Unveiling high-dimensional time-varying extreme risk spillovers: AI-driven warning signals in the global energy market

Drought prediction is crucial for mitigating risks and designing measures to alleviate its impact. Machine learning models have been widely applied in the field of drought prediction in recent years. This study concentrated on predicting meteorological droughts in southwest China, a region prone to frequent and severe droughts, particularly in areas with sparse meteorological station coverage. The long short-term memory (LSTM) predictive model, which is a deep learning model, was constructed by calculating standardized precipitation evapotranspiration index (SPEI) values based on 144 weather station observations from 1980 to 2020. The 5-fold cross-validation method was used for the hyperparameter optimization of the model. The LSTM model underwent comprehensive assessment and validation through multiple methods. This included the use of several accuracy assessment indicators and a comparison of results. The comparison covered different drought characteristics among the LSTM predictive model, the benchmark random forest (RF) predictive model, the historical drought situations, and the calculated SPEI values based on observations from 144 weather stations. The results showed that the training results of the LSTM predictive model basically agreed with the SPEI values calculated from weather station observations. The model-predicted variation trend of SPEI values for 2020 was similar to the variation in SPEI values calculated based on weather station observations. On the test set, the coefficient of determination (R 2), the root mean square error, the explained variance score, the Nash–Sutcliffe efficiency, and the Kling–Gupta efficiency were 0.757, 0.210, 0.802, 0.761, and 0.212, respectively. The total consistency rate of the drought grade was 59.26%. The spatial correlation distribution of SPEI values between LSTM model prediction and calculation from meteorological stations in 2020 was more than 0.5 for most regions. The correlation coefficients exceeded 0.6 in western Tibet and Chengdu Plains. Compared to the RF model, the LSTM model excelled in all five performance evaluation metrics and demonstrated a higher overall consistency rate for drought categories. The Kruskal–Wallis test for both the LSTM and RF models all indicated no significant difference in the distributions between the predicted and observed data. Scatter plots revealed that the prediction accuracy for both models in 2020 was suboptimal, with the SPEI showing a comparatively narrow range of values. Nonetheless, the LSTM model significantly outperformed the RF model in terms of prediction accuracy. In summary, the LSTM model demonstrated good overall performance, accuracy, and applicability. It has the potential to enhance dynamic drought prediction in regions with complex terrain, diverse climatic factors, and sparse weather station networks.

A data-driven strategy using long short term memory models and reinforcement learning to predict building electricity consumption

Evaluation of data preprocessing and feature selection process for prediction of hourly PM10 concentration using long short-term memory models

Traditional Long Short Term Memory (LSTM) model can effectively improve the price prediction problem, but the LSTM model only accepts a single element input, and the power equipment price prediction involves multiple factors. Based on this, this paper proposes a multi-factor input-based LSTM model for transformer purchase price prediction, firstly, by changing the mapping structure of input layer, loop layer and output layer in the LSTM model, and then reasonably introducing the loop dropout restriction mechanism to ensure that the model structure is efficiently adapted to multi-factor input and low data training time. Finally, experimental simulations are conducted on a real price data set, and the validation results show that this algorithm can efficiently improve the price prediction accuracy and model robustness compared with traditional models.

Optimizing WAG processes is crucial for maximizing oil recovery and carbon sequestration efficiency in CO2 Enhanced Oil Recovery (EOR) projects. This study presents a comparative evaluation of two deep learning models, Temporal Fusion Transformer (TFT) and Long Short-Term Memory (LSTM), for multivariate forecasting of oil production, CO2 sequestration efficiency, utilization, and retention in WAG scenarios. A comprehensive dataset of digitized monthly production and injection data from six U.S. fields was used to train and validate both models. The results show that the LSTM model outperforms the TFT model in terms of accuracy and reduced errors, with improved predictive capabilities for oil production and CO2 sequestration efficiency. The LSTM model achieved high predictive accuracy, with R2 values reaching 0.99 and robust mean absolute error (MAE) and root mean squared error (RMSE) factors. In contrast, the TFT model achieved R2 values of 0.87 and higher MAE and RMSE factors. Head-to-head accuracy favors the LSTM model, as it achieves higher fit quality and lower errors in the majority of comparisons for both EOR oil and CO2. The size of the margin varies by case, but the direction of the difference is consistent. This outcome, though unexpected due to the advanced nature of TFT, aligns with the learning conditions in this study, where the forecast horizon is short, the historical time series per field are modest in length, and the covariate set is compact. Under such conditions, a compact recurrent architecture like LSTM tends to generalize efficiently and resist variance from operational noise, while a higher-capacity transformer like TFT is more sensitive to data volume and hyperparameters such as encoder length, attention size, learning rate, and dropout. Additionally, LSTM converges more stably with modest tuning, enabling it to reach strong solutions within the available data and horizon. The forecasts generated by the LSTM model enabled actionable short-term operational recommendations, such as adjusting the WAG ratio to optimize CO2 retention and utilization efficiency. For example, adjusting the WAG ratio from 0.9 to 1.9 in the Denver Unit increased CO2 retention by 168% and utilization efficiency by 50%. These optimizations support enhanced carbon abatement by reducing CO2 recycling and improving sequestration permanence. This study demonstrates the potential of deep learning models, particularly LSTM, to optimize WAG processes and improve the efficiency of CO2 EOR operations. The approach offers a scalable, data-driven alternative to simulation workflows, aligning EOR operations with climate and sustainability targets. To the best of our knowledge, this is the first comparative study of LSTM and TFT models for real-field CO2 EOR forecasting and WAG strategy optimization.

Traffic safety has been thought of as a basic feature of transportation, recent developments in civil aviation have emphasized the need for risk identification and safety prediction. This study aims to increase en-route flight safety through the development of prediction models for flight conflicts. Firstly, flight conflicts time series and traffic parameters are extracted from historical ADS-B data. In the second step, a Long Short-Term Memory (LSTM) model is trained to make a one-step-ahead prediction on the flight conflict time series. The results show that the LSTM model has the greatest prediction effect (MAE 0.3901) with comparison to other models. Based on that, we add traffic parameters (volume, density, velocity) into the LSTM model as new input variables and issue a comprehensive analysis of the relative predictive power of traffic parameters. The accuracy of prediction model is validated with a mean error of less than 3%. Based on the improvements of model performance brought by traffic parameters, LSTM models with a single traffic parameter are proposed for further discussion. The results illustrate that volume is the most important factor in promoting prediction accuracy and density has an advantage of improvement in the aspect of model stability.

Abstract. The information available on the internet nowadays is diverse and moves very quickly. Information is becoming easier to obtain by the general public with the numerous online media outlets, including news portals that provide up-to-date information insights. Various news portals earn revenue from advertising using pay-per-click methods that encourage article writers to use clickbait techniques to attract visitors. However, the negative effects of clickbait include a decrease in journalism quality and the spread of hoaxes. This problem can be prevented by using text classification to classify clickbait in news titles. One method that can be used for text classification is a neural network. Artificial neural networks use algorithms that can independently adjust input coefficient weights. This makes this algorithm highly effective for modeling non-linear statistical data. The artificial neural network algorithm, especially the Long Short-Term Memory (LSTM), has been widely used in various natural language processing fields with satisfying results, including text classification. To improve the performance of the neural network model, adjustments can be made to the model's hyperparameters. Hyperparameters are parameters that cannot be obtained through data and must be defined before the training process. In this research, the Long Short-Term Memory (LSTM) model was used in clickbait classification in news titles. Sixteen neural network models were trained with different hyperparameter configurations for each model. Hyperparameter tuning was carried out using the random search algorithm. The dataset used was the CLICK-ID dataset published by William & Sari, 2020[1], with a total of 15,000 annotated data. The research results show that the developed LSTM model has a validation accuracy of 0.8030, higher than William & Sari's research, and a validation loss of 0.4876. Using this model, researchers were able to classify clickbait in news titles with fairly good accuracy. Purpose: The study was to develop and evaluate a LSTM model with hyperparameter tuning for clickbait classification on news headlines. The thesis also aims to compare the performance of simple LSTM and bidirectional LSTM for this task. Methods: This study uses CLICK-ID dataset and applies different text preprocessing techniques. The dataset later was used to build and train 16 LSTM models with different hyperparameters and evaluates them using validation accuracy and loss. This study uses random search for hyperparameter tuning. Result: The results of the study show that the best model for clickbait classification on news headlines is a bidirectional LSTM model with one layer, 64 units, 0.2 dropout rate, and 0.001 learning rate. This model achieves a validation accuracy of 0.8030 and a validation loss of 0.4876. The results also show that hyperparameter tuning using random search can improve the performance of the LSTM models by avoiding zero probabilities and finding the optimal values for the hyperparameters. Novelty: This study compares and analyzes the different preprocessing methods on text and the different configurations of the models to find the best model for clickbait classification on news headlines. The study also uses hyperparameter tuning to tune the model into the best model and finding the optimal values for the hyperparameters.

Consumer Price Index(CPI) is the main standard to identify inflation or deflation. Accurate prediction of CPI will help the government to implement macro-control and formulate price stabilization policies, so as to achieve the goal of building a moderately prosperous society. CPI is a non-stationary and non-linear time series, and has relevance in time dimension. In order to fully mine the correlation of CPI sequence in long and short time span, a method of predicting CPI using Long Short-Term Memory(LSTM) model is proposed. Taking historical CPI data of Anhui Province as the empirical analysis object, modeling and predicting are carried out. The prediction effect of LSTM is compared with classic time series model-Autoregressive Integrated Moving Average(ARIMA). According to the predicted results, LSTM model has significantly improvement in RMSE and MAE indicators compared with ARIMA model, indicating the LSTM model has higher prediction accuracy. The SDAE indicator of LSTM model is smaller than ARIMA model, indicating the LSTM model has better prediction stability.

An early warning flood forecasting system that uses machine-learning models can be utilized for saving lives from floods, which are now exacerbated due to climate change. Flood forecasting is carried out by determining the river discharge and water level using hydrologic models at the target sites. If the water level and discharge are forecasted to reach dangerous levels, the flood forecasting system sends warning messages to residents in flood-prone areas. In the past, hybrid Long Short-Term Memory (LSTM) models have been successfully used for the time series forecasting. However, the prediction errors grow exponentially with the forecasting period, making the forecast unreliable as an early warning tool with enough lead time. Therefore, this research aimed to improve the accuracy of flood forecasting models by employing real-time monitoring network datasets and establishing temporal and spatial links between adjacent monitoring stations. We evaluated the performance of the LSTM, the Convolutional Neural Networks LSTM (CNN-LSTM), the Convolutional LSTM (ConvLSTM), and the Spatio-Temporal Attention LSTM (STA-LSTM) models for flood forecasting. The dataset, employed for validation, includes hourly discharge records, from 2012 to 2017, on six stations of the Humber River in the City of Toronto, Canada. Experiments included forecasting for both 6 and 12 h ahead, using discharge data as input for the past 24 h. The STA-LSTM model’s performance was superior to the CNN-LSTM, the ConvLSTM, and the basic LSTM models when the forecast time was longer than 6 h.

Accurate air pollution monitoring is critical to understand and mitigate the impacts of air pollution on human health and ecosystems. Due to the limited number and geographical coverage of advanced, highly accurate sensors monitoring air pollutants, many low-cost and low-accuracy sensors have been deployed. Calibrating low-cost sensors is essential to fill the geographical gap in sensor coverage. We systematically examined how different machine learning (ML) models and open-source packages could help improve the accuracy of particulate matter (PM) 2.5 data collected by Purple Air sensors. Eleven ML models and five packages were examined. This systematic study found that both models and packages impacted accuracy, while the random training/testing split ratio (e.g., 80/20 vs. 70/30) had minimal impact (0.745% difference for R2). Long Short-Term Memory (LSTM) models trained in RStudio and TensorFlow excelled, with high R2 scores of 0.856 and 0.857 and low Root Mean Squared Errors (RMSEs) of 4.25 µg/m3 and 4.26 µg/m3, respectively. However, LSTM models may be too slow (1.5 h) or computation-intensive for applications with fast response requirements. Tree-boosted models including XGBoost (0.7612, 5.377 µg/m3) in RStudio and Random Forest (RF) (0.7632, 5.366 µg/m3) in TensorFlow offered good performance with shorter training times (<1 min) and may be suitable for such applications. These findings suggest that AI/ML models, particularly LSTM models, can effectively calibrate low-cost sensors to produce precise, localized air quality data. This research is among the most comprehensive studies on AI/ML for air pollutant calibration. We also discussed limitations, applicability to other sensors, and the explanations for good model performances. This research can be adapted to enhance air quality monitoring for public health risk assessments, support broader environmental health initiatives, and inform policy decisions.

Increasingly intense climate change has increased the frequency and intensity of extreme weather, making weather prediction critical for mitigation and adaptation. This research focuses on long-term prediction of extreme weather using the Long ShortTerm Memory (LSTM) model, as well as evaluating the influence of climate change on prediction accuracy. In this study, historical weather data is used to train and test an LSTM model combined with a RandomForestClassifier. Analysis was carried out using the Mean Squared Error (MSE) evaluation technique for 50 epochs and 8 trials at various threshold values (26, 29, 32, 35, 38, 41, 44, 47). The research results show that the LSTM model is able to predict extreme weather with an accuracy of up to 100%. Apart from that, this research also predicts daily rainfall in Bandung City through the process of data collection, preprocessing, normalization and evaluation using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). This model produces an RMSE of 4.24 and MAE value of 2.72%, indicating quite good predictions. It is hoped that this research can make a significant contribution to the field of meteorology and can be developed further by adding parameters or other methods to improve the quality of predictions. Suggestions are given to increase the amount of data used to obtain better prediction results in the future.

Stress is a common issue in modern society and can lead to various health problems when left unaddressed. Accurate stress detection is, therefore, crucial in order to provide effective interventions and improve overall well-being. This study presents the implementation of a Long Short-Term Memory (LSTM) model to detect stress using electroencephalogram (EEG) signals. EEG signals were collected from a sample of participants while they were exposed to stress-inducing tasks and control tasks. The data was pre-processed using filtering and artifact removal techniques to ensure high quality and reliability. The pre-processed EEG signals were then used to extract relevant features, such as spectral power and coherence, which served as inputs to the LSTM model. A deep learning architecture was developed, incorporating the LSTM layers and other components to optimize the model's performance. The LSTM model was trained and validated using the available dataset. The results showed that the LSTM model significantly outperformed the other algorithms in terms of accuracy, sensitivity, and specificity. Furthermore, the model demonstrated robustness in detecting stress across various tasks and EEG channels. These findings suggest that LSTM-based models have the potential to be used as effective tools for stress detection in real-life scenarios, and can contribute to the development of more personalized stress management interventions. Future research should focus on refining the model and exploring its applicability in different populations and settings.

Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation

Abstract. The information available on the internet nowadays is diverse and moves very quickly. Information is becoming easier to obtain by the general public with the numerous online media outlets, including news portals that provide up-to-date information insights. Various news portals earn revenue from advertising using pay-per-click methods that encourage article writers to use clickbait techniques to attract visitors. However, the negative effects of clickbait include a decrease in journalism quality and the spread of hoaxes. This problem can be prevented by using text classification to classify clickbait in news titles. One method that can be used for text classification is a neural network. Artificial neural networks use algorithms that can independently adjust input coefficient weights. This makes this algorithm highly effective for modeling non-linear statistical data. The artificial neural network algorithm, especially the Long Short-Term Memory (LSTM), has been widely used in various natural language processing fields with satisfying results, including text classification. To improve the performance of the neural network model, adjustments can be made to the model's hyperparameters. Hyperparameters are parameters that cannot be obtained through data and must be defined before the training process. In this research, the Long Short-Term Memory (LSTM) model was used in clickbait classification in news titles. Sixteen neural network models were trained with different hyperparameter configurations for each model. Hyperparameter tuning was carried out using the random search algorithm. The dataset used was the CLICK-ID dataset published by William &amp; Sari, 2020[1], with a total of 15,000 annotated data. The research results show that the developed LSTM model has a validation accuracy of 0.8030, higher than William &amp; Sari's research, and a validation loss of 0.4876. Using this model, researchers were able to classify clickbait in news titles with fairly good accuracy. Purpose: The study was to develop and evaluate a LSTM model with hyperparameter tuning for clickbait classification on news headlines. The thesis also aims to compare the performance of simple LSTM and bidirectional LSTM for this task. Methods: This study uses CLICK-ID dataset and applies different text preprocessing techniques. The dataset later was used to build and train 16 LSTM models with different hyperparameters and evaluates them using validation accuracy and loss. This study uses random search for hyperparameter tuning. Result: The results of the study show that the best model for clickbait classification on news headlines is a bidirectional LSTM model with one layer, 64 units, 0.2 dropout rate, and 0.001 learning rate. This model achieves a validation accuracy of 0.8030 and a validation loss of 0.4876. The results also show that hyperparameter tuning using random search can improve the performance of the LSTM models by avoiding zero probabilities and finding the optimal values for the hyperparameters. Novelty: This study compares and analyzes the different preprocessing methods on text and the different configurations of the models to find the best model for clickbait classification on news headlines. The study also uses hyperparameter tuning to tune the model into the best model and finding the optimal values for the hyperparameters.

In this study, we employed the response surface method (RSM) and the long short-term memory (LSTM) model to optimize operational parameters and predict chemical oxygen demand (COD) removal in the electrocoagulation-catalytic ozonation process (ECOP) for pharmaceutical wastewater treatment. Through RSM simulation, we quantified the effects of reaction time, ozone dose, current density, and catalyst packed rate on COD removal. Then, the optimal conditions for achieving a COD removal efficiency exceeding 50% were identified. After evaluating ECOP performance under optimized conditions, LSTM predicted COD removal (56.4%), close to real results (54.6%) with a 0.2% error. LSTM outperformed RSM in predictive capacity for COD removal. In response to the initial COD concentration and effluent discharge standards, intelligent adjustment of operating parameters becomes feasible, facilitating precise control of the ECOP performance based on this LSTM model. This intelligent control strategy holds promise for enhancing the efficiency of ECOP in real pharmaceutical wastewater treatment scenarios. PRACTITIONER POINTS: This study utilized the response surface method (RSM) and the long short-term memory (LSTM) model for pharmaceutical wastewater treatment optimization. LSTM predicted COD removal (56.4%) closely matched experimental results (54.6%), with a minimal error of 0.2%. LSTM demonstrated superior predictive capacity, enabling intelligent parameter adjustments for enhanced process control. Intelligent control strategy based on LSTM holds promise for improving electrocoagulation-catalytic ozonation process efficiency in pharmaceutical wastewater treatment.