Prediction of tide level based on variable weight combination of LightGBM and CNN-BiGRU model.

Accurate tide level prediction is crucial to human activities in coastal areas. Many practical applications show that compared with traditional harmonic analysis, long short-term memory (LSTM), gated recurrent units (GRUs) and other neural networks, along with ensemble learning models, such as light gradient boosting machine (LightGBM) and eXtreme gradient boosting (XGBoost), can achieve extremely high prediction accuracy in relatively stationary time series. Therefore, this paper proposes a variable weight combination model based on LightGBM and CNN-BiGRU with relevant research. It uses the variable weight combination method to weight and synthesize the prediction results of the two base models so that the combination model has a stronger ability to capture time series features and fits the data well. The experimental results show that in contrast to the base model LightGBM, the RMSE value and MAE value of the combination model are reduced by 43.2% and 44.7%, respectively; in contrast to the base model CNN-BiGRU, the RMSE value and MAE value of the combination model are reduced by 35.3% and 39.1%, respectively. This means that the variable weight combination model can greatly improve the accuracy of tide level prediction. In addition, we use tidal data from different geographical environments to further verify the good universality of the model. This study provides a new idea and method for tide prediction.

Prediction of air pollutant concentrations based on TCN-BiLSTM-DMAttention with STL decomposition.

A model with high accuracy and strong generalization performance is conducive to preventing serious pollution incidents and improving the decision-making ability of urban planning. This paper proposes a new neural network structure based on seasonal-trend decomposition using locally weighted scatterplot smoothing (Loess) (STL) and a dependency matrix attention mechanism (DMAttention) based on cosine similarity to predict the concentration of air pollutants. This method uses STL for series decomposition, temporal convolution, a bidirectional long short-term memory network (TCN-BiLSTM) for feature learning of the decomposed series, and DMAttention for interdependent moment feature emphasizing. In this paper, the long short-term memory network (LSTM) and the gated recurrent unit network (GRU) are set as the baseline models to design experiments. At the same time, to test the generalization performance of the model, short-term forecasts in hours were performed using PM2.5, PM10, SO2, NO2, CO, and O3 data. The experimental results show that the model proposed in this paper is superior to the comparison model in terms of root mean square error (RMSE) and mean absolute percentage error (MAPE). The MAPE values of the 6 kinds of pollutants are 6.800%, 10.492%, 9.900%, 6.299%, 4.178%, and 7.304%, respectively. Compared with the baseline LSTM and GRU models, the average reduction is 49.111% and 43.212%, respectively.

The impact of the digital economy on Chinese enterprise innovation based on intermediation models with financing constraints.

The digital economy has become an important driving force for the steady development of China's economy, and enterprise innovation is a key element for an enterprise's survival and development. This paper constructs a mathematical model to measure the scale of digital economic development and the efficiency of enterprise innovation. It builds a fixed effects model and mediated effects model to study the effect of the development of the digital economy on enterprise innovation based on data from 30 provinces from 2012 to 2020. The results show that (1) there is a significant positive effect of the digital economy on enterprise innovation with an impact coefficient of 0.028, and the economic meaning of the coefficient is that for every 1-point increase in the digital economy index, the ratio of R&D capital expenditures to the enterprise's operating income increases by 0.028% points. This finding remains significant in the robustness test. (2) A further test of the mediating effect finds that the digital economy can drive enterprise innovation by reducing financing constraints. (3) In the regional heterogeneity analysis, it is found that the effect of the digital economy in promoting enterprise innovation is more prominent in the central region, and the impact coefficients are 0.04, 0.06, 0.025, and 0.024 for the eastern, central, western, and northeastern regions, respectively. Taking the central region as an example, the economic meaning of the coefficient is that for every 1-point increase in the digital economy index, the ratio of R&D capital expenditures to the enterprise's operating income increases by 0.06% points. The findings of this paper are of practical significance to enterprises in enhancing their innovation capabilities and promoting the high-quality development of China's economy.

Prediction of air quality index based on the SSA-BiLSTM-LightGBM model.

The air quality index (AQI), as an indicator to describe the degree of air pollution and its impact on health, plays an important role in improving the quality of the atmospheric environment. Accurate prediction of the AQI can effectively serve people's lives, reduce pollution control costs and improve the quality of the environment. In this paper, we constructed a combined prediction model based on real hourly AQI data in Beijing. First, we used singular spectrum analysis (SSA) to decompose the AQI data into different sequences, such as trend, oscillation component and noise. Then, bidirectional long short-term memory (BiLSTM) was introduced to predict the decomposed AQI data, and a light gradient boosting machine (LightGBM) was used to integrate the predicted results. The experimental results show that the prediction effect of SSA-BiLSTM-LightGBM for the AQI data set is good on the test set. The root mean squared error (RMSE) reaches 0.6897, the mean absolute error (MAE) reaches 0.4718, the symmetric mean absolute percentage error (SMAPE) reaches 1.2712%, and the adjusted R2 reaches 0.9995.

Short-term power load forecasting based on the CEEMDAN-TCN-ESN model.

Ensuring an adequate electric power supply while minimizing redundant generation is the main objective of power load forecasting, as this is essential for the power system to operate efficiently. Therefore, accurate power load forecasting is of great significance to save social resources and promote economic development. In the current study, a hybrid CEEMDAN-TCN-ESN forecasting model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and higher-frequency and lower-frequency component reconstruction is proposed for short-term load forecasting research. In this paper, we select the historical national electricity load data of Panama as the research subject and make hourly forecasts of its electricity load data. The results show that the RMSE and MAE predicted by the CEEMDAN-TCN-ESN model on this dataset are 15.081 and 10.944, respectively, and R2 is 0.994. Compared to the second-best model (CEEMDAN-TCN), the RMSE is reduced by 9.52%, and the MAE is reduced by 17.39%. The hybrid model proposed in this paper effectively extracts the complex features of short-term power load data and successfully merges subseries according to certain similar features. It learns the complex and varying features of higher-frequency series and the obvious regularity of the lower-frequency-trend series well, which could be applicable to real-world short-term power load forecasting work.

Dynamic evaluation of low-carbon development in China's power industry and the impact of carbon market policies.

At the 75th session of the United Nations General Assembly, China clearly put forward the goals of "carbon peak" in 2030 and "carbon neutrality" in 2060. Achievement of carbon targets. Therefore, the goal of this paper is to analyze the low-carbon development level of China's power industry and study the impact of carbon market policies on the low-carbon development level of the power industry. Based on this, this paper first constructs the low-carbon development evaluation index system of the power industry around the connotation of low-carbon development in the power industry and uses the global principal component analysis model to measure the low-carbon development level of China's power industry. Then, the dynamic change trend and spatial distribution characteristics of the low-carbon development level of China's power industry are analyzed using kernel density estimation and the K-means clustering method. Finally, propensity score matching and difference-in-difference methods are used to analyze the impact of carbon market policies on the low-carbon development level of China's power industry. The results show that, first, the low-carbon development level of China's power industry generally shows an upward trend and a polarized development trend. Second, the low-carbon development level of China's power industry has regional effects and gradient effects. The low-carbon development level of the power industry from high to low is the eastern region, central region and western region. Third, carbon market policies can help improve the low-carbon development level of China's power industry. The research results provide some reference and guidance for the evaluation of the low-carbon development level of China's power industry and the improvement of carbon market policies.

Prediction of soil moisture using BiGRU-LSTM model with STL decomposition in Qinghai-Tibet Plateau.

Ali Network data based on the Qinghai-Tibetan Plateau (QTP) can provide representative coverage of the climate and surface hydrometeorological conditions in the cold and arid region of the QTP. Among them, the plateau soil moisture can effectively quantify the uncertainty of coarse resolution satellite and soil moisture models. With the objective of constructing an "end-to-end" soil moisture prediction model for the Tibetan Plateau, a combined prediction model based on time series decomposition and a deep neural network is proposed in this article. The model first performs data preprocessing and seasonal-trend decomposition using loess (STL) to obtain the trend component, seasonal component and random residual component of the original time series in an additive way. Subsequently, the bidirectional gated recurrent unit (BiGRU) is used for the trend component, and the long short-term memory (LSTM) is used for the seasonal and residual components to extract the time series information. The experiments based on the measured data demonstrate that the use of STL decomposition and the combination model can effectively extract the information in soil moisture series using its concise and clear structure. The proposed model in this article has a stable performance improvement of 5-30% over a single model and existing prediction models in different prediction time domains. In long-range prediction, the proposed model also achieves the best accuracy in the shape and temporal domains described by using dynamic time warping (DTW) index and temporal distortion index (TDI). In addition, the generalization performance experiments show that the combined method proposed in this article has strong reference value for time series prediction of natural complex systems.

Prediction of sea ice area based on the CEEMDAN-SO-BiLSTM model.

This article proposes a combined prediction model based on a bidirectional long short-term memory (BiLSTM) neural network optimized by the snake optimizer (SO) under complete ensemble empirical mode decomposition with adaptive noise. First, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) was used to decompose the sea ice area time series data into a series of eigenmodes and perform noise reduction to enhance the stationarity and smoothness of the time series. Second, this article used a bidirectional long short-term memory neural network optimized by the snake optimizer to fully exploit the characteristics of each eigenmode of the time series to achieve the prediction of each. Finally, the predicted values of each mode are superimposed and reconstructed as the final prediction values. Our model achieves a good score of RMSE: 1.047, MAE: 0.815, and SMAPE: 3.938 on the test set.

Electricity price forecast based on the STL-TCN-NBEATS model.

Taking long-term high-frequency electricity price data as the research content, this paper proposes seasonal and trend decomposition using loess-temporal convolutional network-neural basis expansion analysis for an interpretable time series forecasting (STL-TCN-NBEATS) model to solve the problems of low forecast accuracy caused by high volatility, high frequency and nonlinearity and poor interpretability of the deep learning model. By comparing the forecast effects of the temporal convolutional network-long short-term memory (TCN-LSTM), LSTM and other models, the main conclusions are as follows: (1) The hybrid model, STL-TCN-NBEATS, selected in this paper can effectively solve the problem of low forecast accuracy after reasonable selection of model parameters. The evaluation indexes of the root mean square error (RMSE) and the mean absolute percentage error (MAPE) were 3.7441 and 4.5044, respectively, which were 3.1416 and 2.1336 lower than those of the second-best model (TCN-LSTM). Compared with the autoregressive integrated moving average model (ARIMA), the accuracy was improved by approximately 49.18% (RMSE) and 60.35% (MAPE). (2) The STL-TCN-NBEATS model has better feature extraction ability, so it can obtain higher forecast accuracy. Since the construction of the TCN introduces extended causal convolution and residual blocks, the deep learning network model has better processing ability and robustness for large sample time series. Moreover, the NBEATS network structure enables the model to be trained quickly, and the experimental results verify the effectiveness and high accuracy of this method. (3) The model not only has high precision but also has some interpretability. By decomposing time series data into a trend term, period term and remainder term, the NBEATS and the TCN are used to process the trend term, period term and remainder term, respectively, so that the hybrid model can forecast electricity prices according to the traditional time series processing mode.

Prediction of PM2.5 concentration based on the CEEMDAN-RLMD-BiLSTM-LEC model.

Air quality has emerged as a critical concern in recent years, with the concentration of PM2.5 recognized as a vital index for assessing it. The accuracy of predicting PM2.5 concentrations holds significant value for effective air quality monitoring and management. In response to this, a combined model comprising CEEMDAN-RLMD-BiLSTM-LEC has been introduced, analyzed, and compared against various other models. The combined decomposition method effectively underlines the fundamental characteristics of the data compared to individual decomposition techniques. Additionally, local error correction (LEC) efficiently addresses the issue of prediction errors induced by excessive disturbances. The empirical results of nine steps indicate that the combined CEEMDAN-RLMD-BiLSTM-LEC model outperforms single prediction models such as RLMD and CEEMDAN, reducing MAE, RMSE, and SAMPE by 36.16%, 28.63%, 45.27% and 16.31%, 6.15%, 37.76%, respectively. Moreover, the inclusion of LEC in the model further diminishes MAE, RMSE, and SMAPE by 20.69%, 7.15%, and 44.65%, respectively, exhibiting commendable performance in generalization experiments. These findings demonstrate that the combined CEEMDAN-RLMD-BiLSTM-LEC model offers high predictive accuracy and robustness, effectively handling noisy data predictions and severe local variations. With its wide applicability, this model emerges as a potent tool for addressing various related challenges in the field.

Classification and prediction of spinal disease based on the SMOTE-RFE-XGBoost model.

Spinal diseases are killers that cause long-term disturbance to people with complex and diverse symptoms and may cause other conditions. At present, the diagnosis and treatment of the main diseases mainly depend on the professional level and clinical experience of doctors, which is a breakthrough problem in the field of medicine. This article proposes the SMOTE-RFE-XGBoost model, which takes the physical angle of human bone as the research index for feature selection and classification model construction to predict spinal diseases. The research process is as follows: two groups of people with normal and abnormal spine conditions are taken as the research objects of this article, and the synthetic minority oversampling technique (SMOTE) algorithm is used to address category imbalance. Three methods, least absolute shrinkage and selection operator (LASSO), tree-based feature selection, and recursive feature elimination (RFE), are used for feature selection. Logistic regression (LR), support vector machine (SVM), parsimonious Bayes, decision tree (DT), random forest (RF), gradient boosting tree (GBT), extreme gradient boosting (XGBoost), and ridge regression models are used to classify the samples, construct single classification models and combine classification models and rank the feature importance. According to the accuracy and mean square error (MSE) values, the SMOTE-RFE-XGBoost combined model has the best classification, with accuracy, MSE and F1 values of 97.56%, 0.1111 and 0.8696, respectively. The importance of four indicators, lumbar slippage, cervical tilt, pelvic radius and pelvic tilt, was higher.

Energy consumption prediction using the GRU-MMattention-LightGBM model with features of Prophet decomposition.

The prediction of energy consumption is of great significance to the stability of the regional energy supply. In previous research on energy consumption forecasting, researchers have constantly proposed improved neural network prediction models or improved machine learning models to predict time series data. Combining the well-performing machine learning model and neural network model in energy consumption prediction, we propose a hybrid model architecture of GRU-MMattention-LightGBM with feature selection based on Prophet decomposition. During the prediction process, first, the prophet features are extracted from the original time series. We select the best LightGBM model in the training set and save the best parameters. Then, the Prophet feature is input to GRU-MMattention for training. Finally, MLP is used to learn the final prediction weight between LightGBM and GRU-MMattention. After the prediction weights are learned, the final prediction result is determined. The innovation of this paper lies in that we propose a structure to learn the internal correlation between features based on Prophet feature extraction combined with the gating and attention mechanism. The structure also has the characteristics of a strong anti-noise ability of the LightGBM method, which can reduce the impact of the energy consumption mutation point on the overall prediction effect of the model. In addition, we propose a simple method to select the hyperparameters of the time window length using ACF and PACF diagrams. The MAPE of the GRU-MMattention-LightGBM model is 1.69%, and the relative error is 8.66% less than that of the GRU structure and 2.02% less than that of the LightGBM prediction. Compared with a single method, the prediction accuracy and stability of this hybrid architecture are significantly improved.

Feature selection for global tropospheric ozone prediction based on the BO-XGBoost-RFE algorithm.

Ozone is one of the most important air pollutants, with significant impacts on human health, regional air quality and ecosystems. In this study, we use geographic information and environmental information of the monitoring site of 5577 regions in the world from 2010 to 2014 as feature input to predict the long-term average ozone concentration of the site. A Bayesian optimization-based XGBoost-RFE feature selection model BO-XGBoost-RFE is proposed, and a variety of machine learning algorithms are used to predict ozone concentration based on the optimal feature subset. Since the selection of the underlying model hyperparameters is involved in the recursive feature selection process, different hyperparameter combinations will lead to differences in the feature subsets selected by the model, so that the feature subsets obtained by the model may not be optimal solutions. We combine the Bayesian optimization algorithm to adjust the parameters of recursive feature elimination based on XGBoost to obtain the optimal parameter combination and the optimal feature subset under the parameter combination. Experiments on long-term ozone concentration prediction on a global scale show that the prediction accuracy of the model after Bayesian optimized XGBoost-RFE feature selection is higher than that based on all features and on feature selection with Pearson correlation. Among the four prediction models, random forest obtained the highest prediction accuracy. The XGBoost prediction model achieved the greatest improvement in accuracy.

Forecast and analysis of aircraft passenger satisfaction based on RF-RFE-LR model.

Airplanes have always been one of the first choices for people to travel because of their convenience and safety. However, due to the outbreak of the new coronavirus epidemic in 2020, the civil aviation industry of various countries in the world has encountered severe challenges. Predicting aircraft passenger satisfaction and excavating the main influencing factors can help airlines improve their services and gain advantages in difficult situations and competition. This paper proposes a RF-RFE-Logistic feature selection model to extract the influencing factors of passenger satisfaction. First, preliminary feature selection is performed using recursive feature elimination based on random forest (RF-RFE). Second, based on different classification models, KNN, logistic regression, random forest, Gaussian Naive Bayes, and BP neural network, the classification performance of the models before and after feature selection is compared, and the prediction model with the best classification performance is selected. Finally, based on the RF-RFE feature selection, combined with the logistic model, the factors affecting customer satisfaction are further extracted. The experimental results show that the RF-RFE model selects a feature subset containing 17 variables. In the classification prediction model, the random forest after RF-RFE feature selection shows the best classification performance. Finally, combined with the four important variables extracted by RF-RFE and logistic regression, further discussion is carried out, and suggestions are given for airlines to improve passenger satisfaction.

Spatiotemporal prediction of O3 concentration based on the KNN-Prophet-LSTM model.

In this paper, a prediction method based on the KNN-Prophet-LSTM hybrid model is established by using the daily pollutant concentration data of Wuhan from January 1, 2014, to May 3, 2021, and considering the characteristics of time and space. First, the data are divided into trend items, periodic items and error items by the Prophet decomposition method. Considering the advantages of the Prophet and the Long Short-Term Memory (LSTM) models, the trend items and periodic items are predicted by the Prophet model. The LSTM model is used to predict the error terms, and the K-Nearest Neighbor algorithm (KNN) is added to fuse the spatial and temporal information to predict the ozone (O3) concentration value day by day. To highlight the effectiveness and rationality of the KNN-Prophet-LSTM hybrid model, four groups of comparative experiments are set up to compare it with the single model Autoregressive Integrated Moving Average (ARIMA), Prophet, LSTM and the hybrid model Prophet-LSTM. The experimental results show that, (1) the daily maximum 8-hour average concentration of O3 in Wuhan has a significant periodic variation. The difference in the surrounding environment will lead to the difference in O3 concentration change in the region, and the O3 concentration change of similar stations will have a high similarity. (2) The Prophet decomposition algorithm decomposes the original time series, which can effectively extract the time series information and remove noise. Thus, the prediction accuracy is obviously improved. (3) Considering the spatial information of the surrounding sites by KNN algorithm, the accuracy of the model can be further improved. Compared with the baseline model ARIMA, the accuracy is improved by approximately 49.76% on mean absolute error (MAE) and 46.81% on root mean square error (RMSE) respectively. (4) The prediction effect of the mixed model is generally better than that of the single model and possesses a higher prediction accuracy.

Research on sentiment classification for netizens based on the BERT-BiLSTM-TextCNN model.

Sentiment analysis of netizens' comments can accurately grasp the psychology of netizens and reduce the risks brought by online public opinion. However, there is currently no effective method to solve the problems of short text, open word range, and sometimes reversed word order in comments. To better solve the above problems, this article proposes a hybrid model of sentiment classification, which is based on bidirectional encoder representations from transformers (BERT), bidirectional long short-term memory (BiLSTM) and a text convolution neural network (TextCNN) (BERT-BiLSTM-TextCNN). The experimental results show that (1) the hybrid model proposed in this article can better combine the advantages of BiLSTM and TextCNN; it not only captures local correlation while retaining context information but also has high accuracy and stability. (2) The BERT-BiLSTM-TextCNN model can extract important emotional information more flexibly in text and achieve multiclass classification tasks of emotions more accurately. The innovations of this study are as follows: (1) the use of BERT to generate word vectors has the advantages of more prior information and a full combination of contextual semantics; (2) the BiLSTM model, as a bidirectional context mechanism model, can obtain contextual information well; and (3) the TextCNN model can obtain important features well in the problem of text classification, and the combined effect of the three modules can significantly improve the accuracy of emotional multilabel classification.