthesis. PAR is a key variable in global ecosystem and Earth system modeling, playing a prominent role in carbon and water cycling. Alongside air temperature, water availability, and atmospheric CO2 concentration, PAR controls photosynthesis and consequently biomass productivity in general. The management of agricultural and horticultural crops, forests, grasslands, and even grasses at sports venues is a non-exhaustive list of applications for which an accurate knowledge of the PAR resource is desirable. Modern agrivoltaic systems also require a good knowledge of PAR in conjunction with the variables needed to monitor the co-located photovoltaic system. In situ quality-controlled PAR sensors provide high-quality information for specific locations. However, due to associated installation and maintenance costs, such high-quality data are relatively scarce and generally extend over a restricted and sometimes non-continuous period. Numerous studies have already demonstrated the potential offered by surface radiation estimates based on satellite information as reliable alternatives to in situ measurements. The accuracy of these estimations is site-dependent and is related, for example, to the local climate, landscape, and viewing angle of the satellite. To assess the accuracy of PAR satellite models, we inter-compared 11 methods for estimating 30 min surface PAR based on satellite-derived estimations at 33 ground-based station locations over several climate regions in Europe, Africa, and South America. Averaged across stations, the results showed average relative biases (relative to the measurement mean) across methods of 1 to 20%, an average relative standard deviation of 25 to 30%, an average relative root mean square error of 25% to 35% and a correlation coefficient always above 0.95 for all methods. Improved performance was seen for all methods at relatively cloud-free sites, and quality degraded towards the edge of the Meteosat Second Generation viewing area. A good compromise between computational time, memory allocation, and performance was achieved for most locations using the Jacovides coefficient applied to the global horizontal irradiance from HelioClim-3 or the CAMS Radiation Service. In conclusion, satellite estimations can provide a reliable alternative estimation of ground-based PAR for most applications.

Track Unevenness Prediction Based on Static Track Inspection Data Matching

A track static misalignment prediction model based on track median deviation is created using an IGA-BP neural network in order to precisely predict the trend of ballastless track static misalignment. The historical static track median deviation detection data are matched using actual compensation edit distance (ERP) to finish the correspondence processing of the original data. The precisely matched data are used to train the model, forecast irregularities in the track median, and compare results with other traditional prediction techniques. The outcomes demonstrate that the IGA-BP neural network can more accurately predict the nonlinear time series data development trend. In comparison to other prediction models, the IGA-BP neural network model’s average relative error and root mean square error are 0.091 and 0.110, respectively. The prediction accuracy is raised by between 43% and 60%, demonstrating the IGA-BP neural network model’s efficacy in predicting static upsets on ballastless tracks and presenting a workable strategy for track predictive maintenance.

Office property price index forecasting using neural networks

PurposeThe Chinese housing market has witnessed rapid growth during the past decade and the significance of housing price forecasting has undoubtedly elevated, becoming an important issue to investors and policymakers. This study aims to examine neural networks (NNs) for office property price index forecasting from 10 major Chinese cities for July 2005–April 2021.Design/methodology/approachThe authors aim at building simple and accurate NNs to contribute to pure technical forecasts of the Chinese office property market. To facilitate the analysis, the authors explore different model settings over algorithms, delays, hidden neurons and data-spitting ratios.FindingsThe authors reach a simple NN with three delays and three hidden neurons, which leads to stable performance of about 1.45% average relative root mean square error across the 10 cities for the training, validation and testing phases.Originality/valueThe results could be used on a standalone basis or combined with fundamental forecasts to form perspectives of office property price trends and conduct policy analysis.