Candidate Inputs Research Articles

Inversion Method for Transformer Winding Hot Spot Temperature Based on Gated Recurrent Unit and Self-Attention and Temperature Lag.

The hot spot temperature of transformer windings is an important indicator for measuring insulation performance, and its accurate inversion is crucial to ensure the timely and accurate fault prediction of transformers. However, existing studies mostly directly input obtained experimental or operational data into networks to construct data-driven models, without considering the lag between temperatures, which may lead to the insufficient accuracy of the inversion model. In this paper, a method for inverting the hot spot temperature of transformer windings based on the SA-GRU model is proposed. Firstly, temperature rise experiments are designed to collect the temperatures of the entire side and top of the transformer tank, top oil temperature, ambient temperature, the cooling inlet and outlet temperatures, and winding hot spot temperature. Secondly, experimental data are integrated, considering the lag of the data, to obtain candidate input feature parameters. Then, a feature selection algorithm based on mutual information (MI) is used to analyze the correlation of the data and construct the optimal feature subset to ensure the maximum information gain. Finally, Self-Attention (SA) is applied to optimize the Gate Recurrent Unit (GRU) network, establishing the GRU-SA model to perceive the potential patterns between output feature parameters and input feature parameters, achieving the precise inversion of the hot spot temperature of the transformer windings. The experimental results show that considering the lag of the data can more accurately invert the hot spot temperature of the windings. The inversion method proposed in this paper can reduce redundant input features, lower the complexity of the model, accurately invert the changing trend of the hot spot temperature, and achieve higher inversion accuracy than other classical models, thereby obtaining better inversion results.

SIG: Speaker Identification in Literature via Prompt-Based Generation

Identifying speakers of quotations in narratives is an important task in literary analysis, with challenging scenarios including the out-of-domain inference for unseen speakers, and non-explicit cases where there are no speaker mentions in surrounding context. In this work, we propose a simple and effective approach SIG, a generation-based method that verbalizes the task and quotation input based on designed prompt templates, which also enables easy integration of other auxiliary tasks that further bolster the speaker identification performance. The prediction can either come from direct generation by the model, or be determined by the highest generation probability of each speaker candidate. Based on our approach design, SIG supports out-of-domain evaluation, and achieves open-world classification paradigm that is able to accept any forms of candidate input. We perform both cross-domain evaluation and in-domain evaluation on PDNC, the largest dataset of this task, where empirical results suggest that SIG outperforms previous baselines of complicated designs, as well as the zero-shot ChatGPT, especially excelling at those hard non-explicit scenarios by up to 17% improvement. Additional experiments on another dataset WP further corroborate the efficacy of SIG.

Multilayer perceptron and support vector regression models for feline parturition date prediction

A crucial challenge in feline obstetric care is the accurate prediction of the parturition date during late pregnancy. The classic simple linear regression (SLR) model, which employed the fetal biparietal diameter (BPD) as the single input feature, was frequently applied for such prediction with limited accuracy. Since Multilayer Perceptron (MLP) and Support Vector Regression (SVR) are now two of the most potent scientific regression models, this study, for the first time, introduced such models as the new promising tools for feline parturition date prediction. The following features were candidate inputs for our models: biparietal diameter (BPD), litter size, and maternal weight. We observed and compared the performance results for each model. As the best-performed model, MLP delivered the highest coefficient score (0.972 ± 0.006), lowest mean absolute error score (1.110 ± 0.060), and lowest mean squared error score (1.540 ± 0.141), respectively. For the first time in this study, BPD, litter size, and maternal weight were considered the essential features for the innovative MLP and SVR modeling. With the optimized model parameters and the described analytical platform, further verification of these advanced models in feline obstetric practices is feasible.

Predicting apparent adsorption capacity of sediment-amended activated carbon for hydrophobic organic contaminants using machine learning

In-situ stabilization of hydrophobic organic compounds (HOCs) using activated carbon (AC) is a promising sediment remediation approach. However, predicting HOC adsorption capacity of sediment-amended AC remains a challenge because a prediction model is currently unavailable. Thus, the objective of this study was to develop machine learning models that could predict the apparent adsorption capacity of sediment-amended AC (KAC,apparent) for HOCs. These models were trained using 186 sets of experimental data obtained from the literature. The best-performing model among those employing various model frameworks, machine learning algorithms, and combination of candidate input features excellently predicted logKAC,apparent with a coefficient of determination of 0.94 on the test dataset. Its prediction results and experimental data for KAC,apparent agreed within 0.5 log units with few exceptions. Analysis of feature importance for the machine learning model revealed that KAC,apparent was strongly correlated with the hydrophobicity of HOCs and the particle size of AC, which agreed well with the current knowledge obtained from experimental and mechanistic assessments. On the other hand, correlation of KAC,apparent to sediment characteristics, duration of AC-sediment contact, and AC dose identified in the model disagreed with relevant arguments made in the literature, calling for further assessment in this subject. This study highlights the promising capability of machine learning in predicting adsorption capacity of AC in complex systems. It offers unique insights into the influence of model parameters on KAC,apparent.

An optimized hybrid methodology for short‐term traffic forecasting in telecommunication networks

AbstractWith the rapid development of telecommunication networks, the predictability of network traffic is of significant interest in network analysis and optimization, bandwidth allocation, and load balancing adjustment. Consequently, in recent years, significant research attention has been paid to forecasting telecommunication network traffic. Telecommunication traffic forecasting problems can be considered a time‐series problem, wherein periodic historical data is fed as the input to a model. Time‐series forecasting approaches are broadly categorized as statistical machine learning (ML) methods and their combinations. Statistical approaches forecast linear characteristics of time‐series data, unable to capture nonlinear and complex patterns. ML‐based approaches can model nonlinear characteristics of data. In recent years, hybrid approaches combining statistical and ML‐based approaches have been widely used to model linear and nonlinear data characteristics. However, the performance of these approaches highly depends on feature selection techniques and hyper‐parameter tuning of ML methods. A novel hybrid method is proposed for short‐term traffic forecasting based on feature selection and hyperparameter optimization to address this problem. It combines statistical and ML methods to model linear and nonlinear components of data. First, a novel feature selection technique, modified mutual information based on a linear combination of targets, is proposed to find the candidate input variables. Next, a combination of vector auto regressive moving average (VARMA), long short‐term memory (LSTM), and multilayer perceptron (MLP), called VARMA‐LSTM‐MLP forecaster, is suggested to forecast short‐term traffic. A hybrid metaheuristic algorithm, composed of firefly and BAT, is employed to find the optimal set of hyper‐parameter values. The proposed method is assessed by a real‐world dataset containing Tehran city's daily telecommunication data in IRAN. The evaluation results demonstrate that the proposed method outperforms the existing methods in terms of mean squared error and mean absolute error.

Statistical refinement of the North American Multi-Model Ensemble precipitation forecasts over Karoon basin, Iran

Abstract An effective postprocessing approach has been examined to improve the skill of North American Multi-Model Ensemble (NMME) precipitation forecasts in the Karoon basin, Iran. The Copula–Bayesian approach was used along with the Normal Kernel Density marginal distribution and the Kernel Copula function. This process creates more than one postprocessing precipitation value as results candidates (first pass). A similar process is used for a second pass to obtain preprocessed values based on the candidate inputs, which helps identify the most suitable postprocessed value. The application of the technique for order preference by similarity to the ideal solution method based on conditional probability distribution functions of the first and second passes leads to achieving final improved forecast data among the existing candidates. To validate the results, data from 1982–2010 and 2011–2018 were used for the calibration and forecast periods. The results show that while the GFDL and CFS2 models tend to overestimate precipitation, most other NMME models underestimate it. Postprocessing improves the accuracy of forecasts for most models by 20%–40%. Overall, the proposed Copula–Bayesian postprocessing approach could provide more reliable forecasts with higher spatial and temporal consistency, better detection of extreme precipitation values, and a significant reduction in uncertainties.

Mobile Assessments of Mood, Cognition, Smartphone-Based Sensor Activity, and Variability in Craving and Substance Use in Patients With Substance Use Disorders in Norway: Prospective Observational Feasibility Study.

Patients with substance use disorders (SUDs) are at increased risk for symptom deterioration following treatment, with up to 60% resuming substance use within the first year posttreatment. Substance use craving together with cognitive and mental health variables play important roles in the understanding of the trajectories from abstinence to substance use. This prospective observational feasibility study aims to improve our understanding of specific profiles of variables explaining SUD symptom deterioration, in particular, how individual variability in mental health, cognitive functioning, and smartphone use is associated with craving and substance use in a young adult clinical population. In this pilot study, 26 patients with SUDs were included at about 2 weeks prior to discharge from inpatient SUD treatment from 3 different treatment facilities in Norway. Patients underwent baseline neuropsychological and mental health assessments; they were equipped with smartwatches and they downloaded an app for mobile sensor data collection in their smartphones. Every 2 days for up to 8 weeks, the patients were administered mobile ecological momentary assessments (EMAs) to evaluate substance use, craving, mental health, cognition, and a mobile Go/NoGo performance task. Repeated EMAs as well as the smartphone's battery use data were averaged across all days per individual and used as candidate input variables together with the baseline measures in models of craving intensity and the occurrence of any substance use episodes. A total of 455 momentary assessments were completed out of a potential maximum of 728 assessments. Using EMA and baseline data as candidate input variables and craving and substance use as responses, model selection identified mean craving intensity as the most important predictor of having one or more substance use episodes and with variabilities in self-reported impulsivity, mental health, and battery use as significant explanatory variables of craving intensity. This prospective observational feasibility study adds novelty by collecting high-intensity data for a considerable period of time, including mental health data, mobile cognitive assessments, and mobile sensor data. Our study also contributes to our knowledge about a clinical population with the most severe SUD presentations in a vulnerable period during and after discharge from inpatient treatment. We confirmed the importance of variability in cognitive function and mood in explaining variability in craving and that smartphone usage may possibly add to this understanding. Further, we found that craving intensity is an important explanatory variable in understanding substance use episodes.

Uncertainty quantification for spindle axial thermal error of CNC machine tools considering hysteresis effect

Most of the existing research on thermal error regression modeling of CNC machine tools establishes deterministic models, presents point predictions for thermal errors and focuses on the scenario where there is no hysteresis effect between input and output. There is little research on quantifying the uncertainties of spindle axial thermal error when there exist significant hysteresis effects between the temperature points and spindle axial thermal error. In this regard, this paper presents a novel uncertainty modeling method for spindle axial thermal error. Firstly, to screen out key temperature points, the whole temperature points are sorted according to the minimal redundancy maximal relevance (mRMR) criterion, and the candidate input feature sets are generated. Then, the gated recurrent unit (GRU) model is introduced to handle the hysteresis effects. Finally, the deterministic GRU model is transformed into the prediction interval-based GRU (PI-GRU) model, which can produce prediction intervals (PIs) of the spindle axial thermal error. The correctness and effectiveness of this method are verified by the spindle axial thermal error experiments. In contrast with the Gaussian process regression (GPR) method, the proposed method deals with the hysteresis effects more appropriately and performs better in uncertainty prediction accuracy.

Data-driven ion-independent relative biological effectiveness modeling using the beam quality Q

Beam quality Q = Z2/E (Z = ion charge, E = energy), an alternative to the conventionally used linear energy transfer (LET), enables ion-independent modeling of the relative biological effectiveness (RBE) of ions. Therefore, the Q concept, i.e. different ions with similar Q have similar RBE values, could help to transfer clinical RBE knowledge from better-studied ion types (e.g. carbon) to other ions. However, the validity of the Q concept has so far only been demonstrated for low LET values. In this work, the Q concept was explored in a broad LET range, including the so-called overkilling region. The particle irradiation data ensemble (PIDE) was used as experimental in vitro dataset. Data-driven models, i.e. neural network (NN) models with low complexity, were built to predict RBE values for H, He, C and Ne ions at different in vitro endpoints taking different combinations of clinically available candidate inputs: LET, Q and linear-quadratic photon parameter α x/β x. Models were compared in terms of prediction power and ion dependence. The optimal model was compared to published model data using the local effect model (LEM IV). The NN models performed best for the prediction of RBE at reference photon doses between 2 and 4 Gy or RBE near 10% cell survival, using only α x/β x and Q instead of LET as input. The Q model was not significantly ion dependent (p > 0.5) and its prediction power was comparable to that of LEM IV. In conclusion, the validity of the Q concept was demonstrated in a clinically relevant LET range including overkilling. A data-driven Q model was proposed and observed to have an RBE prediction power comparable to a mechanistic model regardless of particle type. The Q concept provides the possibility of reducing RBE uncertainty in treatment planning for protons and ions in the future by transferring clinical RBE knowledge between ions.

High resolution annual irrigation water use maps in China based-on input variables selection and convolutional neural networks

Water use and available water resources are the prerequisites for optimal water resources allocation, which is an efficient way to alleviate water scarcity all over the world. However, the spatial scales of water use and available water resources are often not matched due to their different ways for data surveying or observing. The spatial distributed (grid-scale) water use map is one of the ways to convert the spatial scales of the water use and available water resources. As irrigation is essential to guarantee sustainable development of agriculture, food security and economy, and accounts for most water use in China. A framework to generate high resolution (1 km) annual irrigation water use maps has been proposed. An iterative input variables selection (IIS) algorithm is adopted to select the optimal input variables among candidate input variables. After determining the optimal input variables, the convolutional neural network (CNN) is built to establish the relationship between the selected input variables and the irrigation water use. The spatial distributed irrigation water use maps can be produced by the trained CNN with the selected input variables at grid scale. The spatial distributed annual irrigation water use maps in China is produced at 1 km resolution from 1998 to 2013, and the performance of the framework has been proven to be credible with three metrics (i.e., root mean squared error, Nash Sutcliffe efficiency coefficient and relative error). Based on the spatial distributed annual irrigation water use maps, the spatial autocorrelation of annual irrigation water use in China is weak and the clustered pattern is random with 99% confidence. The temporal changing pattern mainly depends on precipitation and soil moisture in most prefectures, and the change of the cultivated area can also lead to dramatic change of the annual irrigation water use in China. The proposed framework can generate high resolution spatial distributed annual irrigation water use maps at grid scale, and the maps can be applied to ensure the optimal water resources allocation to realize efficient utilization of water resources and the agricultural policy-making.

A wind speed forecasting model based on multi-objective algorithm and interpretability learning

More accurate and reliable wind speed forecasting results can provide an effective assessment of wind energy resources and improve the efficiency of wind energy utilization. Therefore, this paper is devoted to constructing accurate wind speed forecasting models and quantitatively analyzing the models by using interpretable analysis. Firstly, a multivariate wind speed forecasting model (PMI-CMOGSA-RELM) is proposed based on machine learning methods and a clustering-based multi-objective gravity search algorithm (CMOGSA). Among them, wavelet packet decomposition (WPD) is used for noise reduction, candidate input feature pool and partial mutual information (PMI) are used for feature selection, and CMOGSA is used to optimize the final combined weights. Secondly, a new evaluation metric, Absolute Error Coverage Probability (AECP), is proposed to better evaluate forecasting accuracy. Then, post-hoc attribution analysis methods and visualization tools are used to analyze the forecasting model interpretability to help us better analyze the robustness and reliability of the forecasted results. Finally, this paper validates and evaluates the proposed model with two data sets of different resolutions. The experimental results not only prove the rationality of the AECP evaluation criteria, but also demonstrate that the proposed model has smaller errors, higher estimation accuracy, and is easier to understand.

Low-dimensional high-fidelity kinetic models for NOX formation by a compute intensification method

A novel compute intensification methodology to the construction of low-dimensional, high-fidelity “compact” kinetic models for NOX formation is designed and demonstrated. The method adapts the data intensive Machine Learned Optimisation of Chemical Kinetics (MLOCK) algorithm for compact model generation by the use of a combinatorial Latin Square method for virtual reaction network generation. A set of logical rules are defined which construct a minimally sized virtual reaction network comprising three additional nodes (N, NO, NO2). This NOX virtual reaction network is appended to a pre-existing compact model for methane combustion comprising fifteen nodes.The resulting eighteen node virtual reaction network is processed by the MLOCK coded algorithm to produce a plethora of compact model candidates for NOX formation during methane combustion. MLOCK automatically; populates the terms of the virtual reaction network with candidate inputs; measures the success of the resulting compact model candidates (in reproducing a broad set of gas turbine industry-defined performance targets); selects regions of input parameters space showing models of best performance; refines the input parameters to give better performance; and makes an ultimate selection of the best performing model or models.By this method, it is shown that a number of compact model candidates exist that show fidelities in excess of 75% in reproducing industry defined performance targets, with one model valid to >75% across fuel/air equivalence ratios of 0.5–1.0. However, to meet the full fuel/air equivalence ratio performance envelope defined by industry, we show that with this minimal virtual reaction network, two further compact models are required.

Soil Liquefaction Prediction Based on Bayesian Optimization and Support Vector Machines

Liquefaction has been responsible for several earthquake-related hazards in the past. An earthquake may cause liquefaction in saturated granular soils, which might lead to massive consequences. The ability to accurately anticipate soil liquefaction potential is thus critical, particularly in the context of civil engineering project planning. Support vector machines (SVMs) and Bayesian optimization (BO), a well-known optimization method, were used in this work to accurately forecast soil liquefaction potential. Before the development of the BOSVM model, an evolutionary random forest (ERF) model was used for input selection. From among the nine candidate inputs, the ERF selected six, including water table, effective vertical stress, peak acceleration at the ground surface, measured CPT tip resistance, cyclic stress ratio (CSR), and mean grain size, as the most important ones to predict the soil liquefaction. After the BOSVM model was developed using the six selected inputs, the performance of this model was evaluated using renowned performance criteria, including accuracy (%), receiver operating characteristic (ROC) curve, and area under the ROC curve (AUC). In addition, the performance of this model was compared with a standard SVM model and other machine learning models. The results of the BOSVM model showed that this model outperformed other models. The BOSVM model achieved an accuracy of 96.4% and 95.8% and an AUC of 0.93 and 0.98 for the training and testing phases, respectively. Our research suggests that BOSVM is a viable alternative to conventional soil liquefaction prediction methods. In addition, the findings of this research show that the BO method is successful in training the SVM model.

DeepBackRib: Deep learning to understand factors associated with readmissions after rib fractures.

Deep neural networks yield high predictive performance, yet obscure interpretability limits clinical applicability. We aimed to build an explainable deep neural network that elucidates factors associated with readmissions after rib fractures among nonelderly adults, termed DeepBackRib . We hypothesized that DeepBackRib could accurately predict readmissions and a game theoretic approach to elucidate how predictions are made would facilitate model explainability. We queried the 2017 National Readmissions Database for index hospitalization encounters of adults aged 18 to 64 years hospitalized with multiple rib fractures. The primary outcome was 3-month readmission(s). Study cohort was split 60-20-20 into training-validation-test sets. Model input features included demographic/injury/index hospitalization characteristics and index hospitalization International Classification of Diseases, Tenth Revision , diagnosis codes. The seven-layer DeepBackRib comprised multipronged strategies to mitigate overfitting and was trained to optimize recall. Shapley additive explanation analysis identified the marginal contribution of each input feature for predicting readmissions. A total of 20,260 patients met the inclusion criteria, among whom 11% (n = 2,185) experienced 3-month readmissions. Feature selection narrowed 3,164 candidate input features to 61, and DeepBackRib yielded 91%, 85%, and 82% recall on the training, validation, and test sets, respectively. Shapley additive explanation analysis quantified the marginal contribution of each input feature in determining DeepBackRib's predictions: underlying chronic obstructive pulmonary disease and long index hospitalization length of stay had positive associations with 3-month readmissions, while private primary payer and diagnosis of pneumothorax during index admission had negative associations. We developed and internally validated a high-performing deep learning algorithm that elucidates factors associated with readmissions after rib fractures. Despite promising predictive performance, standalone deep learning algorithms are insufficient for clinical prediction tasks: a concerted effort is needed to ensure that clinical prediction algorithms remain explainable. Prognostic and Epidemiological; Level III.

Impact of individual and treatment characteristics on wearable sensor-based digital biomarkers of opioid use

Opioid use disorder is one of the most pressing public health problems of our time. Mobile health tools, including wearable sensors, have great potential in this space, but have been underutilized. Of specific interest are digital biomarkers, or end-user generated physiologic or behavioral measurements that correlate with health or pathology. The current manuscript describes a longitudinal, observational study of adult patients receiving opioid analgesics for acute painful conditions. Participants in the study are monitored with a wrist-worn E4 sensor, during which time physiologic parameters (heart rate/variability, electrodermal activity, skin temperature, and accelerometry) are collected continuously. Opioid use events are recorded via electronic medical record and self-report. Three-hundred thirty-nine discreet dose opioid events from 36 participant are analyzed among 2070 h of sensor data. Fifty-one features are extracted from the data and initially compared pre- and post-opioid administration, and subsequently are used to generate machine learning models. Model performance is compared based on individual and treatment characteristics. The best performing machine learning model to detect opioid administration is a Channel-Temporal Attention-Temporal Convolutional Network (CTA-TCN) model using raw data from the wearable sensor. History of intravenous drug use is associated with better model performance, while middle age, and co-administration of non-narcotic analgesia or sedative drugs are associated with worse model performance. These characteristics may be candidate input features for future opioid detection model iterations. Once mature, this technology could provide clinicians with actionable data on opioid use patterns in real-world settings, and predictive analytics for early identification of opioid use disorder risk.

Computational assessment of groundwater salinity distribution within coastal multi-aquifers of Bangladesh

The rising salinity trend in the country’s coastal groundwater has reached an alarming rate due to unplanned use of groundwater in agriculture and seawater seeping into the underground due to sea-level rise caused by global warming. Therefore, assessing salinity is crucial for the status of safe groundwater in coastal aquifers. In this research, a rigorous hybrid neurocomputing approach comprised of an Adaptive Neuro-Fuzzy Inference System (ANFIS) hybridized with a new meta-heuristic optimization algorithm, namely Aquila optimization (AO) and the Boruta-Random forest feature selection (FS) was developed for estimating the salinity of multi-aquifers in coastal regions of Bangladesh. In this regard, 539 data samples, including ten water quality indices, were collected to provide the predictive model. Moreover, the individual ANFIS, Slime Mould Algorithm (SMA), and Ant Colony Optimization for Continuous Domains (ACOR) coupled with ANFIS (i.e., ANFIS-SMA and ANFIS-ACOR) and LASSO regression (Lasso-Reg) schemes were examined to compare with the primary model. Several goodness-of-fit indices, such as correlation coefficient (R), the root mean squared error (RMSE), and Kling-Gupta efficiency (KGE) were used to validate the robustness of the predictive models. Here, the Boruta-Random Forest (B-RF), as a new robust tree-based FS, was adopted to identify the most significant candidate inputs and effective input combinations to reduce the computational cost and time of the modeling. The outcomes of four selected input combinations ascertained that the ANFIS-OA regarding the best accuracy in terms of (R = 0.9450, RMSE = 1.1253 ppm, and KGE = 0.9146) outperformed the ANFIS-SMA (R = 0.9406, RMSE = 1.1534 ppm, and KGE = 0.8793), ANFIS-ACOR (R = 0.9402, RMSE = 1.1388 ppm, and KGE = 0.8653), Lasso-Reg (R = 0.9358), and ANFIS (R = 0.9306) models. Besides, the first candidate input combination (C1) by three inputs, including Cl− (mg/l), Mg2+ (mg/l), Na+ (mg/l), yielded the best accuracy among all alternatives, implying the role importance of (B-RF) feature selection. Finally, the spatial salinity distribution assessment in the study area ascertained the high predictability potential of the ANFIS-OA hybrid with B-RF feature selection compared to other paradigms. The most important novelty of this research is using a robust framework comprised of the non-linear data filtering technique and a new hybrid neuro-computing approach, which can be considered as a reliable tool to assess water salinity in coastal aquifers.

Bayesian optimization package: PHYSBO

PHYSBO (optimization tools for PHYSics based on Bayesian Optimization) is a Python library for fast and scalable Bayesian optimization. It has been developed mainly for application in the basic sciences such as physics and materials science. Bayesian optimization is used to select an appropriate input for experiments/simulations from candidate inputs listed in advance in order to obtain better output values with the help of machine learning prediction. PHYSBO can be used to find better solutions for both single and multi-objective optimization problems. At each cycle in the Bayesian optimization, a single proposal or multiple proposals can be obtained for the next experiments/simulations. These proposals can be obtained interactively for use in experiments. PHYSBO is available at https://github.com/issp-center-dev/PHYSBO. Program summaryProgram Title: PHYSBOCPC Library link to program files:https://doi.org/10.17632/22d72yb6k6.1Developer's repository link:https://github.com/issp-center-dev/PHYSBOLicensing provisions: GNU General Public License version 3Programming language: Python3External routines/libraries: NumPy, SciPy, MPI for Python.Nature of problem: Bayesian optimization (BO) can be used to select inputs that will yield better outputs from a list of candidate inputs with the help of machine learning prediction through a Gaussian process. Although BO is a powerful tool, two of its components, training the Gaussian process regression and optimizing the acquisition function, are generally computationally expensive. Moreover, hyperparameter tuning is necessary for the former process.Solution method: PHYSBO is a Python library for performing fast and scalable Bayesian optimization. To avoid the computationally expensive training process, PHYSBO uses a random feature map, Thompson sampling, and a one-rank Cholesky update. In addition, PHYSBO performs hyperparameter tuning automatically by maximizing the Type II likelihood, and MPI parallelization is used to reduce the calculation time for optimizing the acquisition function.

Long-term multi-step ahead forecasting of root zone soil moisture in different climates: Novel ensemble-based complementary data-intelligent paradigms

The root zone soil moisture (RZSM) is essential for monitoring and forecasting agricultural, hydrological, and meteorological systems. Accordingly, researchers are determined to improve robust machine learning (ML) models to increase the accuracy of the RZSM predictions. This paper designed new complementary forecasting paradigms hybridizing Empirical Wavelet Transform (EWT) and two modern ensemble-based ML models, namely, extreme gradient boosting (XGBoost) and categorical boosting (CatBoost), to forecast long-term multi-step ahead daily RZSM in very cold and very warm semi-arid regions of Iran. For this purpose, the required datasets consisting of soil properties and meteorological information were extracted from the satellite datasets during 2005–2020 for Ardabil and Minab sites. Afterward, the significant lags of RZSM time series and optimal influence candidate inputs were sought based on the partial autocorrelation function (PACF) and mutual information techniques, respectively. Selected lagged components of RZSM time series were decomposed using EWT into different sub-sequences and consequently concatenated with candidate inputs to feed the ensemble ML models to forecast one-, three-, and seven-day-ahead RZSM at each case study. The performance of EWT-CatBoost and EWT-XGBoost and their counterpart standalone approaches was firstly evaluated in forecasting one-, three-, and seven-day-ahead RZSM using satellite data in this study and their accuracy were compared with a standalone kernel ridge regression (KRR) and complementary EWT-KRR models based on several statistical metrics (e.g., correlation coefficient (R), root mean square error (RMSE), Nash–Sutcliffe model efficiency coefficient (NSE)) and diagnostic analysis. The outcomes of testing phase in Ardabil site ascertained that the EWT-CatBoost (for RZSM(t + 1), R= 0.9979, RMSE= 0.0019, and NSE= 0.9985; for RZSM(t + 3), R= 0.9934, RMSE= 0.0035, and NSE= 0.9885; for RZSM(t + 7), R= 0.9489, RMSE= 0.0109, and NSE= 0.8634) outperformed the other models. On the other hand, the EWT-XGBoost model according to its best results (for RZSM(t + 1), R= 0.9911, RMSE= 0.0064, and NSE= 0.9805; for RZSM(t + 3), R= 0.9807, RMSE= 0.0092, and NSE= 0.9589; for RZSM(t + 7), R= 0.9680, RMSE= 0.0120, and NSE= 0.9309) yielded the most promising accuracy in forecasting multi-step ahead daily RZSM followed by the EWT-CatBoost, and EWT-KRR, respectively.

Coordinated optimization on energy capture and torque fluctuation of wind turbines via variable weight NMPC with fuzzy regulator

The main challenge in improving energy harvest faced by modern large-scale wind turbines (WTs) comes from the fact that the blade rotor with the large inertia having a slow response impedes the optimal tip speed ratio tracking. On the premise that the future wind speed can be accurately predicted, nonlinear model predictive control (NMPC) can effectively improve the energy harvest efficiency of large WTs, but it is difficult to maximize the energy capture and minimize the torque fluctuation of the generator simultaneously. In this study, a fuzzy regulator is designed to update the weight coefficient of the cost function, and an improved multi-objective marine predator algorithm (IMMPA) is proposed to optimize the fuzzy regulator, so it is realized the coordinated optimization on energy capture and generator torque fluctuation. Specifically, based on the analysis of the performance of NMPC with fixed weight coefficient under different wind conditions, a basic fuzzy regulator is designed to adjust the weight coefficient according to the characteristics of wind conditions, and four groups of candidate inputs are defined. In order to fully explore the potential of the fuzzy regulator, IMMPA is used to optimize the membership function of the fuzzy regulator. Finally, the variable weight coefficient is used as the input of NMPC to update the objective function in real time. The simulation results show that compared with the one with the fixed weight coefficient, the NMPC controller using the variable weight improves the energy capture by 1.77% while reducing the generator torque fluctuation by 0.126%. Taking the concerned 1.5 MW WT as an example, the variable-weight NMPC could boost its annual energy production by 35842.5 kWh in comparison with the fixed-weight counterpart, showing its promising role in reducing the production cost for the WTs.

Receding interval prediction of district heat load via finite difference multi-operating-domain dynamic modelling

To realize low carbon emission, district heat load (DHL) prediction is of great significance to the efficient operation of urban district heating system (DHS). Due to spatial topology of central heating network, weather conditions and heat users show great spatiotemporal dispersion, whose influence to DHL is very complex and its prediction is challengeable. To solve this problem, a multi-operating-domain dynamic modelling structure is proposed in this paper. Firstly, through detailed analysis from first-principle, external factors such as weather and user factors are quantitatively included to form candidate inputs set where the NCA (Neighbourhood Component Analysis) algorithm is used to extract feature inputs. Considering time-delays of feature inputs to DHL, AIC (Akaike Information Criterion) is applied to determine delay orders. Then, feature inputs, DHL output and their delay-orders are integrated to form a finite difference operating space, representing by a regression vector. After its high-dimensional clustering and hyperplane estimation, the whole space is convexly partitioned into multiple polyhedral domains. In each domain, using the finite difference input vector and output, multi-step receding prediction of heat load is realized using the Bi-LSTM (Bidirectional Long-short Temporal Memory) neural network. To further quantify prediction uncertainty, the nonparametric CKDE (Conditional Kernel Density Estimation) method are adopted to evaluate prediction error, where confidence boundaries can be obtained as interval prediction models. Finally, a DHS in Northwest China is selected for verification. The results show that the proposed method can accurately predict short-term DHL under the proposed multi-model structure. It is meaningful to achieve the purposes of on-demand heating, energy saving and environmental protection.