Root Mean Square Error Error Research Articles

Enhancing Soil Texture and Bulk Density Mapping Using Soil Grids and Machine Learning: A Comparative Analysis with Observed Data

Digital soil mapping plays a crucial role in understanding soil variability and informing sustainable land management practices. This study focuses on the Kurdistan Region of Iraq (KRI), evaluating the accuracy of SoilGrids, a global-scale soil mapping initiative, and exploring the efficacy of machine learning algorithms in refining soil properties estimations. The aim of this research was to assess and represent the physical parameters of soils effectively by comparing ground truth soil sampling data with data obtained from SoilGrids regarding clay, silt, and sand fractions and bulk density. Comparative analyses were conducted between ground truth soil sampling data and SoilGrids predictions, revealing significant differences across soil mineral fractions including clay, silt, sand fractions, and bulk density. The results showed that the mean clay fraction in the ground truth dataset differed notably from SoilGrids estimation, with a Mean Absolute Deviation (MAD) of 124.0 g kg-1 and Root Mean Square Error (RMSE) of 152.5. However, the integration of machine learning algorithms, particularly the Extreme Gradient Boosting (XG Boost) algorithm, showed promising results in improving accuracy. The XG Boost algorithm exhibited a relatively low MAD of 97.9 g kg-1 for clay fractions, indicating a better approximation of observed values compared to SoilGrids. Significant percent improvements in RMSE and Mean Absolute Percentage Error (MAPE) values were observed across soil fractions and bulk density measurements, ranging from approximately 15% for clay to 35% for sand fractions and 20% for bulk density. These findings highlight the importance of integrating advanced mapping techniques and machine learning algorithms to enhance soil mapping methodologies. Moving forward, efforts to expand ground truth datasets through targeted soil sampling campaigns and develop international collaboration initiatives will be crucial for improving the accuracy and reliability of soil mapping products in the KRI. By incorporating advanced mapping approaches, we can better support sustainable land management practices and environmental conservation efforts in the region.

Mechanical Method for Rapid Determination of Step Count Sensor Settings.

With the increased push for personalized medicine, researchers and clinicians have begun exploring the use of wearable sensors to track patient activity. These sensors typically prioritize device life over robust onboard analysis, which results in lower accuracies in step count, particularly at lower cadences. To optimize the accuracy of activity-monitoring devices, particularly at slower walking speeds, proven methods must be established to identify suitable settings in a controlled and repeatable manner prior to human validation trials. Currently, there are no methods for optimizing these low-power wearable sensor settings prior to human validation, which requires manual counting for in-laboratory participants and is limited by time and the cadences that can be tested. This article proposes a novel method for determining sensor step counting accuracy prior to human validation trials by using a mechanical camshaft actuator that produces continuous steps. Sensor error was identified across a representative subspace of possible sensor setting combinations at cadences ranging from 30 steps/min to 110 steps/min. These true errors were then used to train a multivariate polynomial regression to model errors across all possible setting combinations and cadences. The resulting model predicted errors with an R2 of 0.8 and root-mean-square error (RMSE) of 0.044 across all setting combinations. An optimization algorithm was then used to determine the combinations of settings that produced the lowest RMSE and median error for three ranges of cadence that represent disabled low-mobility ambulators, disabled high-mobility ambulators, and healthy ambulators (30-60, 20-90, and 30-110 steps/min, respectively). The model identified six setting combinations for each range of interest that achieved a ±10% error in cadence prior to human validation. The anticipated range of errors from the optimized settings at lower walking speeds are lower than the reported errors of wearable sensors (±30%), suggesting that pre-human-validation optimization of sensors may decrease errors at lower cadences. This method provides a novel and efficient approach to optimizing the accuracy of wearable activity monitors prior to human validation trials.

Optimizing energy storage plant discrete system dynamics analysis with graph convolutional networks

Addressing the challenges of suboptimal model performance and excessive parameters and operations in the optimization of energy storage power plants utilizing Graph Convolutional Network (GCN), this paper introduces a novel approach – the packet-switched graph convolutional network. Initially, a GCN extreme learning machine is established. Drawing inspiration from this solid foundation, we have innovatively crafted a group exchange graph convolution module. This module leverages group graph convolution techniques to amalgamate unique node feature information, tailored to diverse topology graph matrices based on various groupings. This innovative approach ensures that information flows freely and effectively among distinct groupings. Furthermore, we have designed a cutting-edge timing depth separation convolution module, comprising two innovative components. The first component introduces timing depth separation convolution, revolutionizing the original timing convolution module. The second component, the packet-switching graph convolutional network, revolutionizes the time sequence depth separation convolution process. It achieves this by employing 1 × 1 convolutional layers between different feature fusion packets, enabling seamless information exchange between distinct packets. Experimental results demonstrate the efficacy of the proposed model, with root mean square error (RMSE) metrics and root mean square error (MAE) metrics for single-step prediction reaching 46.08 and 26.22 at 60 min, respectively. In multi-step testing, the proposed model exhibits a 14.71 % reduction in RMSE error at the 15-min scale and a 9.29 % reduction at the 60-min scale compared to the benchmark model. This performance improvement enhances the operational efficiency and reliability of the energy storage plant, particularly under dynamic changes in the time series.

Identification of the Initial Anthesis of Soybean Varieties Based on UAV Multispectral Time-Series Images

Accurate and high-throughput identification of the initial anthesis of soybean varieties is important for the breeding and screening of high-quality soybean cultivars in field trials. The objectives of this study were to identify the initial day of anthesis (IADAS) of soybean varieties based on remote sensing multispectral time-series images acquired by unmanned aerial vehicles (UAVs), and analyze the differences in the initial anthesis of the same soybean varieties between two different climatic regions, Shijiazhuang (SJZ) and Xuzhou (XZ). First, the temporal dynamics of several key crop growth indicators and spectral indices were analyzed to find an effective indicator that favors the identification of IADAS, including leaf area index (LAI), above-ground biomass (AGB), canopy height (CH), normalized-difference vegetation index (NDVI), red edge chlorophyll index (CIred edge), green normalized-difference vegetation index (GNDVI), enhanced vegetation index (EVI), two-band enhanced vegetation index (EVI2) and normalized-difference red-edge index (NDRE). Next, this study compared several functions, like the symmetric gauss function (SGF), asymmetric gauss function (AGF), double logistic function (DLF), and fourier function (FF), for time-series curve fitting, and then estimated the IADAS of soybean varieties with the first-order derivative maximal feature (FDmax) of the CIred edge phenology curves. The relative thresholds of the CIred edge curves were also used to estimate IADAS, in two ways: a single threshold for all of the soybean varieties, and three different relative thresholds for early, middle, and late anthesis varieties, respectively. Finally, this study presented the variations in the IADAS of the same soybean varieties between two different climatic regions and discussed the probable causal factors. The results showed that CIred edge was more suitable for soybean IADAS identification compared with the other investigated indicators because it had no saturation during the whole crop lifespan. Compared with DLF, AGF and FF, SGF provided a better fitting of the CIred edge time-series curves without overfitting problems, although the coefficient of determination (R2) and root mean square error (RMSE) were not the best. The FDmax of the SGF-fitted CIred edge curve (SGF_CIred edge) provided good estimates of the IADAS, with an RMSE and mean average error (MAE) of 3.79 days and 3.00 days, respectively. The SGF-fitted_CIred edge curve can be used to group the soybean varieties into early, middle and late groups. Additionally, the accuracy of the IADAS was improved (RMSE = 3.69 days and MAE = 3.09 days) by using three different relative thresholds (i.e., RT50, RT55, RT60) for the three flowering groups compared to when using a single threshold (RT50). In addition, it was found that the IADAS of the same soybean varieties varied greatly when planted in two different climatic regions due to the genotype–environment interactions. Overall, this study demonstrated that the IADAS of soybean varieties can be identified efficiently and accurately based on UAV remote sensing multispectral time-series data.

Short-term wind power prediction based on anomalous data cleaning and optimized LSTM network

Wind power prediction values are often unstable. The purpose of this study is to provide theoretical support for large-scale grid integration of power systems by analyzing units from three different regions in China and using neural networks to improve power prediction accuracy. The variables that have the greatest impact on power are screened out using the Pearson correlation coefficient. Optimize LSTM with Lion Swarm Algorithm (LSO) and add GCT attention module for optimization. Short-term predictions of actual power are made for Gansu (Northwest China), Hebei (Central Plains), and Zhejiang (Coastal China). The results show that the mean absolute percentage error (MAPE) of the nine units ranges from 9.156% to 16.38% and the root mean square error (RMSE) ranges from 1.028 to 1.546 MW for power prediction for the next 12 h. The MAPE of the units ranges from 11.36% to 18.58% and the RMSE ranges from 2.065 to 2.538 MW for the next 24 h. Furthermore, the LSTM is optimized by adding the GCT attention module to optimize the LSTM. 2.538 MW. In addition, compared with the model before data cleaning, the 12 h prediction error MAPE and RMSE are improved by an average of 34.82% and 38.10%, respectively; and the 24 h prediction error values are improved by an average of 26.32% and 20.69%, which proves the necessity of data cleaning and the generalizability of the model. The subsequent research content was also identified.

Utilizing Multivariate Adaptive Regression Splines (MARS) for Precise Estimation of Soil Compaction Parameters

Traditional laboratory methods for estimating soil compaction parameters, such as the Proctor test, have been recognized as time-consuming and labor-intensive. Given the increasing need for the rapid and accurate estimation of soil compaction parameters for a range of geotechnical applications, the application of machine learning models offers a promising alternative. This study focuses on employing the multivariate adaptive regression splines (MARS) model algorithm, a machine learning method that presents a significant advantage over other models through generating human-understandable piecewise linear equations. The MARS model was trained and tested on a comprehensive dataset to predict essential soil compaction parameters, including optimum water content (wopt) and maximum dry density (ρdmax). The performance of the model was evaluated using coefficient of determination (R2) and root mean square error (RMSE) values. Remarkably, the MARS models showed excellent predictive ability with high R2 and low RMSE, MAE, and relative error values, indicating its robustness and reliability in predicting soil compaction parameters. Through rigorous five-fold cross-validation, the model’s predictions for wopt returned an RMSE of 1.948%, an R2 of 0.893, and an MAE of 1.498%. For ρdmax, the results showcased an RMSE of 0.064 Mg/m3, an R2 of 0.899, and an MAE of 0.050 Mg/m3. When evaluated on unseen data, the model’s performance for wopt prediction was marked with an MAE of 1.276%, RMSE of 1.577%, and R2 of 0.948. Similarly, for ρdmax, the predictions were characterized by an MAE of 0.047 Mg/m3, RMSE of 0.062 Mg/m3, and R2 of 0.919. The results also indicated that the MARS model outperformed previously developed machine learning models, suggesting its potential to replace conventional testing methods. The successful application of the MARS model could revolutionize the geotechnical field through providing quick and reliable predictions of soil compaction parameters, improving efficiency for construction projects. Lastly, a variable importance analysis was performed on the model to assess how input variables affect its outcomes. It was found that fine content (Cf) and plastic limit (PL) have the greatest impact on compaction parameters.

A novel deep belief network architecture with interval type-2 fuzzy set based uncertain parameters towards enhanced learning

This paper proposes a novel Deep Belief Network (DBN) architecture, the ‘Interval Type-2 Fuzzy DBN (IT2FDBN)’, which models the weights and biases with IT2 FSs. Thus, it introduces a novel algorithm for augmented deep leaning, which has the capability to address all the limitations of the classical DBN (CDBN) and T1 fuzzy DBN (T1FDBN). We comparatively evaluate the performance of the IT2FDBN by conducting experiments using the popular MNIST handwritten digit recognition datasets. Additionally, to demonstrate its robustness and generalization capabilities, we also conduct experiments taking two noisy variants of MNIST dataset, viz. the MNIST with AWGN (additive white Gaussian noise) and the MNIST with motion blur. We conduct extensive simulations by considering different combinations of nodes in the hidden layers of the DBN for better model selection. We thoroughly compare the results using well-known performance measures such as root mean square error (RMSE) and Error rate. We show that, in terms of RMSE values and error rates, the proposed IT2FDBN outperforms both T1FDBN and CDBN across all the three datasets. Further, we also provide the results of convergence, runtime-based comparison, and statistical analysis in support of our proposal.

Improving Linear Interpolation of Missing Hydrological Data by Applying Integrated Autoregressive Models

The application of linear interpolation for handling missing hydrological data is unequivocal. On one hand, such an approach offers good reconstruction in the vicinity of last observation before a no-data gap and first measurement after the gap. On the other hand, it omits irregular variability of hydrological data. Such an irregularity can be described by time series models, such as for instance the autoregressive integrated moving average (ARIMA) model. Herein, we propose a method which combines linear interpolation with autoregressive integrated model (ARI, i.e. ARIMA without a moving average part), named LinAR (available at GitHub), as a tool for inputing hydrological data. Linear interpolation is combined with the ARI model through linear scaling the ARI-based prediction issued for the no-data gap. Such an approach contributes to the current state of art in gap-filling methods since it removes artificial jumps between last stochastic prediction and first known observation after the gap, also introducing some irregular variability in the first part of the no-data gap. The LinAR method is applied and evaluated on hourly water level data collected between 2016 and 2021 (52,608 hourly steps) from 28 gauges strategically located within the Odra/Oder River basin in southwestern and western Poland. The data was sourced from Institute of Meteorology and Water Management (Poland). Evaluating the performance with over 100 million assessments in the validation experiment, the study demonstrates that the LinAR approach outperforms the purely linear method, especially for short no-data gaps (up to 12 hourly steps) and for rivers of considerable size. Based on rigorous statistical analysis of root mean square error (RMSE) – expressed (1) absolutely, (2) as percentages and (3) using RMSE error bars – the percentage improvement, understood as percentage difference between RMSE of linear and LinAR interpolations, was found to reach up to 10%.

An Entropy Weight‐Based Method for Path Loss Predictions for Terrestrial Services in the VHF and UHF Bands

AbstractVHF and UHF are widely used frequency bands, and accurate path loss prediction in these bands is of great significance. In order to improve the prediction accuracy and stability of radio wave propagation, we propose a combined modeling method based on the entropy weight method. This method assigns appropriate weights to the predicted values of sub‐models using entropy, and calculates the final predicted value through weighted aggregation. To validate the feasibility of our proposed method, we conduct modeling using data from Denver, Colorado. We compare our method with the ITU‐R models and a model established using the coefficient of variation method. The results demonstrate that our proposed model outperforms the compared models. Specifically, the root‐mean‐square error (RMSE) of our proposed model is reduced by 5.94 and 5.51 dB compared to the ITU‐R P.1546 and 2001 models, respectively. Moreover, our proposed model exhibits better stability than the ITU‐R models. We also use the improvement percentage (γ) to evaluate the degree of improvement of our model over the sub‐models, which is 49.13% and 47.86% for the ITU‐R P.1546 and 2001 models, respectively. Additionally, by comparing the RMSE and absolute error, we find that the entropy weight‐based method outperforms the coefficient of variation‐based method. This research demonstrates the superiority of the entropy weight‐based modeling method, providing a valuable channel modeling approach for path loss prediction and supporting the regional assimilation of radio propagation prediction methods.

Estimation of satellite link’s fade margin using non-meteorological technique and worst month analysis

<span lang="EN-US">Satellite technology is shifting to higher frequencies such as Q or V-band to cater to greater bandwidth and higher data rates applications such as videoconferencing, internet of things (IoT) and telemedicine. The main challenge in deploying high-frequency bands in heavy precipitation areas is severe rain attenuation. In this paper, a frequency scaling technique was developed to estimate the fade margin at a higher frequency. The worst month analysis was also conducted since the analysis is also important in determining dependable fade margin. The result was evaluated and analyzed using root mean square error (RMSE) and percentage error. The proposed model offers the smallest RMSE and lowest percentage error when compared to all existing prediction models. A dependable fade margin acquired from high-accuracy rain attenuation estimation is very important. This is to apply the best mitigation technique in overcoming rain attenuation in the satellite-Earth link so that, the best system performance can be delivered.</span>

Accurate long-term prognostics of proton exchange membrane fuel cells using recurrent and convolutional neural networks

Estimating the remaining useful life (RUL) of proton exchange membrane fuel cells (PEMFCs) is key to predicting and increasing their durability. This paper investigates six deep learning techniques – long short-term memory (LSTM) networks, gated recurrent units (GRU), 1-D convolutional neural network (CNN)-LSTMs, 1D–CNN–GRUs, 1D–CNN–Bidirectional-LSTMs, and 1D–CNN–Bidirectional-GRUs – for RUL and long-term degradation trend prediction for a five-cell PEMFC stack operated with and without current ripples. The hyperparameters of all models are optimized for minimum root-mean-square error (RMSE) of the stack voltage using tree-structured Parzen estimators (TPE) with hyperband pruning. The obtained prediction results are benchmarked using the coefficient of determination (R2), RMSE, and mean absolute percentage error (MAPE) in stack voltage predictions and relative error (RE) in RUL estimates. The comparative analysis for models trained on 50% datasets reveals that the best R2, RMSE, MAPE, and RE of 98.87E-2, 1.258E-3, 0.285E-1, and 0.0425E-1 are offered by the LSTM model for the stack without current ripples. Further, for the stack with current ripples, the best R2, RMSE, MAPE, and RE of 99.482E-2, 1.77E-3, 0.444E-1, and 0.089E-1 are exhibited by the 1D–CNN–Bidirectional-GRU model. The LSTM model also reveals excellent transfer learning performance on the stack with current ripples with the best R2, RMSE, MAPE, and RE of 98.91E-2, 2.455E-3, 0.362E-1, and 0.044E-1, respectively.

Multiple PM Low-Cost Sensors, Multiple Seasons’ Data, and Multiple Calibration Models

In this study, we combined state-of-the-art data analysis techniques (machine learning [ML] methods) and data from state-of-the-art low-cost particulate matter (PM) sensors (LCSs) to improve the accuracy of LCS-measured PM2.5 (PM with aerodynamic diameter less than 2.5 microns) mass concentrations. We collocated nine LCSs and a reference PM2.5 instrument for 9 months, covering all local seasons, in Bengaluru, India. Using the collocation data, we evaluated the performance of the LCSs and trained around 170 ML models to reduce the observed bias in the LCS-measured PM2.5. The ML models included (i) Decision Tree, (ii) Random Forest (RF), (iii) eXtreme Gradient Boosting, and (iv) Support Vector Regression (SVR). A hold-out validation was performed to assess the model performance. Model performance metrics included (i) coefficient of determination (R2), (ii) root mean square error (RMSE), (iii) normalised RMSE, and (iv) mean absolute error. We found that the bias in the LCS PM2.5 measurements varied across different LCS types (RMSE = 9–30 µg m-3) and that SVR models performed best in correcting the LCS PM2.5 measurements. Hyperparameter tuning improved the performance of the ML models (except for RF). The performance of ML models trained with significant predictors (fewer in number than the number of all predictors, chosen based on recursive feature elimination algorithm) was comparable to that of the ‘all predictors’ trained models (except for RF). The performance of most ML models was better than that of the linear models. Finally, as a research objective, we introduced the collocated black carbon mass concentration measurements into the ML models but found no significant improvement in the model performance.

An integrated framework of robust local mean decomposition and bidirectional long short-term memory to forecast solar irradiance

ABSTRACT An accurate forecasting of solar global horizontal irradiance (GHI) provides the estimation of future output from photovoltaic (PV) cells, resulting in guaranteed sustainable functioning of solar integrated smart grids. Traditional forecasting algorithms find it relatively hard to obtain the intrinsic non-linearity of solar GHI, leading to poor forecasting accuracy. This work offers a deep learning (DL)-based hybrid model called RLMD BILSTM that combines robust local mean decomposition (RLMD) algorithm with bidirectional long short-term memory (BILSTM) predictor. The proposed RLMD BILSTM model has been developed and evaluated for two separate Indian locations: Hisar and Jaipur, by comparing with benchmark models: persistence, long short-term memory (LSTM), gated recurrent unit (GRU), BILSTM, and their RLMD-based hybrid variations (RLMD LSTM and RLMD GRU). The performance of the proposed model has been verified by the statistical and visual results of short-term annual and seasonal forecast of solar GHI. From the results, it has been observed that the proposed model achieved lower root mean square error (RMSE) (16.34 W/m2-35.07 W/m2) compared to contrast mforecastsodels. The higher annual R2 yielding a value of 0.977–0.995 for the proposed model compared to the contrast model proved its better fitness. Moreover, the study showed that the RLMD with BILSTM improved the RMSE (59.16%–88.88%) and mean absolute error (MAE) (66.45%–92.22%) over various contrast models. The study also conducted the sensitivity analysis using the forecasting efficacy and forecast skill to prove the significance of the proposed model.

Complexity reduction of ordinary kriging algorithm for 3D REM design

This work has investigated the feasibility of using cluster ordinary kriging (OK) interpolation to speed up indoor three-dimensional (3D) radio environment map (REM) generation time than the conventional OK-based REM generation time in two-dimensional (2D) and 3D ways mainly. The REM has been generated on the real-time received signal strength (RSS) dataset of an ultra-high frequency active television (TV) channel to explore TV grey space (TVGS) volume for cognitive access inside a six-storied office building. It can support future home networks for high-speed data-based applications. The optimal number of clusters has been found at K=4 on both 3D and 2D ways through distortion % deviation analysis. The maximum distortion % deviation = 88.74%, has been found at K=4. The exponential semivariogram model has been selected as the best-fit model after a thorough cross-validated comparative analysis of the clustered and non-clustered OK algorithms separately on residual squared error (RSE), root mean square error (RMSE) and the ratio of expected variance (EV) and kriging variance (KV) results. The RSE and RMSE are minimum, and the EV: KV ratio is in between 0.95 to 1.05 for the exponential model. Significant observation of the analysis of the results shows that cluster OK algorithms outperform conventional OK algorithms of corresponding domains on time complexity. A comparative study on RMSE, correlation coefficient (CC), and relative recovery error (RRE) show that cluster OK improves the accuracy. Cluster 2D and 3D OK-based detected TVGS volume is 13450 m3, 5.634% of the whole building volume.

Spatiotemporal estimation of model error to improve soil moisture analysis in ensemble Kalman filter data assimilation

As a key variable in the surface hydrological cycle and energy balance, soil moisture is often analyzed using data assimilation to improve precise and high spatiotemporal resolution from multisource data. However, accurate estimation of model error in soil moisture data assimilation is not sufficient in spatial and temporal dimensions. This paper proposes a spatiotemporal error estimation method that integrates the spatial and temporal dimensions of the study area into model error estimation. The in-situ data was regarded as the “true value” for the temporal dimensions model error estimation. The triple collocation (TC) technique was used to estimate the spatial error of the model. Based on the aforementioned estimation, a linear method to construct the relationship between spatial and temporal information was proposed to fuse the spatiotemporal model error. Result from the proposed method was compared against the overall model error estimation and spatial estimation methods in ensemble Kalman filter (EnKF) data assimilation. The ERA-Interim reanalysis data and in-situ soil moisture data from Washington State in 2016 were used to evaluate the performance of EnKF data assimilation. Using statistical metrics, including the root mean square error (RMSE), the mean bias error (MBE), and the Pearson correlation coefficient (i.e., R-value), the results show that our proposed approach, which uses spatiotemporal approach to model error estimation in EnKF data assimilation, yielded more accurate soil moisture estimates. When ERA-Interim reanalysis soil moisture data was used as the reference data, compared with the overall model error estimation EnKF Data Assimilation Experiment, RMSE and MBE of spatiotemporal model error estimation EnKF Data Assimilation Experiment were reduced by 0.0062 and 0.0061 m3 / m3, respectively, and R remained basically unchanged. When using in-situ measurements as reference data, RMSE and MBE decreased by 0.0034 and 0.0038 m3 / m3, respectively, and R increased by 0.0365. Compared with the other estimation approaches in the experiments, the spatiotemporal error estimation approach greatly improved the estimation accuracy of soil moisture analysis, yielding the closest values and variation trends with the in-situ measurements. Fully considering the temporal and spatial variation of model error and improving the estimation accuracy of model error can provide more accurate model information for data assimilation. The proposed method and framework in this paper can be used in model error estimation and data assimilation, particularly in the fields of numerical weather forecasting, natural environment monitoring, and geographical environment research.

Estimation of Swell Height Using Spaceborne GNSS-R Data from Eight CYGNSS Satellites

Global Navigation Satellite System (GNSS)-Reflectometry (GNSS-R) technology has opened a new window for ocean remote sensing because of its unique advantages, including short revisit period, low observation cost, and high spatial-temporal resolution. In this article, we investigated the potential of estimating swell height from delay-Doppler maps (DDMs) data generated by spaceborne GNSS-R. Three observables extracted from the DDM are introduced for swell height estimation, including delay-Doppler map average (DDMA), the leading edge slope (LES) of the integrated delay waveform (IDW), and trailing edge slope (TES) of the IDW. We propose one modeling scheme for each observable. To improve the swell height estimation performance of a single observable-based method, we present a data fusion approach based on particle swarm optimization (PSO). Furthermore, a simulated annealing aided PSO (SA-PSO) algorithm is proposed to handle the problem of local optimal solution for the PSO algorithm. Extensive testing has been performed and the results show that the swell height estimated by the proposed methods is highly consistent with reference data, i.e., the ERA5 swell height. The correlation coefficient (CC) is 0.86 and the root mean square error (RMSE) is 0.56 m. Particularly, the SA-PSO method achieved the best performance, with RMSE, CC, and mean absolute percentage error (MAPE) being 0.39 m, 0.92, and 18.98%, respectively. Compared with the DDMA, LES, TES, and PSO methods, the RMSE of the SA-PSO method is improved by 23.53%, 26.42%, 30.36%, and 7.14%, respectively.

New SHapley Additive ExPlanations (SHAP) Approach to Evaluate the Raw Materials Interactions of Steel-Fiber-Reinforced Concrete.

Recently, artificial intelligence (AI) approaches have gained the attention of researchers in the civil engineering field for estimating the mechanical characteristics of concrete to save the effort, time, and cost of researchers. Consequently, the current research focuses on assessing steel-fiber-reinforced concrete (SFRC) in terms of flexural strength (FS) prediction by employing delicate AI techniques as well as to predict the raw material interaction that is still a research gap. In this study, the FS of SFRC is estimated by deploying supervised machine learning (ML) techniques, such as DT-Gradient Boosting, DT-XG Boost, DT-AdaBoost, and DT-Bagging. In addition to that, the performance model is also evaluated by using R2, root mean square error (RMSE), and mean absolute error (MAE). Furthermore, the k-fold cross-validation method is also applied to validate the model’s performance. It is observed that DT-Bagging with an R2 value of 0.95 is superior to DT-XG Boost, DT-Gradient Boosting, and DT-AdaBoost. Lesser error MAE and RMSE and higher R2 values for the DT-Bagging model show the enhanced performance of the model compared to the other ensembled approaches. Considerable conservation of time, effort, and cost can be made by applying ML techniques to predict concrete properties. The evaluation of the outcome depicts that the estimated results of DT-Bagging are closer to the experimental results, indicating the accurate estimation of SFRC flexural strength. It is further revealed from the SHapley Additive exPlanations (SHAP) study that the volumetric content of steel fiber highly and positively influences the FS of SFRC.

Short‐term photovoltaic power prediction based on MDCM‐GA‐LSTM model

In recent years, photo-voltaic (PV) system has become one of the most potential renewable energy power generation technologies because of its many advantages. Considering the influence of the randomness of PV system on the operation and dispatching of power system, the necessity of a comprehensive forecasting model is increased rapidly. This paper proposes a short-term PV power forecasting method based on MDCM-GA-LSTM model to solve the problem of low accuracy of traditional and single forecasting model. First, the meteorological data are pre-processed based on wavelet denoising algorithm to improve the data quality. Second, a meteorological model is established based on genetic algorithm (GA) to optimize long short-term memory (LSTM) neural network. Finally, the network is trained with the modified data of the meteorological model as the input and the actual power as the output, and the power forecasting model is established. In this study, the forecasting accuracy is evaluated based on mean absolute error (MAE) and root mean square error (RMSE). The experimental results demonstrated that the MDCM-GA-LSTM model outperforms the conventional and single model by a difference of about 98.43% of the MAE and 98.97% of the RMSE error.

RSS-Based Wireless LAN Indoor Localization and Tracking Using Deep Architectures

Wireless Local Area Network (WLAN) positioning is a challenging task indoors due to environmental constraints and the unpredictable behavior of signal propagation, even at a fixed location. The aim of this work is to develop deep learning-based approaches for indoor localization and tracking by utilizing Received Signal Strength (RSS). The study proposes Multi-Layer Perceptron (MLP), One and Two Dimensional Convolutional Neural Networks (1D CNN and 2D CNN), and Long Short Term Memory (LSTM) deep networks architectures for WLAN indoor positioning based on the data obtained by actual RSS measurements from an existing WLAN infrastructure in a mobile user scenario. The results, using different types of deep architectures including MLP, CNNs, and LSTMs with existing WLAN algorithms, are presented. The Root Mean Square Error (RMSE) is used as the assessment criterion. The proposed LSTM Model 2 achieved a dynamic positioning RMSE error of 1.73m, which outperforms probabilistic WLAN algorithms such as Memoryless Positioning (RMSE: 10.35m) and Nonparametric Information (NI) filter with variable acceleration (RMSE: 5.2m) under the same experiment environment.

Multivariate time series prediction by RNN architectures for energy consumption forecasting

Households and buildings have been utilizing the traditional electric network structure for the last decade, relying on energy supplied by manufacturing centers based on fossil fuels. Large energy use places a burden on such centers. In this perspective, smart grids are a new technology and a new generation of traditional electric networks that provide increased efficiency, dependability, and energy management based on demand optimization. The importance of smart grids can also be seen in the possibility of integrating communication systems for energy demand forecasting, to provide an optimal management of the combination of renewable energies and production centers energy. The authors present a comparative analysis of several deep learning models, notably Recurrent Neural Network (RNN) architectures such as basic RNN, Long Short Term Memory (LSTM), and Gated Recurrent Unit (GRU), in this paper. These architectures are trained and tested on the Smart Grid Smart City (SGSC) project’s energy datasets (2010–2014) and assessed using a variety of indicators such as Root Mean Square Error (RMSE), Mean Absolute Error MAE, and R2 scores in order to analyze, compare and ultimately choose the most efficient model. As expected from the literature of RNN architectures, with the lowest value of RMSE error and the highest value of R2 Score among the three architectures, GRU outperformed both of basic RNN and LSTM, this result can be explained by several reasons the most important one is the ability of the GRU model to deal with the vanishing gradient problem and the impact of the number of parameters, used in building such a model, on the same problem.