Low Prediction Accuracy Research Articles

Prediction of formation fracture pressure based on reinforcement learning and XGBoost

Abstract Clearly determining the magnitude of fracture pressure is a crucial indicator for fracturing design. Traditional methods for predicting fracture pressure suffer from challenges such as difficulties in obtaining required data, low prediction accuracy, and local limitations in application. In light of these issues, the article proposes a fracture pressure prediction model based on reinforcement learning and XGBoost utilizing geophysical well logging data. Based on the relevance analysis, optimal input parameters, including DEPTH, DEN, AC, GR, CRL, and RT, are selected from geophysical well logging data. We have developed a framework for a fracture pressure prediction model based on XGBoost, wherein hyperparameters are fine-tuned using an improved Q-learning algorithm. The optimized XGBoost model for fracture pressure prediction attains outstanding performance metrics, including an R 2 value of 0.992, a root mean square error of 0.006%, and a mean absolute error of 0.539%. In direct comparison with grid search, Bayesian optimization, and ant colony optimization, the improved Q-learning algorithm emerges as the most effective optimization approach. The predictions generated by the proposed method exhibit remarkable consistency with fracture pressure data measured on-site. This approach successfully addresses the shortcomings encountered with traditional fracture pressure prediction methods, such as inadequate accuracy, demanding data prerequisites, and constrained applicability.

D-dimer as a Predictor of ICU Admission and Mortality in COVID-19 Patients: Insights From a Two-Year Retrospective Study From a Tertiary Care Center in South India.

Introduction Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-induced pneumonitis results in a prothrombotic and hypercoagulable state. Prognostic indicators are crucial for identifying patients at risk of complications. D-dimer, a degradation product of cross-linked fibrin, is a specific marker for thrombosis. Elevated D-dimer levels have been strongly correlated with poor prognosis and increased severity of illness in COVID-19 patients. Given D-dimer's eight-hour half-life, periodic measurement is necessary to track disease progression. This study aimed to analyze and derive threshold and peak D-dimer values to predict outcomes in COVID-19 patients, comparing those treated in isolation wards to those requiring intensive care. Methods This two-year retrospective observational study included patients above 18 years with confirmed COVID-19. Patients were categorized into those treated in isolation wards and those admitted to the intensive care unit (ICU). Based on the outcome, they were further divided into survivors and non-survivors. Demographic and outcome-related data were collected from the hospital's laboratory information system. Serial D-dimer measurements were taken at eight time points. Statistical analysis was performed using the Mann-Whitney test for laboratory values and the chi-square test for demographic data. Receiver operating characteristic (ROC) curve analysis was utilized to derive critical D-dimer values. The area under the curve (AUC) was calculated for initial and peak D-dimer values. Results Of 2.149 patients with confirmed COVID-19, 811 (38%) presented with elevated D-dimer levels. ICU admission was required for 239 patients, either due to direct admission or worsening conditions. An initial D-dimer value of ≥0.93 mg/L FEU indicated the need for ICU admission, while a peak D-dimer value of 5.65 mg/L FEU predicted mortality. The AUC for the initial D-dimer was 0.60 (95% CI: 0.55-0.64), indicating moderate discriminatory power. The AUC for the peak D-dimer was 0.58 (95% CI: 0.54-0.62), suggesting lower predictive accuracy for peak values. Sensitivity was high for both initial (0.925) and peak (0.960) D-dimer values, although specificity was lower, especially for the peak D-dimer (0.486), resulting in a higher rate of false positives. Among the ICU patients, the age range was 27-97 years, with a mean of 53.5 years. Males were more affected than females (71% vs. 29%), with a male-to-female ratio of 1.4:1. Of the ICU patients, 64.8% recovered, while 35.2% succumbed to the disease. Younger patients (mean age: 50.5 ± 12 years) recovered faster than older patients (mean age: 64 ± 16 years), with a significant difference in recovery time (p < 0.001). Gender did not significantly impact outcomes (p = 0.743). Survivors spent less time in the ICU (3-7 days) compared to non-survivors (4-14 days) (p = 0.041). Conclusion Serial D-dimer monitoring is essential for predicting outcomes and guiding treatment in COVID-19 patients. Initial and peak D-dimer values can help identify patients requiring intensive care and those at risk of mortality, allowing for timely interventions. D-dimer levels should be integrated into routine clinical assessments for managing COVID-19 patients.

Multiple remotely sensed datasets and machine learning models to predict chlorophyll-a concentration in the Nakdong River, South Korea.

The Nakdong River is a crucial water resource in South Korea, supplying water for various purposes such as potable water, irrigation, and recreation. However, the river is vulnerable to algal blooms due to the inflow of pollutants from multiple points and non-point sources. Monitoring chlorophyll-a (Chl-a) concentrations, a proxy for algal biomass is essential for assessing the trophic status of the river and managing its ecological health. This study aimed to improve the accuracy and reliability of Chl-a estimation in the Nakdong River using machine learning models (MLMs) and simultaneous use of multiple remotely sensed datasets. This study compared the performances of four MLMs: multi-layer perceptron (MLP), support vector machine (SVM), random forest (RF), and eXetreme Gradient Boosting (XGB) using three different input datasets: (1) two remotely sensed datasets (Sentinel-2 and Landsat-8), (2) standalone Sentinel-2, and (3) standalone Landsat-8. The results showed that the MLP model with multiple remotely sensed datasets outperformed other MLMs with 0.43 - 0.86 greater in R2 and 0.36 - 5.88 lower in RMSE. The MLP model demonstrated the highest performance across the range of Chl-a concentrations and predicted peaks above 20 mg/m3 relatively well compared to other models. This was likely due to the capacity of MLP to handle imbalanced datasets. The predictive map of the spatial distribution of Chl-a generated by MLP well captured the areas with high and low Chl-a concentrations. This study pointed out the impacts of imbalanced Chl-a concentration observations (dominated by low Chl-a concentrations) on the performance of MLMs. The data imbalance likely led to MLMs poorly trained for high Chl-a values, producing low prediction accuracy. In conclusion, this study demonstrated the value of multiple remotely sensed datasets in enhancing the accuracy and reliability of Chl-a estimation, mainly when using the MLP model. These findings would provide valuable insights into utilizing MLMs effectively for Chl-a monitoring.

Research on Machining Quality Prediction Method Based on Machining Error Transfer Network and Grey Neural Network

Machining quality prediction is the critical link of quality control in parts machining. With the advent of the Industry 4.0 era, intelligent manufacturing and data-driven technologies bring new ideas for quality control in complex machining processes. Quality control is complicated for multi-process, multi-condition, small-batch, and high-precision parts processing requirements. To solve this problem, this paper proposes a machining quality prediction method based on the machining error transfer network and the grey neural network. Initially, by constructing a processing error transfer network, the error transfer law in part processing is described, and the PageRank algorithm and the influence degree of the nodes are used to determine the critical quality features. Additionally, the problem of low prediction accuracy due to small sample data and multiple coupling relationships is solved using the grey neural network algorithm, and a high accuracy prediction of critical quality features is achieved. Finally, the effectiveness and reliability of the method are verified by the case of medium-speed marine diesel engine fuselage processing. The results indicate that this method not only effectively identifies critical quality features in the machining process of complex parts, but it also maintains a high predictive accuracy for these features, even with small samples and limited data.

Pantograph fault prediction of urban rail transit vehicles based on edge feature extraction and detection

Nowadays, as an indispensable part of urban infrastructure, urban rail transit (URT) vehicles have also developed rapidly. A large amount of manpower, material resources, and financial resources need to be invested in the construction process of URT. For URT vehicles, research on more accurate fault prediction methods can save a lot of maintenance costs and improve the reliability of URT construction. As an important electrical equipment for urban rail transit vehicles to obtain electric energy from the catenary, the operation of rail transit vehicles puts forward higher performance requirements for the pantograph. For solving the problems of low accuracy of fault prediction, over reliance on practical experience and high cost of fault prediction in the application of traditional URT vehicle pantograph fault prediction model. Combining sensor network and artificial intelligence algorithm, this paper analyzed the traditional rail transit vehicle pantograph fault prediction model, and verified it through comparative experiments. Through the comparative analysis of the experimental results, this paper can draw a conclusion that compared with the traditional rail transit vehicle pantograph fault prediction model, the rail transit vehicle pantograph fault prediction model has higher fault prediction accuracy, less model response time, lower risk of pantograph failure, higher model application satisfaction, and the accuracy of fault prediction increased by about 6.6%. The rail transit vehicle pantograph fault prediction model can effectively improve the accuracy of vehicle pantograph fault prediction, which can greatly promote the safety of URT and promote the intelligent process of URT.

Efficient prediction framework for large-scale nonlinear petrochemical process based on feature selection and temporal-attention LSTM: Applied to fluid catalytic cracking

Data-driven modeling plays a vital role in petrochemical industry, especially fluid catalytic cracking (FCC). However, the long operational cycles, large-scale measurements, multivariate data, and intricate temporal correlations in FCC units may lead to the problem of low prediction accuracy when only use a single time series data-driven modeling neural network such as long short-term memory (LSTM) network. To address these challenges, an effective prediction framework is proposed that integrates LSTM network with extreme gradient boosting (XGBOOST)-based feature selection and temporal-attention (TA) mechanisms. XGBOOST is applied to filter features related to the predictive variables in order to eliminate redundant variables. TA mechanisms within an LSTM network is used to capture the relevant historical time steps of the current moment. The results of our efficient prediction framework, applied to FCC process and three additional petrochemical processes, have proven to be superior to other methods.

Prediction of the effective diffusion coefficient on sulfate ions in heterogeneous concrete based on Mori-Tanaka scheme

The interfacial transition zone (ITZ) between the aggregates and the matrix in concrete is the main reason for the low prediction accuracy of the effective diffusion coefficient of sulfate ions in concrete. To solve this problem, a new multi-scale prediction model of the effective diffusion coefficient for the transport of sulfate in concrete was established based on the Mori-Tanaka scheme, which fully reflects the characteristics of the imperfect ITZ, the morphological characteristics of the aggregates, the aggregate grading, and the time-varying characteristics of the content of the ITZ, the porosity and the tortuosity of the pore structure. The results showed that the prediction results of the model were basically consistent with the experimental and literature results, and the maximum error was only 20.43 %. In addition, taking the commonly used strength grades C30 and C50 concrete in engineering as examples, the changes in effective diffusion coefficient under different concentrations of sulfate erosion were predicted, showing a trend of first decreasing, plateauing, then increasing, and objectively reflecting the objective law of sulfate transport-reaction-filling-expansion damage in concrete. The predicted results confirmed that at the concentration of 3 % Na2SO4 solution, the starting time of expansion for C50 concrete is approximately 3 years later than that for C30 concrete, verifying that enhancing the concrete's strength grade significantly improves its sulfate corrosion resistance.

Logistic regression analysis and machine learning for predicting post-stroke gait independence: a retrospective study

This study investigated whether machine learning (ML) has better predictive accuracy than logistic regression analysis (LR) for gait independence at discharge in subacute stroke patients (n = 843) who could not walk independently at admission. We developed prediction models using LR and five ML algorithms—specifically, the decision tree (DT), support vector machine, artificial neural network, ensemble learning, and k-nearest neighbor methods. Functional Independence Measure sub-items were used to evaluate the ability to walk independently. Model predictive accuracies were evaluated using areas under receiver operating characteristic curves (AUCs) as well as accuracy, precision, recall, F1 score, and specificity. The AUC for DT (0.812) was significantly lower than those for the other algorithms (p < 0.01); however, the AUC for LR (0.895) did not differ significantly from those for the other models (0.893–0.903). Other performance metrics showed no substantial differences between LR and ML algorithms. In conclusion, the DT algorithm had significantly low predictive accuracy, and LR showed no significant difference in predictive accuracy compared with the other ML algorithms. As its predictive accuracy is similar to that of ML, LR can continue to be used for predicting the prognosis of gait independence, with additional advantages of being easily understandable and manually computable.

Predicting Ozone Concentration in Hangzhou with the Fusion Class Stacking Algorithm

Aiming at the problem that the single machine learning model has low prediction accuracy of daily average ozone concentration, an ozone concentration prediction method based on the fusion class Stacking algorithm （FSOP） was proposed, which combined the statistical method ordinary least squares （OLS） with machine learning algorithms and improved the prediction accuracy of the ozone concentration prediction model by integrating the advantages of different learners. Based on the principle of the Stacking algorithm, the observation data of the daily maximum 8h ozone average concentration and meteorological reanalysis data in Hangzhou from January 2017 to December 2022 were used. Firstly, the specific ozone concentration prediction models based on the light gradient boosting machine （LightGBM） algorithm, long short-term memory model （LSTM）, and Informer model were established, respectively. Then, the prediction results of the above models were used as meta-features, and the OLS algorithm was used to obtain the prediction expression of ozone concentration to fit the observed ozone concentration. The results showed that the prediction accuracy of the model combined with the class Stacking algorithm was improved, and the fitting effect of ozone concentration was better. Among them, R2, RMSE, and MAE were 0.84, 19.65 μg·m-3, and 15.50 μg·m-3, respectively, which improved the prediction accuracy by approximately 8% compared with that of the single machine learning model.

Multivariate quality prediction of thin-walled parts machining using multi-task parallel deep transfer learning

Multivariate machining quality prediction of thin-walled parts with multiple machining features is a complex problem due to different data distribution between training and unlabelled test samples. Traditional quality prediction methods ignore the correlation of multiple quality labels and do not consider changes in data distribution, resulting in low accuracy of multivariate quality prediction. Therefore, a multivariate quality prediction method using multi-task parallel deep transfer learning is proposed to solve this problem. Specifically, a multi-output quality prediction model of cross-machining features is constructed through the joint design of multi-task parallel learning and deep transfer learning. Furthermore, a domain matcher is designed to form multiple transfer strategies, which can be used for dynamic matching of multi-source and multi-target machining features with multiple quality labels. The domain invariant data features through dynamic domain adaptation are extracted to deal with data distribution discrepancy between the source and target domains. Finally, the results of multiple comparison experiments show that the proposed method can effectively achieve the accurate quality prediction of the target domain with unlabelled labels and different distributions. Compared with the traditional methods, the proposed method has improved by 8.34%, 7.14%, and 9.09%, respectively, in MAE, RMSE, and score on average.

Prediction of hydrogen production in proton exchange membrane water electrolysis via neural networks

Advancements in water electrolysis technologies are crucial for green hydrogen production. Proton exchange membrane water electrolysis (PEMWE) is characterized by its efficiency and environmental benefits. The prediction and optimization of hydrogen production rates (HPRs) in PEMWE systems is difficult and still challenging because of the complexity of the system as well as the operational parameters. The integration of artificial intelligence (AI) and machine learning (ML) appears to be effective in optimization within the energy sector. Hence, this work employs the artificial neural network (ANN) to develop a model that accurately predicts HPR in PEMWE setups. A novel approach is introduced by employing the Levenberg–Marquardt backpropagation (LMBP) algorithm for training the ANN. This model is designed to predict HPR based on critical operational parameters, including anode and cathode areas (mm2), cell voltage (V) and current (A), water flow rate (mL/min), power (W), and temperature (K). The optimized ANN configuration features an architecture with 7 input nodes, two hidden layers of 64 neurons each, and a single output node. The performance of the ANN model was evaluated against conventional regression models using key metrics: mean squared error (MSE), coefficient of determination (R2), and mean absolute error (MAE). The findings of this study reveal that the developed ANN model significantly outperforms traditional models, achieving an R2 value of 0.9989 and an MAE of 0.012. In comparison, random forest (R2 = 0.9795), linear regression (R2 = 0.9697), and support vector machines (R2 = − 0.4812) show lower predictive accuracy, underscoring the ANN model's superior performance. This work demonstrates the efficiency of the LMBP in enhancing hydrogen production forecasts and sets a foundation for future improvements in PEMWE efficiency. By enabling precise control and optimization of operational parameters, this study contributes to the broader goal of advancing green hydrogen production as a viable and scalable alternative to fossil fuels, offering both immediate and long-term benefits to sustainable energy initiatives.

Research on a semi-supervised soft sensor modelling method for complex chemical processes based on INGO-VMD-ESN

Abstract The dynamic and non-linear nature of complex chemical processes often leads to low prediction accuracy of key quality variables by traditional soft sensors, thus affecting the overall system control accuracy and operational efficiency. Therefore, this paper proposes a semi-supervised soft sensor modelling method based on improved the northern goshawk optimization (INGO)-variable mode decomposition (VMD)-echo state network (ESN). Firstly, a new semi-supervised fusion method is proposed to address the problem of model training difficulty due to the scarcity of labelled samples and process dynamics, which reconstructs the sample dataset by fusing labelled and unlabelled samples into more representative new samples, improving the model’s generalization ability. Secondly, for the noise interference present in the reconstructed data, the input data is denoised using the VMD method to improve the quality of data. Then, a soft sensor model is built based on ESN. Additionally, the denoising and prediction performance of VMD and ESN is significantly affected by parameters, therefore the paper utilizes the INGO algorithm to achieve parameter rectification for VMD and ESN. Finally, the method is validated based on actual sulphur recovery data from a refinery. The results demonstrate that the method effectively mitigates the impact of dynamics and nonlinearity in the complex chemical process which enhances prediction accuracy.

Selection of Tuning Parameter and Comparison of Lasso and Adaptive Lasso on ZYZ Condition: A Monte Carlo Study

One of the fundamental objectives of statistics is to achieve accurate predictions. In high-dimensional settings (where the number of variables, p, exceeds the number of observations, n), the performance of ordinary least squares (OLS) is often suboptimal due to its high variance, which leads to lower prediction accuracy. Shrinking the variables is a promising approach, and methods such as ridge regression, elastic net, lasso, and adaptive lasso are well-known techniques for this purpose. While variable shrinkage introduces a small bias, it significantly reduces the variance compared to OLS. The effectiveness of shrinkage methods largely depends on the selection of the tuning parameter. Cross-validation and the Bayesian Information Criterion (BIC) are commonly used for this purpose, and an improved version of BIC has shown impressive results.???????? = (5.6,5.6,5.6,0), ???????? = (3,1.5,0,0,2,0,0,0), ???????? = (0.85,0.85,0.85,0) are the multiple regression models which are compared.

RUL Prediction of Rolling Bearings Based on Multi-Information Fusion and Autoencoder Modeling

As an important part of industrial equipment, the safe and stable operation of rolling bearings is an important guarantee for the performance of mechanical equipment. Aiming at the problem that it is difficult to characterize the running state of rolling bearings, this paper mainly analyzes and processes the vibration signals of rolling bearings, extracts and fuses multi-information entropy, and monitors the running state of rolling bearings and predicts the remaining useful life prediction (RUL) through test verification. Firstly, in view of the difficulty in characterizing the bearings running state characteristics, a rolling bearings running state monitoring method based on multi-information entropy fusion and denoising autoencoder (DAE) was proposed to extract the multi-entropy index features of vibration signals to improve the accuracy of feature extraction, and to solve the problem of not obvious information representation of a single feature indicator and missing information in the feature screening process. Secondly, in view of the problems of low prediction accuracy and poor robustness and generalization in traditional RUL models, a rolling bearings RUL model combining convolutional autoencoder (CAE) and bidirectional long short-term memory network (BiLSTM) was proposed. The introduction of convolution operation made CAE have the feature of weight sharing, reducing the complexity of the model. Finally, the XJTU-SY data set was used to verify the constructed model. The results show that the condition monitoring model established in this paper can accurately evaluate the running state of the rolling bearing and accurately locate the failure time. At the same time, the residual life prediction model can realize the residual life prediction of most data sets, and has good accuracy and robustness.

Collaborative-driven reservoir formation pressure prediction using GAN-ML models and well logging data

Formation pressure is the foundation and prerequisite for achieving efficient drilling and risk control in complex geological formations. However, intelligent prediction of formation pressure faces challenges such as insufficient sample sizes, poor prediction performance, and low prediction accuracy, which severely restrict the realization of safe and efficient drilling. To address this, this paper proposes a new method based on Generative Adversarial Networks (GAN) and Machine Learning (ML), aiming to improve adaptation to complex geological conditions and effectively capture the nonlinear relationship between logging data and formation pressure for intelligent prediction of formation pressure. The research results show that the GAN technology successfully amplified the 125 cable-measured formation pressure data by 204.8 times. Compared to machine learning predictions without using GAN technology, the constructed GAN-ML model reduced the average root mean square error by 0.59 MPa and the average absolute error by 0.71 MPa in the training set. The GAN-ML model predicted the formation pressure of adjacent wells with an average root mean square error of 1.59 MPa and an average absolute error of 1.96 MPa compared to the cable-measured formation pressure values. This achievement significantly enhances the robustness and generalization performance of intelligent models, demonstrating the potential of GAN-ML in addressing small sample data problems. It opens a new technical path for data-driven intelligent prediction and provides innovative data analysis and prediction methods for the field of geological exploration.

Remote Sensing Data Assimilation in Crop Growth Modeling from an Agricultural Perspective: New Insights on Challenges and Prospects

The frequent occurrence of global climate change and natural disasters highlights the importance of precision agricultural monitoring, yield forecasting, and early warning systems. The data assimilation method provides a new possibility to solve the problems of low accuracy of yield prediction, strong dependence on the field, and poor adaptability of the model in traditional agricultural applications. Therefore, this study makes a systematic literature retrieval based on Web of Science, Scopus, Google Scholar, and PubMed databases, introduces in detail the assimilation strategies based on many new remote sensing data sources, such as satellite constellation, UAV, ground observation stations, and mobile platforms, and compares and analyzes the progress of assimilation models such as compulsion method, model parameter method, state update method, and Bayesian paradigm method. The results show that: (1) the new remote sensing platform data assimilation shows significant advantages in precision agriculture, especially in emerging satellite constellation remote sensing and UAV data assimilation. (2) SWAP model is the most widely used in simulating crop growth, while Aquacrop, WOFOST, and APSIM models have great potential for application. (3) Sequential assimilation strategy is the most widely used algorithm in the field of agricultural data assimilation, especially the ensemble Kalman filter algorithm, and hierarchical Bayesian assimilation strategy is considered to be a promising method. (4) Leaf area index (LAI) is considered to be the most preferred assimilation variable, and the study of soil moisture (SM) and vegetation index (VIs) has also been strengthened. In addition, the quality, resolution, and applicability of assimilation data sources are the key bottlenecks that affect the application of data assimilation in the development of precision agriculture. In the future, the development of data assimilation models tends to be more refined, diversified, and integrated. To sum up, this study can provide a comprehensive reference for agricultural monitoring, yield prediction, and crop early warning by using the data assimilation model.

Spatial Mapping of Soil CO2 Flux in the Yellow River Delta Farmland of China Using Multi-Source OpticalRemote Sensing Data

The spatial prediction of soil CO2 flux is of great significance for assessing regional climate change and high-quality agricultural development. Using a single satellite to predict soil CO2 flux is limited by climatic conditions and land cover, resulting in low prediction accuracy. To this end, this study proposed a strategy of multi-source spectral satellite coordination and selected seven optical satellite remote sensing data sources (i.e., GF1-WFV, GF6-WFV, GF4-PMI, CB04-MUX, HJ2A-CCD, Sentinel 2-L2A, and Landsat 8-OLI) to extract auxiliary variables (i.e., vegetation indices and soil texture features). We developed a tree-structured Parzen estimator (TPE)-optimized extreme gradient boosting (XGBoost) model for the prediction and spatial mapping of soil CO2 flux. SHapley additive explanation (SHAP) was used to analyze the driving effects of auxiliary variables on soil CO2 flux. A scatter matrix correlation analysis showed that the distributions of auxiliary variables and soil CO2 flux were skewed, and the linear correlations between them (r &lt; 0.2) were generally weak. Compared with single-satellite variables, the TPE-XGBoost model based on multiple-satellite variables significantly improved the prediction accuracy (RMSE = 3.23 kg C ha−1 d−1, R2 = 0.73), showing a stronger fitting ability for the spatial variability of soil CO2 flux. The spatial mapping results of soil CO2 flux based on the TPE-XGBoost model revealed that the high-flux areas were mainly concentrated in eastern and northern farmlands. The SHAP analysis revealed that PC2 and the TCARI of Sentinel 2-L2A and the TVI of HJ2A-CCD had significant positive driving effects on the prediction accuracy of soil CO2 flux. The above results indicate that the integration of multiple-satellite data can enhance the reliability and accuracy of spatial predictions of soil CO2 flux, thereby supporting regional agricultural sustainable development and climate change response strategies.

Multi-granularity spatial temporal graph convolution network with consecutive attention for human motion prediction

Human motion prediction is attracting increasing attention for its numerous potential applications in fields including autonomous driving, video surveillance and virtual reality. However, accurate motion prediction is challenging due to the complex spatial dependencies, dynamic temporal correlations and high dimension of human pose sequences. Existing graph-based methods rarely consider positional and channel information of the feature map, resulting in lower prediction accuracy. Therefore, we propose a novel multi-granularity spatial temporal graph convolution network with consecutive attention (MSTCA) for human motion prediction. Firstly, a multi-granularity spatial convolution network is introduced to capture spatial joint features through multiple kernel sizes. Then, consecutive attention module is proposed to capture both positional and channel information of the feature map. Next, MSTCA uses multi-granularity temporal convolutional network to extract temporal correlations with multiple receptive fields and predict future poses. Finally, a decoder composed of a 2D convolution layer and several PRelu layers integrates the output of the whole model. Experimental results on the GTA-IM and PROX datasets demonstrate that our method significantly improves the accuracy of human motion prediction in comparison to the existing approaches.

Short-Term Power Load Forecasting Based on Secondary Cleaning and CNN-BILSTM-Attention

Accurate power load forecasting can provide crucial insights for power system scheduling and energy planning. In this paper, to address the problem of low accuracy of power load prediction, we propose a method that combines secondary data cleaning and adaptive variational mode decomposition (VMD), convolutional neural networks (CNN), bi-directional long short-term memory (BILSTM), and adding attention mechanism (AM). The Inner Mongolia electricity load data were first cleaned use the K-means algorithm, and then further refined with the density-based spatial clustering of applications with the noise (DBSCAN) algorithm. Subsequently, the parameters of the VMD algorithm were optimized using a multi-strategy Cubic-T dung beetle optimization algorithm (CTDBO), after which the VMD algorithm was employed to decompose the twice-cleaned load sequences into a number of intrinsic mode functions (IMFs) with different frequencies. These IMFs were then used as inputs to the CNN-BILSTM-Attention model. In this model, a CNN is used for feature extraction, BILSTM for extracting information from the load sequence, and AM for assigning different weights to different features to optimize the prediction results. It is proved experimentally that the model proposed in this paper achieves the highest prediction accuracy and robustness compared to other models and exhibits high stability across different time periods.

Predicting the soil bulk density using a new spectral PTF based on intact samples

Sample collection and measurement of soil bulk density (BD) are often labor-intensive and expensive in large regions. Conversely, soil spectra are easy to measure and facilitate BD prediction. However, the literature suggests that the damage to the physical structure of soil during scanning spectra on the ground and/or sieved samples might hinder the capacity of spectral technology to accurately predict BD. In addition, because some soil properties that have high correlations with BD, such as the soil organic matter (SOM), are routinely measured and available in most soil databases, coupling them with soil spectra may improve BD prediction compared to using soil properties or spectra. Therefore, in this study, we propose a novel spectral pedo-transfer function (spectral PTF) that couples the measured visible and near-infrared spectra of soils on intact samples and other soil properties to accurately predict the BD (BD = f (soil spectra, soil properties)), which is different from the traditional PTF that uses only soil properties (BD = f (soil properties)) or spectra alone (BD = f (soil spectra)). In this study, we collected topsoil (0–20 cm) and subsoil (20–40 cm) samples from 586 sites in Northeast China, covering a large area of 1.09 million km2 characterized by black soils with high SOM contents. Five routinely measured soil properties were selected: SOM, moisture content (MC), Sand, Silt, and Clay, and various spectral PTFs with one, two, and three soil properties were calibrated using the partial least square regression. The cross-validation results show that the traditional PTF can only predict BD for subsoil with an R2 of 0.51 and an RMSE of 0.11 g·cm−3 when using SOM + MC + Silt or SOM + MC. Compared to subsoil, topsoil and all layers (topsoil + subsoil) had a lower BD prediction accuracy, and a saturation effect was observed for BD values above 1.5 g·cm−3. Unexpectedly, the soil spectra did not provide a higher BD prediction accuracy than traditional PTFs, although the spectra were measured on intact samples. However, adding soil properties to the spectral PTF improved the prediction accuracy and saturation effect for high BD values. The optimal spectral PTF with a single soil property (MC) showed an acceptable BD prediction performance with R2≥0.49, RPD>1.4, and RPIQ>1.7 regardless of whether the sample was topsoil, subsoil, or all layers. Furthermore, the spectral PTF with two or three soil properties yielded a slightly better prediction performance and a more stable prediction among different combinations of soil properties. These results indicate that soil properties and spectra are irreplaceable for BD prediction. Our study demonstrates the potential of spectral PTFs for the accurate prediction of BD and offers insights into the prediction of other soil properties using soil spectra.