Multivariate Long Short-term Memory Research Articles

Exploring the applicability of the experiment-based ANN and LSTM models for streamflow estimation

AbstractThe Yeşilırmak River Basin in northern Türkiye is crucial for the region’s water supply, agriculture, hydroelectric power generation, and clean drinking water. The primary goal of this study is to determine which modeling approach is most appropriate for various locations within the basin and how well meteorological data can predict river flow rates. Hydrological and meteorological forecasting both depend on the prediction of river flow rates. An artificial neural network (ANN), Univariate and Multivariate Long Short-Term Memory (LSTM) models have been utilized for streamflow forecasting. This research aims to determine the best model for several provinces in the basin area and give decision-makers a tool for reliable river flow rate estimates by combining LSTM and ANN models. According to research findings, the supervised multivariate LSTM model performed better than the unsupervised model in accuracy and precision. The sliding window methodology is suitable for estimating river flow based on meteorological datasets because it offers a primary method for reinterpreting time-series data in a supervised learning style. Compared to LSTM models, the ANN model that has been statistically optimized through experiments (DoE) design performs better in forecasting the river flow rate in the Yeşilırmak River basin (R2 = 0.98, RMSE = 0.18). The study’s findings provided prospective cognitive models for the strategic management of water resources by forecasting future data from flow monitoring stations.

Feature engineering and deep learning-based approach for event detection in Medical Internet of Things (MIoT)

Medical Internet of Things (MIoT) is becoming increasingly mainstream as their applications continue to grow. These applications include remote healthcare monitoring, drug storage, alarm systems, and medical wearable devices. Remote patient monitoring, especially using wearable devices, has improved the health and protection of numerous people, while avoiding unnecessary hospital visits. Ideally, healthcare monitoring systems should accurately and timely detect if the patient is entering a critical condition, and alert the concerned doctor accordingly. However, in practice, there are two kinds of alarms raised by such systems, namely, events and anomalies. Events are non-erroneous data that do not conform to the expected values, indicating abnormality in the patient’s condition. On the other hand, anomalies are erroneous data that may result from faulty sensors, electromagnetic interference, malicious attacks, or hardware tampering. These anomalies lead to false alarms which affect the decision making process and may cause danger to the patient’s life. Traditionally, wearable MIoTs, measuring different vitals, frequently communicate with the patient’s phone, or a local processing unit (LPU), in order to analyze and process the collected data. However, the increase in processing capabilities of IoT devices has made on-device event detection possible. This adds an extra layer of defense while avoiding unnecessary communication with LPU. In this paper, a healthcare monitoring system is proposed which compromises of two layers - (1) an online lightweight approach, based on multivariate long-short term memory (LSTM) autoencoder, embedded in each MIoT, that is able to detect data abnormality and alarms the LPU, (2) a correlation technique, at the LPU, that differentiates between anomalies and events, and alerts the patient’s doctor only in case of an event. Since a single sensor reading does not provide enough clinical insight to detect the full length of an event, a feature engineering approach is implemented to extract interpretable statistical, dynamic and physiological features that provide the clinical insight needed. The proposed approach is simulated using Medical Information Mart for Intensive Care (MIMIC) dataset for various vital signs, such as heart rate, systolic and diastolic blood pressure. It is compared with four benchmarks, where the results show the robustness of the model in differentiating between anomalies and events, with event detection sensitivity and specificity above 93%.

Machine Learning Algorithms for Power System Sign Classification and a Multivariate Stacked LSTM Model for Predicting the Electricity Imbalance Volume

The energy transition to a cleaner environment has been a concern for many researchers and policy makers, as well as communities and non-governmental organizations. The effects of climate change are evident, temperatures everywhere in the world are getting higher and violent weather phenomena are more frequent, requiring clear and firm pro-environmental measures. Thus, we will discuss the energy transition and the support provided by artificial intelligence (AI) applications to achieve a cleaner and healthier environment. The focus will be on applications driving the energy transition, the significant role of AI, and collective efforts to improve societal interactions and living standards. The price of electricity is included in almost all goods and services and should be affordable for the sustainable development of economies. Therefore, it is important to model, anticipate and understand the trend of electricity markets. The electricity price includes an imbalance component which is the difference between notifications and real-time operation. Ideally it is zero, but in real operation such differences are normal due to load variation, lack of renewable energy sources (RES) accurate prediction, unplanted outages, etc. Therefore, additional energy has to be produced or some generating units are required to reduce generation to balance the power system. Usually, this activity is performed on the balancing market (BM) by the transmission system operator (TSO) that gathers offers from generators to gradually reduce or increase the output. Therefore, the prediction of the imbalance volume along with the prices for deficit and surplus is of paramount importance for producers’ decision makers to create offers on the BM. The main goal is to predict the imbalance volume and minimize the costs that such imbalance may cause. In this chapter, we propose a method to predict the imbalance volume based on the classification of the imbalance sign that is inserted into the dataset for predicting the imbalance volume. The imbalance sign is predicted using several classifiers and the output of the classification is added to the input dataset. The rest of the exogenous variables are shifted to the values from previous day d − 1. Therefore, the input variables are either predicted (like the imbalance sign) or are known from d − 1. Several metrics, such as mean average percentage error (MAPE), determination coefficient R2 and mean average error (MAE) are calculated to assess the proposed method of combining classification machine learning (ML) algorithms and recurrent neural networks (RNN) that memorize variations, namely long short-term memory (LSTM) model.

Multivariate GRU and LSTM models for wave forecasting and hindcasting in the southern Caspian Sea

Reliable wave forecasts and hindcasts are pivotal elements for a wide range of marine activities, coastal engineering applications, renewable energy and wave climate studies. This study explores capability of recurrent neural networks for wave hindcasting and multi-step wave forecasting in the southern Caspian Sea, a region with a limited observational data. Gated recurrent unit (GRU) and long short-term memory (LSTM) models are fed by buoy records for wave forecasting up to 6 h ahead and ERA5 reanalysis data as the model inputs for wave hindcasting. Special efforts are devoted to improve the accuracy of the models by including some additional features (e.g., wave age and swell) in the input layer. Different error measures are employed to evaluate performance of the models at two stations, Amirabad and Anzali. Using multivariate GRU and LSTM models, suitable wave forecasts and hindcasts are achieved for the locations. Although the model performance deteriorates with extending the forecasting time horizon, the forecasts of significant wave height (Hs) up to 6 h ahead are still satisfactory. The best hindcasting model yields a high linear correlation between hindcasted and measured Hs with R2 = 0.75 for Anzali and R2 = 0.83 for Amirabad. Finally, wave age and significant height of total swell (Hs-swell) can be considered as tentative input variables to improve efficiency of the models.

Machine learning in neurological disorders: A multivariate LSTM and AdaBoost approach to Alzheimer's disease time series analysis

AbstractIntroductionAlzheimer's disease (AD) is a progressive brain disorder that impairs cognitive functions, behavior, and memory. Early detection is crucial as it can slow down the progression of AD. However, early diagnosis and monitoring of AD's advancement pose significant challenges due to the necessity for complex cognitive assessments and medical tests.MethodsThis study introduces a data acquisition technique and a preprocessing pipeline, combined with multivariate long short‐term memory (M‐LSTM) and AdaBoost models. These models utilize biomarkers from cognitive assessments and neuroimaging scans to detect the progression of AD in patients, using The AD Prediction of Longitudinal Evolution challenge cohort from the Alzheimer's Disease Neuroimaging Initiative database.ResultsThe methodology proposed in this study significantly improved performance metrics. The testing accuracy reached 80% with the AdaBoost model, while the M‐LSTM model achieved an accuracy of 82%. This represents a 20% increase in accuracy compared to a recent similar study.DiscussionThe findings indicate that the multivariate model, specifically the M‐LSTM, is more effective in identifying the progression of AD compared to the AdaBoost model and methodologies used in recent research.

Li-Ion Battery Temperature Forecasting Method: Case-Study

Monitoring and managing battery health is crucial for enhancing performance and lowering running expenses for electronic devices. This paper covers the Deep-learning-enabled temperature forecasting for Li- ion batteries, where they are tested independently. This research presents time series forecasting approaches to predict the temperature of the battery packs. In the proposed model, a Long Short-Term Memory (LSTM) and autoregressive integrated moving average (ARIMA) for predicting the battery temperature and beware of probable future temperatures beforehand to minimize the chances of overcharging and prevent the battery from crossing the threshold value above which battery's health characteristics might get hampered. The growing popularity of data-driven battery prognostics methods shows that ARIMA and LSTM are even when there aren't many prior details available about the batteries. Have a unique dataset of 34 lithium-ion battery packs for this challenge. In one way, the results imply that the existing ARIMA techniques offer interpreting data at various batteries. Having said that, LSTM model outcome recommend that the developed Univariate and Multivariate LSTM model provides finer prediction accuracy in the existence of greater diversification in data for one battery. Thus, try to generalize one forecasting model for each battery type depending on the model's performance.

LSTM time series NDVI prediction method incorporating climate elements: A case study of Yellow River Basin, China

Accurate prediction of the trend of Normalized Difference Vegetation Index (NDVI) time series in the Yellow River Basin (YRB) is crucial for the assessment of the hydrological and ecological environment in this region. Currently, the NDVI time series prediction model is primarily based on traditional models and single-variable neural network models. Nevertheless, these models present challenges in considering the limitations of multiple factors, causing the NDVI time series prediction results to lack reliability. To predict NDVI time-series in the YRB of China, this study constructed a multilayer multivariate Long-Short Term Memory (LSTM) neural network model including climatic components. The initial important climatic elements in this region were identified using GeoDetector. Then, the relationship between NDVI and climatic factors in the YRB of China is established. Finally, numerical scale data are used to train and predict a multilayer multivariate LSTM model with climatic components. According to the results, the three-layer multivariate LSTM neural network NDVI time series prediction model developed in this study has the best performance among the evaluated indices. When compared to existing time series prediction models, the proposed model in this study takes into account the common constraint effect of various climate factors on NDVI. This leads to a significantly improved prediction accuracy, presenting new opportunities for enhancing the prediction model. By analyzing the NDVI time series prediction outcomes for the YRB, it has been determined that the ecological environment of the area will continuously improve in the future. This study offers significant technological and theoretical backing for assessing the hydrological and ecological environment of the YRB and comparable ecologically vulnerable regions in China.

Multivariate multi-step LSTM model for flood runoff prediction: a case study on the Godavari River Basin in India

Abstract Flood is India's most prevalent natural calamity, devastatingly affecting human lives, infrastructure, and agriculture. Predicting floods can help to mitigate the potential damage and conduct timely evacuation drives. This research proposes a deep-learning regression model to forecast flood runoff. Various climatological, hydrological, land, and vegetation-related data have been collected from multiple sources for 18 years (2002–2019) to create a comprehensive dataset for the Godavari River at the Perur water station in India. The relevant attributes identified through feature selection are river water level, precipitation, temperature, surface pressure, evaporation, soil water content, daily runoff, and average river flow. The selected features were fed into various time series prediction models like AutoRegressive Integrated Moving Average (ARIMA), Prophet, Neural Prophet, and Long Short-Term Memory (LSTM). The LSTM model obtained the best results achieving a Root Mean Squared Error (RMSE) value of 0.05, Mean Absolute Error (MAE) value of 0.007, Willmott's Index (WI) of 0.83, Legates-McCabe's Index (LMI) of 0.58, and R2 of 0.67 for a 1-day prediction with a look-back window of 183 days. The model is also trained to predict the flood runoff value for a week ahead. The proposed model can serve as an essential component in flood warning systems.

Univariate and Multivariate Long Short Term Memory (LSTM) Model to Predict Covid-19 Cases in Malaysia Using Integrated Meteorological Data

The rate of transmission of coronavirus disease (COVID-19) has been very fast since the first reported case in December 2019 in Wuhan, China. The disease has infected more than 3 million people worldwide and resulted in more than 224 thousand deaths as of May 1, 2020, reported by The World Health Organization (WHO). In the past, meteorological parameters such as temperature and humidity were essential and effective factors against serious infectious diseases such as influenza and Severe Acute Respiratory Syndrome (SARS). Therefore, exploring the relationship between meteorological factors and active COVID-19 cases is essential. This study employs the long-short term memory (LSTM) method to predict Covid-19 Cases in Malaysia. We propose a univariate and multivariate model using Covid-19 cases and meteorology data. The univariate LSTM model uses Covid-19 active cases data in a year as a control attribute for model development. The multivariate LSTM model uses the integrated Covid-19 cases, and meteorology data consists of attributes: minimum, maximum, and average values of Humidity, Temperature, Windspeed, and Pressure from 13 states of Malaysia. The model's performance is evaluated using errors such as MAE, RMSE, MAPE, and the R2 Score. The low errors and higher R2 score indicate the model's excellent performance. We observed that the univariate LSTM model gives the least error in five states, indicating that those states' daily active cases are the main contributing factors. In the multivariate LSTM model, the daily cases and humidity, temperature, and windspeed are the main factors in several different states. The result of the study is to help the government to prevent and manage the spread of the COVID-19 and other upcoming pandemic better.

Deep learning approach to forecast air pollution based on novel hourly index

Air pollution is a pressing concern that the entire world is striving to combat. Among air pollutants, particulate matter poses a significant threat to human health. The Sustainable Development Goals (SGD3, SGD7 and SGD11) include initiatives to address air pollution. Two innovative methods are proposed in this research to predict the PM2.5 concentration in advance. While multivariate time series prediction models typically employ multiple features as inputs, this research reduces the number of inputs, which makes the proposed combination of approaches simple and effective. The approaches involve the development of two new indexing methods, namely, the Hourly Relative Mean Index and the Hourly Weighted Index. This research offers innovative hybrid deep learning models that incorporate the newly developed indices, Long Short Term Memory (LSTM) models, and robust preprocessing techniques. Multivariate Isolation Forest Relative Index Bidirectional LSTM and Multivariate Isolation Forest Weighted Index LSTM methods are used to forecast PM2.5 concentration for an hourly time frame. Further, Multivariate Isolation Forest Relative Index LSTM and Multivariate Isolation Forest Weighted Index LSTM methods are used to forecast PM2.5 concentration 48 h ahead. The study establishes that the proposed combination of approaches outperform traditional ways to achieve superior performance with reduced complexities requiring fewer inputs for predictions.

Accident parameter prediction method for lead-bismuth cooled reactor based on a multivariate LSTM network coupled with an optimization algorithm

Accurate acquisition of key parameters of lead–bismuth cooled reactors under accident conditions is a prerequisite for reactor safety analyses. In this work, four optimization algorithms(Particle Swarm Algorithm, Genetic algorithm, Quantum genetic algorithm, Whale optimization algorithm) are used to improve the forecast efficiency of a long short-term memory (LSTM) neural network using hyperparameter optimization, and a method is developed to predict the parameters of a lead–bismuth cooled reactor (MARS-3) during a loss of flow accident. A comprehensive evaluation of the proposed method is performed using the TOPSIS technique based on the data samples generated using the sub-channel code SUBCHANFLOW. The results show that the prediction performance of the multivariate LSTM neural network coupled with the particle swarm optimization method is optimal, and its computational efficiency is 438 times that of SUBCHANFLOW. Overall, the study findings can help improve the prediction efficiency for key thermal parameters of lead–bismuth cooled reactors and enhance the emergency response capability of such reactors.

Predicting Commercial Building Energy Consumption Using a Multivariate Multilayered Long-Short Term Memory Time-Series Model

The global demand for energy has been steadily increasing due to population growth, urbanization, and industrialization. Numerous researchers worldwide are striving to create precise forecasting models for predicting energy consumption to manage supply and demand effectively. In this research, a time-series forecasting model based on multivariate multilayered long short-term memory (LSTM) is proposed for forecasting energy consumption and tested using data obtained from commercial buildings in Melbourne, Australia: the Advanced Technologies Center, Advanced Manufacturing and Design Center, and Knox Innovation, Opportunity, and Sustainability Center buildings. This research specifically identifies the best forecasting method for subtropical conditions and evaluates its performance by comparing it with the most commonly used methods at present, including LSTM, bidirectional LSTM, and linear regression. The proposed multivariate, multilayered LSTM model was assessed by comparing mean average error (MAE), root-mean-square error (RMSE), and mean absolute percentage error (MAPE) values with and without labeled time. Results indicate that the proposed model exhibits optimal performance with improved precision and accuracy. Specifically, the proposed LSTM model achieved a decrease in MAE of 30%, RMSE of 25%, and MAPE of 20% compared with the LSTM method. Moreover, it outperformed the bidirectional LSTM method with a reduction in MAE of 10%, RMSE of 20%, and MAPE of 18%. Furthermore, the proposed model surpassed linear regression with a decrease in MAE by 2%, RMSE by 7%, and MAPE by 10%.These findings highlight the significant performance increase achieved by the proposed multivariate multilayered LSTM model in energy consumption forecasting.

Spatiotemporal pore-water pressure prediction using multi-input long short-term memory

The increase in pore-water pressure (PWP) in slopes due to extreme rainfall is one of the major triggering factors for landslides. In recent years, machine learning (ML) techniques have been proposed to predict PWP response under heavy rainfall for slope stability analysis. However, most of these methods neglect the spatiotemporal nature of the problem by treating the PWP dataset as a univariate time-series problem. As such, the trained model remains valid for the given sensor and fails to predict the response when used for other locations. In this paper, a novel multivariate long short-term memory (M-LSTM) is proposed to predict the PWP response by simultaneously using the spatial and temporal PWP data from multiple measurement locations. The choice of optimal measurement locations for model training is made using the principal component analysis (PCA) and silhouette value analysis. The performance of the proposed model is evaluated using five different performance indicators named (i) mean absolute error (MAE), (ii) mean square error (MSE), (iii) root mean square error (RMSE), (iv) coefficient of determination (R2), and (v) Pearson correlation coefficient (PCC). The results obtained with M-LSTM are compared with the predictions from the univariate LSTM algorithm. The comparison shows that the univariate LSTM model is only valid for the location used for training and cannot be applied to other locations, implying the loss of generality of the model. In contrast, the proposed M-LSTM is not hamstrung by the foregoing issue and accurately predicts the PWP response for non-training sensor locations, which can also incorporate the spatial and temporal variation within the data.

Forecasting of Ionospheric Total Electron Content Data Using Multivariate Deep LSTM Model for Different Latitudes and Solar Activity

The ionospheric state is becoming increasingly important to forecast for the reliable operation of terrestrial and space-based radio-communication systems which are influenced by ionospheric space weather. In this study, we have investigated and tested a multivariate long short-term memory (LSTM) deep learning model for its forecasting accuracy over different latitudinal regions during the solar quiet and solar active years. We also tested its prediction capability during the occurrence of a geomagnetic storm. Four stations qaq1 (60.7°N, 46.04°W), baie (49.18°N, 68.26°W), mas1 (27.76°N, 15.63°W), and bogt (4.64°N, 74.08°W) in the northern hemisphere were used in this study. To optimize the feature extraction process, we used heat map to find the correlation between TEC and the various exogenous parameters and finally nine correlated parameters were used as inputs to train the LSTM model. The performance of the LSTM model was validated by comparing it with the multilayer perceptron (MLP) machine learning algorithm using root mean square error (RMSE) and mean absolute error (MAE) as evaluation indices. The results showed an accuracy improvement of 70% and 64% over MLP during the solar quiet and active years, respectively. The prediction accuracy of our LSTM model was also 74% better than MLP during the geomagnetic storm event. These findings demonstrate the effectiveness of the developed LSTM model and the right selection of the exogenous parameters in estimating TEC, and suggest that this LSTM model can be used for short-term TEC forecasting.

Novel MIA-LSTM Deep Learning Hybrid Model with Data Preprocessing for Forecasting of PM2.5

Day by day pollution in cities is increasing due to urbanization. One of the biggest challenges posed by the rapid migration of inhabitants into cities is increased air pollution. Sustainable Development Goal 11 indicates that 99 percent of the world’s urban population breathes polluted air. In such a trend of urbanization, predicting the concentrations of pollutants in advance is very important. Predictions of pollutants would help city administrations to take timely measures for ensuring Sustainable Development Goal 11. In data engineering, imputation and the removal of outliers are very important steps prior to forecasting the concentration of air pollutants. For pollution and meteorological data, missing values and outliers are critical problems that need to be addressed. This paper proposes a novel method called multiple iterative imputation using autoencoder-based long short-term memory (MIA-LSTM) which uses iterative imputation using an extra tree regressor as an estimator for the missing values in multivariate data followed by an LSTM autoencoder for the detection and removal of outliers present in the dataset. The preprocessed data were given to a multivariate LSTM for forecasting PM2.5 concentration. This paper also presents the effect of removing outliers and missing values from the dataset as well as the effect of imputing missing values in the process of forecasting the concentrations of air pollutants. The proposed method provides better results for forecasting with a root mean square error (RMSE) value of 9.8883. The obtained results were compared with the traditional gated recurrent unit (GRU), 1D convolutional neural network (CNN), and long short-term memory (LSTM) approaches for a dataset of the Aotizhonhxin area of Beijing in China. Similar results were observed for another two locations in China and one location in India. The results obtained show that imputation and outlier/anomaly removal improve the accuracy of air pollution forecasting.

Spatio-Temporal vehicle traffic flow prediction using multivariate CNN and LSTM model

Traffic congestion is a major problem in developing and developed countries vehicle traffic management systems. Traffic control system works based on the idea of removing instabilities and avoid accidents in order to minimize the traffic and maximize the vehicle flow. To control the congestion need to predict the upcoming traffic flow and it will be useful for Advanced Traffic Information Systems (ATIS), Advanced Traffic Management Systems (ATMS) and traffic analytics. Non–linear historical data and uncertain factors influence the vehicle congestion at peak hours which cannot be considered in existing algorithms. This study proposes hybrid neural network algorithms such as Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) network for short term traffic flow prediction based on multivariate analysis. Widely referred datasets Performance Measurement Systems (PEMS) and Mesowest have been used to evaluate this model. Experiment results shows that CNN-LSTM Hybrid prediction model achieves high accuracy compared with other models.

딥러닝 기법을 활용한 양식산 조피볼락 산지가격 예측 연구 －LSTM(Long-short Term Memory)과 GRU(Gated Recurrent Units) 모델을 중심으로－

This study is aimed to forecast the producer price of aquaculture seafood using LSTM(Long-short Term Memory) and GRU(Gated Recurrent Units) models, a type of deep learning model. Since the producer price is directly related to aquacultural farm’s profitability, accurate forecasting of the producer price is essential to establish an effective production and management plan for aquaculture and stabilize supply and demand of farmed seafood. Korean Rockfish(Sebastes schlegelii) is a commercially important fish species that ranks second in domestic farmed fish production and is the main breed of fish farms in Tongyeong region. As the volatility of the producer price of Korean Rockfish has recently intensified, the importance of forecasting the producer price is increasing. In the analysis, total 19 variables were used, including producer prices in other regions, production-related variables, consumption-related variables, alternative farmed fish variables, water temperature, and COVID-19 dummy variables. Total 189 monthly data from October 2006 to June 2022 were used. In this study, the producer price of farmed Korean Rockfish was forecasted by LSTM and GRU models, a type of RNN(Recurrent Neural Network) model specialized for time series forecasting and the accuracy of models was compared with MAPE(Mean Absolute Percent Error). Results showed that MAPEs of LSTM and GRU were 4.66% and 6.27%, respectively. In addition, when comparing the accuracy by the number of independent variables, it was found that the accuracy of the multivariate LSTM model was better than that of the univariate LSTM model.

Forecasting cryptocurrencies’ price with the financial stress index: a graph neural network prediction strategy

ABSTRACT This article proposes a graph neural network strategy (GNN), in which the long short-term memory (LSTM) and graph convolution network (GCN) are applied to capture both temporal and spatial features to forecast the price of Bitcoin, Litecoin, Ethereum, and Dash Coin with the ‘stable-coin’ Tether (USDT) and financial stress index (FSI). The main results show that the GNN strategy has better performance than univariate LSTM and multivariate LSTM in all of the seven steps forward forecasting. A sensitivity check shows that USDT and FSI/sub-FSI are important factors in the construction of the graphs and they verify the validity of the results.

Stock Price Prediction through STL Decomposition using Multivariate Two-way Long Short-term Memory

With advancements in machine-learning techniques, stock-price movements can ostensibly be forecasted using time-series data. In this study, several different types of long short-term memory (LSTM) are used to predict the closing prices of Japanese stocks five days into the future. Also, in this study, four different features [i.e., simple moving average (SMA), linear weighted moving average (WMA), exponential WMA (EMA), and the Savitzky–Golay (SG) metric] are generated from daily stock-price data and split into two components (i.e., trend and seasonal) by applying seasonal–trend decomposition using Loess (STL) decomposition. The prediction results are evaluated in terms of return, root-mean-square error (RMSE), mean absolute error (MAE), and other relevant measures of accuracy and relevancy. As a result, the multivariate two-way LSTM model yielded the highest overall performance. With respect to the RMSE and MAE of the training data, the multivariate two-way LSTM was not superior to the other models. However, with respect to RMSE and MAE on the validation data, it was the best. Also, the multivariate two-way LSTM model yielded the highest overall performance in terms of the accuracy of the direction of stock prices.

Weather Conditions and COVID-19 Cases: Insights from the GCC Countries

The prediction of new COVID-19 cases is crucial for decision makers in many countries. Researchers are continually proposing new models to forecast the future tendencies of this pandemic, among which long short-term memory (LSTM) artificial neural networks have exhibited relative superiority compared to other forecasting techniques. Moreover, the correlation between the spread of COVID-19 and exogenous factors, specifically weather features, has been explored to improve forecasting models. However, contradictory results have been reported regarding the incorporation of weather features into COVID-19 forecasting models. Therefore, this study compares uni-variate with bi- and multi-variate LSTM forecasting models for predicting COVID-19 cases, among which the latter models consider weather features. LSTM models were used to forecast COVID-19 cases in the six Gulf Cooperation Council countries. The root mean square error (RMSE) and coefficient of determination () were employed to measure the accuracy of the LSTM forecasting models. Despite similar weather conditions, the weather features that exhibited the strongest correlation with COVID-19 cases differed among the six countries. Moreover, according to the statistical comparisons that were conducted, the improvements gained by including weather features were insignificant in terms of the RMSE values and marginally significant in terms of the values. Consequently, it is concluded that the uni-variate LSTM models were as good as the best bi- and multi-variate LSTM models; therefore, weather features need not be included. Furthermore, we could not identify a single weather feature that can consistently improve the forecasting accuracy.