Long Short-term Memory Method Research Articles

Machine-learning downscaling of GPM satellite precipitation products in mountainous regions: A case study in Chongqing

High-quality precipitation data are essential for research in hydrology, meteorology and ecology. Nevertheless, in mountainous regions with intricate terrain, the reliability of gridded precipitation data derived from station data interpolation is low due to the limited number of stations caused by the difficulty of station setup. Current satellite precipitation products suffer from low spatial resolution, making them unsuitable for hydrological and meteorological research at small and medium scales. Their application in mountainous regions with significant spatiotemporal heterogeneity is even more challenging. To this end, downscaling satellite precipitation products has become an effective method for obtaining accurate spatial distribution information of precipitation in these regions. This study employs a method of first calibration followed by downscaling analysis of GPM daily precipitation product in the Chongqing area using random forest (RF), extreme gradient boosting (XGBoost), and long short-term memory (LSTM) algorithms. Ultimately, the spatial resolution of GPM product is improved from 0.1° to 0.01° (~1 km). The findings demonstrate that: (1) the station-calibrated GPM precipitation product performed better than the original GPM product, and it is closer to the station measurements; (2) in practical applications, the LSTM downscaling algorithm can effectively enhance spatial resolution without compromising accuracy, whereas RF and XGBoost incur considerable accuracy loss when enhancing spatial resolution; (3) the downscaled results from all three algorithms were consistent with the calibrated GPM precipitation maps and significantly improved the spatial details of precipitation. Among them, the results of the LSTM method exhibited greater continuity in the spatial distribution of precipitation, aligning more closely with the characteristics of precipitation distribution. In summary, the LSTM algorithm demonstrates greater potential for the downscaling of GPM precipitation product in the study area. This research provides a promising high-quality precipitation data generation scheme for mountainous regions with sparse station coverage and complex terrain and landforms.

Physics-guided fault diagnosis method for proton exchange membrane fuel cells based on LSTM neural network

In this paper, we propose a novel hybrid method for fault diagnosis of Proton Exchange Membrane Fuel Cells (PEMFCs) based on the combination of a physics-based model and a long short-term memory (LSTM) neural network. By incorporating the physics-based model in the fault diagnosis algorithm, we can access to several process variables not directly measured through sensors but related to the state of the PEMFC stack. The model estimates are subsequently combined with signals measured on the PEMFC stack and inputted to a LSTM neural network. The performance of the physics-guided LSTM is evaluated on an extensive dataset comprising a thousand hours of operation of a PEMFC stack under dynamic load profiles, proving the enhanced capability of the proposed fault diagnosis method in capturing complex fault patterns. Furthermore, the effectiveness of the proposed method in dealing with PEMFC aging is tested by using data from the initial phase of stack operation for algorithm training and reserving the data from the aged stack operation for the testing phase. The experimental results reveal that the proposed physics-guided LSTM method allows for a significant amelioration over purely data-driven LSTM.

COMPARISON OF ARIMA AND LSTM METHODS IN PREDICTING JAKARTA SEA LEVEL

As a coastal city, Jakarta faces enormous risks from sea level rise brought on by climate change, and it is critical to create efficient plans to anticipate and minimize any potential negative effects. Predictive modeling is essential in addressing this challenge in order to anticipate and mitigate any potential negative effects of sea level rise. Therefore, research was conducted with the aim of comparing the performance of two prediction methods, namely Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM). Sea level was predicted using both techniques up to the end of 2023. Performance indicators, including Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE), were employed to assess the quality of both prediction models. The result shows that the ARIMA (1,1,4) model is more effective in predicting sea level than the LSTM. The MAE, MAPE, and RMSE values for ARIMA (1,1,4) are 7.19, 4.86%, and 10.35, respectively. In the meantime, the sea level in Jakarta is predicted to remain reasonably steady, according to the forecasted findings from both models. This study is expected to make a significant contribution to understanding and mitigating the potential impacts of sea level rise in Jakarta as a result of climate change.

A Case Study: Comparison of LSTM and GRU Methods for Forecasting Oil, Non-Oil, and Gas Export Values in Indonesia

This study explores the forecasting of Indonesia’s oil, non-oil, and gas export values, highlighting its critical role in supporting national economic growth. Given the inherent volatility in export values, accurate forecasting is vital for informed economic decision-making. The research employs Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models, both well-regarded for their ability to handle sequential data and complex temporal patterns. Model performance was evaluated using Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The findings indicate that although both models produced nearly identical MAPE values of 99.99% across the oil, non-oil, and gas sectors, the GRU model outperformed the LSTM model with RMSE values of 0.0655 for oil and gas exports and 0.0697 for non-oil and gas exports. Moreover, the GRU model’s forecasts align closely with data from the Central Bureau of Statistics (BPS), which reported an 11.33% decline in Indonesia’s export values by the end of 2023. These results suggest that the GRU model not only offers greater accuracy but is also applicable to other economic forecasting contexts, such as exchange rate and inflation predictions, thereby enhancing economic policy-making.

Verb Form Recognition and Error Detection in English Articles Using Long Short-Term Memory and Grammar Checks

Error checking of verb forms in English articles is beneficial for learning English and improving the fluency of English texts. In this study, long shortterm memory (LSTM) was used to recognize the types of errors in verb forms. To maximize the utilization of textual context information, a bidirectional LSTM algorithm was employed. Simulation experiments were then conducted, and the algorithm was evaluated against the support vector machine (SVM) algorithm and the grammar rules-based algorithm. The bidirectional LSTM method demonstrated higher accuracy in recognizing the parts of speech of words and the types of verb form errors in the text. Additionally, the accuracy was more stable when faced with different types of verb form errors.

Application of deep learning in summer climate prediction over northwestern China based on CWRF model

This study analyzes the performance of the Climate–Weather Research and Forecasting (CWRF) model in predicting the summer temperature and precipitation in northwestern China (NWC) for the 1991–2021 period. It also examines the improvements in prediction resulting from the implementation of convolutional neural network (CNN) and long short-term memory (LSTM) downscaling methods. The results indicate that the CWRF model demonstrates reasonable ability in capturing the characteristics of climatological temperature and precipitation in NWC. Both the climatological temperature and precipitation predictions consistently demonstrate a systematic underestimation, revealing evident biases in regions characterized by complex terrain. In terms of interannual variation, the temperature prediction outperforms the precipitation prediction, whereas there is no significant difference in the temperature predictions for lead Months 1–3. However, uncertainties increase as the lead time is extended in precipitation prediction. Therefore, the combination of dynamical and statistical downscaling is employed to the summer temperature and precipitation prediction over NWC. It is shown both the CNN and LSTM downscaling methods can improve the prediction ability of the CWRF model for summer climatological temperature and precipitation. The LSTM method significantly reduces the root mean square error (RMSE) of precipitation and temperature predictions, indicating an improvement in predicting the spatial structure. At the interannual scale, the CNN method is less dependent on the lead time of prediction than the LSTM method is, and the interannual correlation coefficient of precipitation and temperature is greater than 0.1 compared with that of the raw CWRF model. These results provide valuable insights into understanding the prediction capabilities of the CWRF model in NWC and highlight the necessity of applying downscaling methods to the CWRF model to increase its prediction ability.

Study on the Fluctuating Load Characteristics of the Submerged Radial Gate in the High-Head Flood Discharge Outlet

The fluctuating pressure acting on the radial gate in the high-head flood discharge outlet is the main excitation source of flow-induced vibration. Therefore, this paper delves into the distribution characteristics of fluctuating pressure on the panel of the high-head submerged radial gate based on hydraulic model tests. Hydraulic tests were first conducted to obtain the distribution patterns of time-averaged pressure and the root mean square (RMS) of fluctuating pressure on the radial gate panel. Secondly, the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and HHT method was employed to identify the causes of the fluctuating pressure on the gate panel. Finally, the ICEEMDAN-SSA (the sparrow search algorithm)–LSTM (long short-term memory) method was utilized to achieve accurate prediction of the fluctuating pressure on the gate panel. The results show that the time-averaged pressure in the middle of the gate panel is higher than that at the top and near the bottom edge, which differs significantly from the static pressure distribution. The RMS of the fluctuating pressure near the bottom edge is higher than that in the middle and at the top. The fluctuating pressure acting on the gate panel in the time domain can be regarded as a stationary process. The fluctuating pressure on the gate panel is caused by the combined diffusion and random mixing of multi-scale vortices in the turbulent eddy structure. The ICEEMDAN-SSA-LSTM combined method significantly improves the prediction accuracy of fluctuating pressure on the gate panel compared to the LSTM and ICEEMDAN-LSTM methods.

Image analysis and LSTM methods for forecasting surficial displacements of a landslide triggered by snowfall and rainfall

AbstractLandslide-prone areas, predominantly located in mountainous regions with abundant rainfall, present unique challenges when subject to significant snowfall at high altitudes. Understanding the role of snow accumulation and melting, alongside rainfall and other environmental variables like temperature and humidity, is crucial for assessing landslide stability. To pursue this aim, the present study focuses first on the quantification of snow accumulated on a slope through a simple parameter obtained with image processing. Then, this parameter is included in a slope displacement prediction analysis carried out with long short-term memory (LSTM) neural network. By employing image processing algorithms and filtering out noise from white-shown rocks, the methodology evaluates the percentage of snow cover in RGB images. Subsequent LSTM forecasts of landslide displacement utilize 28-day historical data on rainfall, snow, and slope movements. The presented procedure is applied to the case of a deep-seated landslide in Italy, a site that in winter 2020–2021 experienced heavy snowfall, leading to significant snow accumulation on the slope. These episodes motivated a study aimed at forecasting the superficial displacements of this landslide, considering the presence of snow both at that time and in the following days, along with humidity and temperature. This approach indirectly incorporates snow accumulation and potential melting phenomena into the model. Although the subsequent winters were characterized by reduced snowfall, including this information in the LSTM model for the period characterized by snow on the slope demonstrated a dependency of the predictions on this parameter, thus suggesting that snow is indeed a significant factor in accelerating landslide movements. In this context, detecting snow and incorporating it into the predictive model emerges as a significant aspect for considering the effects of winter snowfall. The method aims to propose an innovative strategy that can be applied in the future to the study of the landslide analyzed in this paper during upcoming winters characterized by significant snowfall, as well as to other case studies of landslides at high altitudes that lack precise snow precipitation recording instruments.

Forecasting and unveiling the impeded factors of total export of Bangladesh using nonlinear autoregressive distributed lag and machine learning algorithms

Rising global oil prices are a major challenge for an emerging oil-importing nation such as Bangladesh. The majority of prior research on the economic effects of an oil price shock has concentrated on developed countries, with emerging economies receiving comparatively less attention. Bangladesh is vulnerable to price shocks due to its rising oil consumption over the past decade. This study aims to investigate how changes in oil prices would affect Bangladesh's total export earnings and to forecast the overall export volume. This study utilized a nonlinear autoregressive distributed lag (NARDL) approach to account for the asymmetric behavior of oil prices from 1991 to 2021. To assess the accuracy of predictions, the study employed the Prophet forecasting model and the Long Short-Term Memory (LSTM) method. Additionally, the symmetry test revealed a nonlinear relationship between export volume and oil price but a linear relationship between inflation and export volume. According to the NARDL assessment, both positive and negative oil shocks increase export earnings over the long run. The short run summary clarifies that both positive and negative changes in oil prices exert a significant negative effect on exports. Also, Inflation influences export earnings negatively in the short run but positively over the long term. Moreover, using machine learning methods, it was found that the LSTM method outperforms the prophet model in prediction performance with a low root mean square error (RMSE) of 1.88. Also, the analysis revealed policymakers that the export sector requires diversification to reduce its exposure to oil price shocks.

Predicting Energy Production in Renewable Energy Power Plants Using Deep Learning

It is very important to analyze and forecast energy production for investments in renewable energy resources. In this study, the energy production of wind and solar power plants, which are among the leading renewable energy sources, was estimated using deep learning. For a solar power plant, three different solar power plants with 1MW installed power were examined. Three-year energy production data of power plants were taken. These data were used with the deep learning method long short-term memory (LSTM) and seasonal autoregressive moving average (SARIMA). Results were obtained for each dataset; they were subjected to five different (MSE, RMSE, NMSE, MAE, and MAPE) error performance measurement systems. In the LSTM model, the highest accuracy rate was 81% and the lowest accuracy rate was 59%. In the SARIMA model, the highest accuracy rate was 66% and the lowest accuracy rate was 41%. As for wind energy, wind speeds in two different places were estimated. Wind speed data were taken from meteorological stations. Datasets were tested with MAPE, R2, and RMSE error performance measurement systems. LSTM, GRU, CNN-LSTM, CNN-RNN, LSTM-GRU, and CNN-GRU deep learning methods were used in this study. The CNN-GRU model achieved a maximum accuracy of 99.81% in wind energy forecasting.

Combining signal decomposition and deep learning model to predict noisy runoff coefficient

Predicting runoff coefficient (Rc), as an indicator of the catchment’s response to the rainfall-runoff process, remains a persistent challenge using different modelling techniques, especially in catchments with strong human manipulation. This study investigates the efficiency of the Long Short-Term Memory (LSTM) method in predicting Rc for the Rur catchment, in Germany. The period from 1961 to 2021 is considered, which is subject to human intervention and significant urbanization especially in the northern part of the catchment. An LSTM structure is defined by employing inputs at a monthly resolution including temperature, precipitation, soil water storage, and total evaporation with a look-back window of 1 to 6 months to model noisy Rc data of the study area. Two approaches using either undecomposed or decomposed Rc were employed in conjunction with the LSTM method, to mitigate the impact of noise associated with Rc. The results show that in the case of undecomposed Rc, the best performance of the LSTM structure was obtained with a 4-month look-back window, yielding Nash-Sutcliffe efficiency (NSE) of 0.55, 0.46, and 0.15 for training, validation, and test sets, respectively. These results highlight inadequate accuracy in accounting for the presence of noise in Rc. Therefore, in the second novel approach, we used maximal overlap discrete wavelet transform (MODWT) to decompose the Rc up to level 3 to reduce the complexity and distribute the noise effects across each level. The new approach showed high accuracy in modelling noisy data of Rc with NSE values of 0.97, 0.95, and 0.90 for training, validation, and test sets, respectively. The obtained results underscore the pivotal role of decomposition techniques in conjunction with LSTM to account for the presence of noise, especially in catchments with strong human manipulation.

An Approach for Future Droughts in Northwest Türkiye: SPI and LSTM Methods

Predetermining the risk of possible future droughts enables proactive measures to be taken in key areas such as agriculture, water management, and food security. Through these predictions, governments, non-governmental organizations, and farmers can develop water-saving strategies, encourage more efficient use of water, and minimize economic losses that may occur due to drought. Thus, future drought forecasts stand out as a strategic planning tool for the protection of natural resources. To achieve this aim, forecasted drought conditions for the next decade (2024–2034) at nine meteorological stations in the Sakarya basin, located northwest of Türkiye, are examined, using historical monthly precipitation data from 1991 to 2023. This study uses the Standardized Precipitation Index (SPI) and Long Short-Term Memory (LSTM) deep learning methods to investigate future meteorological droughts. The research confirms the compatibility and reliability of the LSTM method for forecasting meteorological droughts by comparing historical and forecasted SPI values’ correlograms and trends. In addition, drought maps are created to visually represent the spatial distribution of the most severe droughts expected in the coming years, and areas at risk of drought in the Sakarya Basin are determined. The study contributes to the limited literature on forward-looking drought forecasts in the Sakarya Basin and provides valuable information for long-term water resource planning and drought management in the region.

MIMO Signal Detection Based on IM-LSTMNet Model

Signal detection is crucial in multi-input multi-output orthogonal frequency division multiplexing (MIMO-OFDM) systems, yet classical detection methods often struggle with nonlinear issues in wireless channels. To handle this challenge, we propose a novel signal detection method for MIMO-OFDM system based on the fractional Fourier transform (FrFT), leveraging the robust time series processing capabilities of long short-term memory (LSTM) networks. Our innovative approach, termed IM-LSTMNet, integrates LSTM with convolutional neural networks (CNNs) and incorporates a Squeeze and Excitation Network to emphasize critical information, enhancing neural network performance. The proposed IM-LSTMNet is applied to the FrFT-based MIMO-OFDM system to improve signal detection performance. We compare the detection results of IM-LSTMNet with zero forcing (ZF), minimum mean square error (MMSE), simple LSTM neural network, and CNN–LSTM network by evaluating the bit error rate. Experimental results demonstrate that IM-LSTMNet outperforms ZF, MMSE, LSTM, and other methods, significantly enhancing system signal detection performance. This work offers a promising advancement in MIMO-OFDM signal detection, presenting a deep learning-based solution that effectively improves the system signal detection performance.

Extending battery life in CubeSats by charging current control utilizing a long short-term memory network for solar power predictions

Recently, there has been a surge in small satellites and CubeSats. A crucial factor limiting the duration of their missions is the lifespan of their batteries. Typically, batteries are charged immediately when there is sufficient power generated from the solar panels. However, this practice results in additional charging stress and degradation due to unnecessarily high current amplitudes. In this work, a distributed charging strategy based on solar power prediction is proposed to mitigate charging stress and thereby extend battery life, ensuring sufficient charging without jeopardizing spacecraft operation. The proposed method for power generation prediction relies on a Long Short-Term Memory (LSTM) network, trained on GOMX-4A satellite telemetry data. The proposed LSTM method performed an order of magnitude better, with a root mean square error (RMSE) of 0.2274 W, while a baseline prediction utilizing a Seasonal Auto-Regressive Moving Average has an RMSE of 1.2406 W. Using the predicted power generation from the LSTM method, the current is distributed using a proposed charging multiplier control, resulting in 72.0882% reduction in the median charging current. A direct possible impact on lithium-ion batteries was evaluated by employing an electrochemical model from the literature, confirming that the proposed strategy effectively reduces degradation caused by lithium plating. Moreover, the capacity fade in the example scenario at 25 °C was reduced by 0.0849%. The extent of degradation reduction will vary according to the required mission profile, the operational conditions, the specific chemistry, and the type of battery in use.

Chimp Optimization Algorithm with Deep Learning-Driven Fine-grained Emotion Recognition in Arabic Corpus

Recently, emotion analysis and classification of tweets have become a crucial area of research. The Arabic language had experienced difficulties with emotion classification on Twitter(X), needing preprocessing more than other languages. Emotion detection is a major challenge in Natural Language Processing (NLP), which allows machines to ascertain the emotions expressed in the text. The task includes recognizing and identifying human feelings such as fear, anger, sadness, and joy. The discovered sentiments and feelings expressed in tweets have gained much recognition in recent years. The Arab region has played a substantial role in international politics and the global economy needs to scrutinize the emotions and sentiments in the Arabic language. Lexicon-based and machine-learning techniques are two common models that address the problems of emotion classification. This study introduces a Chimp Optimization Algorithm with a Deep Learning-Driven Arabic Fine-grained Emotion Recognition (COADL-AFER) technique. The presented COADL-AFER technique mainly aims to detect several emotions in Arabic tweets. In addition to its academic significance, the COADL-AFER technique has practical applications in various fields, including enhancing applications of E-learning, aiding psychologists in recognising terrorist performance, improving product quality, and enhancing customer service. The COADL-AFER technique applies the long short-term memory (LSTM) model for emotion detection. Finally, the hyperparameter selection of the LSTM method can be accomplished by COA. The experimental validation of the COADL-AFER system, a crucial step in our research, is verified utilizing the Arabic tweets dataset. The simulation results stated the betterment of the COADL-AFER technique, further reinforcing the reliability of our research.

Deep learning‐based location prediction in VANET

AbstractIn recent years, Vehicular Ad‐hoc Network (VANET) has become an essential component of intelligent transportation systems that, along with the previous systems such as traffic condition, accident alert, automatic parking, and cruise control, use the communication of vehicle to vehicle and vehicle to the roadside unit to facilitate road transportation. Several challenges hinder efforts to improve traffic conditions and reduce traffic fatalities through VANET. A critical challenge is achieving highly accurate and reliable vehicle localization within the VANET. Additionally, the frequent unavailability of Global Positioning System (GPS), particularly in tunnels and parking lots, presents another significant obstacle. Traditional methods like Dead Reckoning offer low accuracy and reliability due to accumulating errors. Similarly, GPS positioning, map matching with mobile phone location services, and other existing solutions struggle with accuracy and economic feasibility. In this article, two Kalman filter approaches are used based on signal statistical information and the other learning‐based networks, including traditional neural network, deep neural network and LSTM (long short‐term memory) to locate the car. The prediction error of car position with root mean square measures. The squared error and distance prediction error are evaluated. It is shown that in terms of prediction time and processing time of vehicle localization, all the vehicle localization methods are efficient in terms of response time for localization, and Kalman filter methods, traditional neural network and deep neural network are faster than LSTM method. Also, in terms of localization error, Kalman filter works better than learning‐based methods, and in learning‐based methods, both deep neural network and LSTM methods perform better than traditional neural network in terms of localization error.

Long Short‐Term Memory‐Based Multi‐Robot Trajectory Planning: Learn from MPCC and Make It Better

The current trajectory planning methods for multi‐robot systems face challenges due to high computational burden and inadequate adaptability in complex constrained environments, obstructing efficiency improvements in production and logistics. This article presents an innovative solution by integrating model predictive contouring control (MPCC) and long short‐term memory (LSTM) networks for real‐time trajectory planning of multiple mobile robots. Based on the datasets generated by MPCC, a customized LSTM network is constructed to learn the collaborative planning behavior from these datasets offline, subsequently producing smooth and efficient trajectories online with a low computational burden. Moreover, a hybrid control scheme, incorporating a lidar‐based safety evaluator, avoids unexpected collision risks by switching to MPCC when necessary, ensuring the overall safety and reliability of the multi‐robot system. The proposed hybrid LSTM method is implemented and tested in the robot operating system (ROS) within diverse constrained scenarios. Experimental results demonstrate that the hybrid LSTM method achieves ≈6% enhancements in trajectory productivity and a reduced computational burden of roughly 75% compared to MPCC, thereby providing a promising solution for local multi‐robot trajectory planning in logistics transportation tasks.

Research on Abnormity Detection based on Big Data Analysis of Smart Meter

There are over five hundred million smart meters in China. The current standard for the use of smart meters is physical inspection of meter dismantling within 8 years. The method leads to many issues including high cost of testing, low sampling rate, unknown meter status huge waste of resources etc. Searching for non- dismantling meter detection solution is necessary. Although the smart grid can be managed much better with the increasing use of smart meters, the current standard brings many issues. To solve the problems like a huge waste of resources, detecting inaccurate smart meters and targeting them for replacement must be done. Based on the big data analysis of smart meters, abnormity can be predicted and diagnosed. For this purpose, the method is based on Long Short-Term Memory (LSTM) and a modified Convolutional Neural Network (CNN) to predict electricity usage patterns based on historical data. In this process, LSTM is used to fit the trend prediction of smart meters, and recurrence plot is used to detect the abnormality of smart meter. Both LSTM and recurrence plot method is the first time to be used in smart meter detection. In actual research, many methods including Elastic Net, GBR, LSTM and etc. are used to predict the trend of smart meters. Through the best method LSTM, the accurate rate of the trend prediction of smart meters can arrive at about 96%. Similarly many methods are used to detect the abnormality of smart meters. In single-input modeling, there are sequence-input and matrix-input methods. In dual-input modeling, there are TS-RP CNN, VGG+BiLSTM, ResNet50+1D-CNN and ResNet50+BiLSTM etc. Eventually based on the most successful method recurrence plot, the abnormity testing and failure recognition can be got at 82% roughly. This is the breakthrough in the electricity power domain. With the success of the solution, the service time of a normal meter can be prolonged by abnormity detection. This will lead to saving a lot of resources on smart meter applications.

DACLnet: A Dual-Attention-Mechanism CNN-LSTM Network for the Accurate Prediction of Nonlinear InSAR Deformation

Nonlinear deformation is a dynamically changing pattern of multiple surface deformations caused by groundwater overexploitation, underground coal mining, landslides, urban construction, etc., which are often accompanied by severe damage to surface structures or lead to major geological disasters; therefore, the high-precision monitoring and prediction of nonlinear surface deformation is significant. Traditional deep learning methods encounter challenges such as long-term dependencies or difficulty capturing complex spatiotemporal patterns when predicting nonlinear deformations. In this study, we developed a dual-attention-mechanism CNN-LSTM network model (DACLnet) to monitor and accurately predict nonlinear surface deformations precisely. Using advanced time series InSAR results as input, the DACLnet integrates the spatial feature extraction capability of a convolutional neural network (CNN), the advantages of the time series learning of a long short-term memory (LSTM) network, and the enhanced focusing effect of the dual-attention mechanism on crucial information, significantly improving the prediction accuracy of nonlinear surface deformations. The groundwater overexploitation area of the Turpan Basin, China, is selected to test the nonlinear deformation prediction effect of the proposed DACLnet. The results demonstrate that the DACLnet accurately captures developmental trends in historical surface deformations and effectively predicts surface deformations for the next two months in the study area. Compared to traditional LSTM and CNN-LSTM methods, the root mean square error (RMSE) of the DACLnet improved by 85.09% and 68.57%, respectively. These research results can provide crucial technical support for the early warning and prevention of geological disasters and can serve as an effective alternative tool for short-term ground subsidence prediction in areas lacking hydrogeological and other related data.

Forecasting the Stock Price of PT Astra International Using the LSTM Method

Stocks are one of the long-term investment options and represent ownership in a company that can be acquired through buying and selling. Investment carries both the profit potential and the risks that investors must face when providing their capital to companies. Accurate stock price forecasts are very important because they provide an estimate of risk. This research aims to forecast the stock price of PT Astra International Tbk (ASII.JK) using a Long Short-Term Memory (LSTM) method. Data set closing stock prices were taken from January 2, 2015, to December 30, 2020, with a total observation of 1506. This data set is divided into 80% for training and 20% for training. The forecasting results show that the best performances have MSE, MSE, MAE and MAPE are 151.910, 23076.561, 118.128, and 2.3%, respectively. The model has a batch size of 4 and epochs of 50. This research recommends that other parties consider this method when they need to manage their investment risk in stocks.