Search

• An improved singular spectrum decomposition is proposed. • High complexity components are secondarily decomposed to reduce its complexity. • An improved prediction model of optimization algorithm is proposed. • Intelligent weighting strategy is introduced to overcome traditional weighting problem. • A combined prediction model for carbon emission is proposed. Accurate prediction of carbon emission is critical for the development of low-carbon economy. However, most carbon emission prediction studies use a single model with low prediction accuracy, and do not consider the instability of carbon emission. Therefore, this paper proposes a combined prediction model of carbon emission. Firstly, the original data is decomposed by singular spectrum decomposition to obtain a limited amount of singular spectrum components. Secondly, high complexity components are secondarily decomposed by variational mode decomposition. Then, chameleon swarm algorithm and carnivorous plant algorithm are used to train the regularization coefficients and kernel parameters of kernel extreme learning machine and least squares support vector machine respectively, and the trained model is used to predict the decomposition components. Finally, induced ordered weighted averaging operator is used to calculate the weight of single model, and error correction is introduced to further promote the prediction accuracy. The carbon emission data of China and the United States is used to make a prediction experiment. The results indicate that the proposed model is superior to other comparative models in different indexes, which provides a new idea for carbon emission prediction. [ABSTRACT FROM AUTHOR]

The factors influencing precipitation in western China are quite complex, which increases the difficulty in determining accurate predictors. Hence, this paper models the monthly measured precipitation data from 240 meteorological stations in mainland China and the precipitation data from the European Centre for Medium-Range Weather Forecasts and the National Climate Centre and employs 88 atmospheric circulation indices to develop a precipitation prediction scheme. Specifically, a high-quality grid-point field is created by fusing and revising the precipitation data from multiple sources. This field is combined with the Empirical Orthogonal Function decomposition and the causal information flow. Next, the best predictors are screened through Empirical Orthogonal Function decomposition and causal information flow, and a data-driven precipitation prediction model is established using a Back Propagation Neural Network and a Random Forest algorithm to conduct the 1-month, 3-month, and 6-month precipitation predictions. The results show that: The machine learning-based precipitation prediction model has high accuracy and is generally able to predict the precipitation trend in the western region better. The Random Forest algorithm significantly outperforms the Back Propagation Neural Network algorithm in the prediction of the three starting times, and the prediction ability of both models gradually decreases as the starting time increases. Compared with the 2022 flood season prediction scores of the Institute of Atmospheric Sciences of the Chinese Academy of Sciences, the model improves the prediction of 1-month and 3-month precipitation in the western region and provides a new idea for the short-term climate prediction of precipitation in western China. [ABSTRACT FROM AUTHOR]

In this paper, we propose a general model for the soybean export market share dynamics and provide several theoretical analyses related to a special case of the general model. We implement machine and neural network algorithms to train, analyze, and predict US Gulf soybean market shares (target variable) to China using weekly time series data consisting of several features between January 6, 2012 and January 3, 2020. Overall, the results indicate that US Gulf soybean market shares to China are volatile and can be effectively explained (predicted) using a set of logical input variables. Some of the variables, including shipments due at US Gulf port in 10 days, cost of transporting soybean shipments via barge at Mid‐Mississippi, and soybean exports loaded at US Gulf port in the past 7 days, and binary variables have shown significant influence in predicting soybean market shares. [ABSTRACT FROM AUTHOR]

There are many thyroid diseases affecting people all over the world. Many diseases affect the thyroid gland, like hypothyroidism, hyperthyroidism, and thyroid cancer. Thyroid inefficiency can cause severe symptoms in patients. Effective classification and machine learning play a significant role in the timely detection of thyroid diseases. This timely classification will indeed affect the timely treatment of the patients. Automatic and precise thyroid nodule detection in ultrasound pictures is critical for reducing effort and radiologists' mistake rate. Medical images have evolved into one of the most valuable and consistent data sources for machine learning generation. In this paper, various machine learning algorithms like decision tree, random forest algorithm, KNN, and artificial neural networks on the dataset create a comparative analysis to better predict the disease based on parameters established from the dataset. Also, the dataset has been manipulated for accurate prediction for the classification. The classification was performed on both the sampled and unsampled datasets for better comparison of the dataset. After dataset manipulation, we obtained the highest accuracy for the random forest algorithm, equal to 94.8% accuracy and 91% specificity. [ABSTRACT FROM AUTHOR]

Due to the presence of asphaltene, the flow assurance of high viscosity crude oil becomes more challenging and costly to produce in wellbores and pipelines. One of the most effective ways to reduce viscosity is to blend heavy oil with light oil. However, the viscosity measurement of diluted heavy crude is either time-consuming or inaccurate. This work aims to develop a more accurate viscosity model of diluted heavy crude based on machine learning techniques. A multilayer neural network is used to predict the viscosity of heavy oil diluted with lighter oil. The input data used in the training include temperature, light oil viscosity, heavy oil viscosity, and dilution ratio. In this modeling process, 156 datasets were retrieved from the available iterature of various heavy-oil fields in China. Part of the data (80%) is used to train the developed models using Adam optimizer algorithms, while the other part of the data (20%) is used to predict the viscosity of heavy oil diluted with lighter. The performance and accuracy of the machine learning models were tested and compared with the existing viscosity models. It was found that the new model can predict the viscosity of diluted heavy oil with higher accuracy, and it performs better than other models. The absolute average relative error is 10.44%, the standard deviation of the relative error is 8.45%, and the coefficient of determination is R2 = 0.95. The viscosity predicted by the neural network outperformed existing correlations by the statistical analysis used for the datasets available in the literature. Therefore, the method proposed in this paper can better estimate the viscosity of diluted heavy crude oil and has important promotion value. [ABSTRACT FROM AUTHOR]

Accurate prediction of the rate of penetration (ROP) is a difficult issue in the drilling process, especially under complex formation conditions. Many methods, such as mechanism and machine learning, were introduced to investigate it. However, most of them are offline prediction methods which may not be capable of capturing the online trend of ROP. In this paper, a novel dynamic model for ROP prediction is proposed considering the process characteristics, which consists of three stages. In the first stage, the correlations between ROP and eight drilling parameters are analyzed, and the rotational speed, weight on bit, depth are selected as the model inputs. In the second stage, the drilling data are pre-processed by using the filtering and re-sampling techniques. In the last stage, the moving window strategy, extreme learning machine, and 10-fold cross validation are used to establish the ROP model. Our main idea of online prediction of ROP lies in this last stage. Specifically, two steps (modeling and prediction) are executed alternately in the moving drilling depth windows so as to predict the ROP more accurately. Finally, the proposed ROP prediction model is applied to the drilling well ZK3 in Xiangyang area, Central China. The prediction accuracy is improved by at least 7% compared with seven well-known ROP prediction methods, two online and five offline, which validates the effectiveness of the proposed method. It is believed that the proposed model provides a basis for intelligent optimization control in drilling process. • A novel intelligent dynamic model is proposed for the online prediction of drilling ROP. • The influence of the length of moving window and distance between two windows are investigated thoroughly. • The proposed model can learn autonomously in the drilling process and has a fast computation speed. • The proposed method has a higher prediction accuracy than two online and five offline well-known conventional methods. [ABSTRACT FROM AUTHOR]

The outbreak of Coronavirus 2019 (COVID‐19) has impacted everyday lives globally. The number of positive cases is growing and India is now one of the most affected countries. This paper builds predictive models that can predict the number of positive cases with higher accuracy. Regression‐based, Decision tree‐based, and Random forest‐based models have been built on the data from China and are validated on India's sample. The model is found to be effective and will be able to predict the positive number of cases in the future with minimal error. The developed machine learning model can work in real‐time and can effectively predict the number of positive cases. Key measures and suggestions have been put forward considering the effect of lockdown. [ABSTRACT FROM AUTHOR]

Influent quality and quantity were important factors that caused the abnormal operation of WWTP. In this study, the prediction models of influent quality and quantity were established based on four machine learning methods of Linear Regression, Ridge Regression, ElasticNet Regression and Lasso Regression. The meteorological conditions (precipitation and air temperature) and influent indicators (influent quantity, COD, and NH3-N) were used as training data. The influent quantity prediction of the models were evaluated using the historical data obtained from a WWTP located in western China, and the results showed that the normal rates of influent quantity were ranged from 98.9%-100%. The highest accuracy was obtained with Ridge method which was 86.19%. For influent quality (COD) prediction, Ridge method is relatively ideal, with 82% accuracy. For influent quality (NH3-N) prediction, because of higher data normality rates, Lasso and ElasticNet method were more ideal, both with 74% accuracy. Further, in view of the reason of low prediction accuracy, this paper puts forward the idea of model improvement from the three directions of data fluctuation, correlation and amount. It is expected that this study will provide reference for similar research and provide a reference and thought for similar research. [ABSTRACT FROM AUTHOR]

With the development of quality of life, people pay more and more attention to the surrounding environmental factors, especially air pollution. The problem of air pollution in China is becoming more and more serious, which poses a great threat to people's health. Therefore, the prediction of air quality concentration is very important. PM2.5 is the primary indicator for evaluating the concentration of smog. Currently, studies have been proposed to predict the concentration of PM2.5. Before, most methods use traditional machine learning or real-time monitoring to predict pollution of PM2.5 value. However, the previous prediction methods cannot meet the requirement of the accuracy. For this end, this paper uses Convnet and Dense-based Bidirectional Gated Recurrent Unit to predict PM2.5 value which combined Convnet, Dense and Bi-GRU. The feature in air quality data was extracted from convnets without max-pooling instead another convolutional layer and Bi-GRU with additional Dense could provide a more accuracy result. Experiments show that the effectiveness of our method PM2.5 mass concentration prediction model provides a more superior method for PM2.5 mass concentration prediction. [ABSTRACT FROM AUTHOR]

• Adasyn and t-SNE are used to pre-process the collected rockburst data. • SVM, BP, RBF, RF and ELM optimized by global optimization algorithm are used to predict rockburst intensity. • An improved D-S evidence theory rockburst prediction fusion model based on multiple machine learning algorithms is raised. • The fusion model predicts much better than single algorithm model in engineering application. Accurate prediction of rockburst hazards is an effective means to improve the development and utilization of underground space. When using a single machine learning algorithm for rockburst prediction, the reliability of the classification results can hardly be guaranteed. In this paper, a fusion model for rockburst prediction based on multiple machine learning algorithms is proposed in combination with D-S evidence theory. Six characteristic parameters (σ θ , σ c , σ t , SR , BR and Wet) were statistically analyzed for 304 sets of rockburst cases, and the data had outliers and class imbalances. The box plot method was used to detect replacement of a small number of outliers, and the Adasyn oversampling method eliminated the effect of data class imbalance. The visualization of the data by using the t-SNE method showed improved classifiability. SVM, BP, RBF, RF and ELM rockburst prediction models were developed with the six characteristic parameters as model inputs. In addition, the global optimization algorithms were used to find the optimal hyperparameters of the five machine learning algorithms. The accuracy of the optimized models was improved by 2.63%, 5.27%, 2.63%, 6.58% and 7.5% compared to the unoptimized models. Based on the prediction results, the precision was proposed as the fusion index. Additionally, based on improved D-S evidence theory, a fusion model for rockburst prediction was developed with five optimized machine learning algorithm models as base classifiers. Finally, the fusion model was applied to the rockburst prediction of Jiangbian Hydropower Station and Sanshan Island Gold Mine in China with the accuracy of 92.86%, and the prediction was outperformed by a single base classifier. The fusion model compensated for the uncertainty and poor robustness of the prediction results of the single-base classifier, and improved the accuracy and reliability of rockburst prediction. [ABSTRACT FROM AUTHOR]

With photovoltaic (PV) penetration increasing, PV-output prediction has become a research hotspot. Due to the close correlation between PV-output fluctuation and weather conditions, PV-output prediction models often vary different weather types, while the historical/forecast weather types for modeling are mostly obtained from weather-service providers. However, weather-service providers generally have deficiencies in forecast accuracy, spatio-temporal resolution, and investment/operating costs. Based on the above, this paper changes the current acquisition way of the weather types, and proposes a framework of reversely determining weather types from historical PV-output data. First, the symbol-sequence histograms (SSH) are used to describe the PV-output volatility in a coarse-grained manner. Then, the SSHs are partitionally clustered and a classification rule for weather-types is proposed to label the historical weather types. Next, considering the chaotic characteristics of PV output, a prediction method combining phase-space reconstruction with an extremely learning machine based single-layer forward net is developed to predict the SSH. Finally, the day-ahead weather type is forecasted. Simulations were implemented on the weather-type classification and forecasting using a campus PV-system in East China. The PV-output prediction results show that, compared with weather information from a weather-service supplier, 75-day mean errors are significantly reduced by 15.55% (MAPE) and 12.69% (rRMSE), respectively. • A framework to reversely label weather type according to historical PV-output data. • The volatility of PV-output is quantified based on a coarse-grained manner. • A weather-type classification rule is proposed based on symbol histogram clustering. • Symbol-sequence histogram is forecasted using a phase-space reconstruction-ELM model. • The effect of the method is evaluated through the accuracy of PV-output prediction. [ABSTRACT FROM AUTHOR]

Global climate change has led to large fluctuations in lake levels in recent years as meteorological and hydrological parameters have changed and water use has been intense. Water scientists use various computer models to analyze the hydrological variables recorded in the past and make projections for all future scenarios. Based on the technological progress, six different types of algorithms were studied in this review to predict the water level in lakes. The prediction results show that Deep Learning (DL) has the highest accuracy in terms of the evaluation metrics. Since the Artificial Intelligence (AI) field is still emerging and continue to improve, this study highlights better comprehension of current applications and the problems that need to be investigated more for LWL forecasting techniques. It reveals that the studies mainly focused on lakes either in USA or China and there is room for improvement for other locations that are scarcely investigated. • This paper presents a systematic literature review for lake and reservoir water level studies for the first time. • Researchers favored input parameters as lake water level, precipitation and temperature among others. • The studies can be extended towards the direction of least studied areas such as deep learning based algorithms. • Increasing water level prediction areas recently indicates it became a hot topic because of visible climate change effects. [ABSTRACT FROM AUTHOR]

The short-term photovoltaic (PV) power prediction is mainly used to prevent photovoltaic power generation fluctuations, grid overvoltage, reverse current, and islanding effects. At the same time, the mid-term PV power forecast is of great significance to improving the availability of PV power generation and the benefit of PV grid connection. Because of the significant differences in time scales between mid-term and short-term power prediction, the short-term power prediction model or method cannot be directly applied to mid-term power prediction. Therefore, few scholars have developed effective short-to-mid-term power forecasting strategies for photovoltaics. As a result, this research proposes a prediction model based on a fast cull outlier algorithm (FC), a decision tree (DT), least squares support vector regression (LSSVR), and an improved whale bat optimization algorithm (IWBOA), which is used for the prediction of the short-to-mid-term photovoltaic power on different time scales, one day and one month in advance. The FC algorithm is used to analyze the difference between the overall data and the abnormal data in the local density and distance to remove the outliers in the original data set. The revised DT model differentiates the data according to climate characteristics to obtain different input data subsets with the best correlation and constructs an independent LSSVR-based model corresponding to the data subsets. The WOA algorithm is improved by independently designing the Chebyshev chaotic initialization strategy, chaotic adaptive inertia weight and BOA algorithm, and the kernel function width and penalty factor of each short-to-mid-term independent sub-PV power prediction model are optimized by IWBOA, thereby improving the computational speed and prediction accuracy of the LSSVR model. Finally, the effectiveness of the proposed strategy is evaluated using actual data from photovoltaic power plants in China. The regression coefficient (R2), mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) of short-term forecasting ability of the FCDT-IWBOA-LSSVR model established in this paper are 0.99657, 0.22009, 0.32515, and 0.20959, respectively, while the R2, MSE, RMSE, and MAE of medium-term forecasting ability are 0.98374, 1.91371, 1.38336, and 0.6256. The calculation results show that the prediction accuracy of the FCDT-IWBOA-LSSVR model is higher than that of the WOA-LSSVR, PSO-LSSVR, PSO-BP, I-ACO-SVR, ANN, EMS-DSM-RT, 5 ML, and ELM models. • Short-to-mid-term photovoltaic power generation prediction model established. • The FC algorithm analyze local density and distance for data and remove outliers. • The DT model differentiates the data according to climate characteristics. • The IWBOA was used to optimize the parameters of the LSSVR prediction model. [ABSTRACT FROM AUTHOR]

• Construct a light model library, train different light model for each market distribution. • Devise a novel reward function based on inverse reinforcement learning, and estimate the profits of each order. • Devise an algorithm for dynamically selecting model based on reinforcement learning. • Promising performance on real-world high-frequency trading in China Commodity Future market. In this paper, we propose an online model optimization algorithm based on reinforcement learning for quantitative trading. The combination of prediction model and trading policy is the most commonly used framework in practical quantitative trading. Integrated with machine learning methods, this framework brings huge profits to quantified companies. In the framework, the prediction model is used to predict future trading price trend, and the trading policy is used to determine the price and number of orders. Even though, the shortcomings of machine learning models are obvious, mainly are, (1) Slow prediction speed. Huge human-craft features and model computing cost much time, which is ten times of pure trading policy without model. (2) Poor generalization. This kind of models can hardly adapt to market data in each period, because market traders will change time to time at micro level, thus the distribution of market data will change. But current model is trained on a long period dataset, it achieves best effect at average, but can not adapt to different market at each period. To address this problem, we propose a novel online model optimization algorithm. A light model library will be constructed. Each light model in this library corresponds to a different market distribution. By devising the appropriate reward function via inverse reinforcement learning algorithm, the algorithm can accurately estimate the profits of each model. Then the model can be selected automatically in real-time trading, so that the trading policies can automatically adapt to changes in trading market, overcoming previous shortcoming of manually updating model and slow prediction speed. Experimental results show that the proposed algorithm achieves state-of-the-art performance on China Commodity Futures Market Data. [ABSTRACT FROM AUTHOR]

In order to implement the national need for the optimal allocation of power resources, power load forecasting, as an important research topic, has important theoretical and practical significance. The purpose of this study is to construct a prediction model considering climate factors based on a large amount of historical data, and to prove that the prediction accuracy is related to both climate factors and load regularity. The results of load forecasting are affected by many climate factors, so firstly the climate variables affecting load forecasting are screened. Secondly, a load prediction model based on the IPSO-Elman network learning algorithm is constructed by taking the difference between the predicted value of the neural network and the actual value as the fitness function of particle swarm optimization. In view of the great influence of weights and thresholds on the prediction accuracy of the Elman neural network, the particle swarm optimization algorithm (PSO) is used to optimize parameters in order to improve the prediction accuracy of ELMAN neural network. Thirdly, prediction with and without climate factors is compared and analyzed, and the prediction accuracy of the model compared by using cosine distance and various error indicators. Finally, the stability discriminant index of historical load regularity is introduced to prove that the accuracy of the prediction model is related to the regularity of historical load in the forecast area. The prediction method proposed in this paper can provide reference for power system scheduling. [ABSTRACT FROM AUTHOR]