Traditional Long Short-term Memory Research Articles

Research on error detection in English translation texts using machine learning algorithms

This paper provides a concise overview of a grammatical error correction algorithm based on the encoder-decoder structure. The traditional unidirectional long short-term memory (LSTM) in the encoder was transformed into a bidirectional LSTM. Subsequently, the grammatical error correction algorithm was simulated and experimented with. In the experiments, it was compared with two other error correction algorithms: one based on the LSTM classification model and the other on the traditional unidirectional LSTM translation model. The results indicated that the three error correction algorithms exhibited little difference in detection performance when faced with distinct corpus databases. Furthermore, when dealing with the same corpus database, the bidirectional LSTM algorithm demonstrated the most robust detection performance, followed by the one based on the traditional unidirectional LSTM translation model, and lastly, the one based on the LSTM classification model performed the least effectively.

Dynamic Perception-Based Vehicle Trajectory Prediction Using a Memory-Enhanced Spatio-Temporal Graph Network

In the realm of intelligent transportation systems, accurately predicting vehicle trajectories is paramount for enhancing road safety and optimizing traffic flow management. Addressing the impacts of complex traffic environments and efficiently modeling the diverse behaviors of vehicles are the key challenges at present. To achieve precise prediction of vehicle trajectories, it is essential to fully consider the dynamic changes in traffic conditions and the long-term dependencies of time-series data. In response to these challenges, we propose the Memory-Enhanced Spatio-Temporal Graph Network (MESTGN), an innovative model that integrates a Spatio-Temporal Graph Convolutional Network (STGCN) with an attention-enhanced Long Short-Term Memory (LSTM)-based sequence to sequence (Seq2Seq) encoder–decoder structure. MESTGN utilizes STGCN to capture the complex spatial dependencies between vehicles and reflects the interactions within the traffic network through road traffic data and network topology, which significantly influences trajectory prediction. Additionally, the model focuses on historical vehicle trajectory data points using an attention-weighted mechanism under a traditional LSTM prediction architecture, calculating the importance of critical trajectory points. Finally, our experiments conducted on the urban traffic dataset ApolloSpace validate the effectiveness of our proposed model. We demonstrate that MESTGN shows a significant performance improvement in vehicle trajectory prediction compared with existing mainstream models, thereby confirming its increased prediction accuracy.

Adaptive fuzzy energy management strategy for range‐extended electric vehicles integrated with deep learning

AbstractA novel framework for adaptive energy management, rooted in deep learning principles, is proposed to minimize fuel consumption in extended‐range electric vehicles amidst intricate driving scenarios. This innovative approach integrates a long short‐term memory (LSTM) network for pattern recognition across three driving patterns and an adaptive fuzzy controller. To mitigate the impact of poor hyperparameter selection on recognition accuracy, Gray Wolf Optimization is employed to optimize the hidden layer nodes, training times, and learning rate of the LSTM. Simultaneously, a genetic algorithm is utilized to optimize the vertex coordinates of the fuzzy control membership function, enabling the adaptive adjustment of parameters in the fuzzy energy management strategy. The condition recognition model accurately identifies the vehicle's driving status and seamlessly transitions to an energy management strategy tailored to the present conditions. This ensures optimal operation, enhancing overall fuel efficiency and performance. The simulation results robustly validate the efficacy of this approach: the GWO‐LSTM network achieves an impressive 97.7% accuracy in recognizing working conditions, surpassing the 88.9% accuracy of the traditional LSTM network. Furthermore, the fuel consumption reduction achieved by the adaptive fuzzy energy management strategy amounts to 11.9% compared with the conventional fuzzy energy management approach. This outcome underscores the tangible enhancement in vehicle fuel economy resulting from the seamless integration of deep learning techniques.

A Spiking LSTM Accelerator for Automatic Speech Recognition Application Based on FPGA

Long Short-Term Memory (LSTM) finds extensive application in sequential learning tasks, notably in speech recognition. However, existing accelerators tailored for traditional LSTM networks grapple with high power consumption, primarily due to the intensive matrix–vector multiplication operations inherent to LSTM networks. In contrast, the spiking LSTM network has been designed to avoid these multiplication operations by replacing multiplication and nonlinear functions with addition and comparison. In this paper, we present an FPGA-based accelerator specifically designed for spiking LSTM networks. Firstly, we employ a low-cost circuit in the LSTM gate to significantly reduce power consumption and hardware cost. Secondly, we propose a serial–parallel processing architecture along with hardware implementation to reduce inference latency. Thirdly, we quantize and efficiently deploy the synapses of the spiking LSTM network. The power consumption of the accelerator implemented on Artix-7 and Zynq-7000 is only about 1.1 W and 0.84 W, respectively, when performing the inference for speech recognition with the Free Spoken Digit Dataset (FSDD). Additionally, the energy consumed per inference is remarkably efficient, with values of 87 µJ and 66 µJ, respectively. In comparison with dedicated accelerators designed for traditional LSTM networks, our spiking LSTM accelerator achieves a remarkable reduction in power consumption, amounting to orders of magnitude.

A Data-Driven Prediction Method for Proton Exchange Membrane Fuel Cell Degradation

This paper proposes a long short-term memory (LSTM) network to predict the power degradation of proton exchange membrane fuel cells (PEMFCs), and in order to promote the performance of the LSTM network, the ant colony algorithm (ACO) is introduced to optimize the hyperparameters of the LSTM network. First, the degradation mechanism of PEMFCs is analyzed. Second, the ACO algorithm is used to set the learning rate and dropout probability of the LSTM network combined with partial aging data, which can show the characteristics of the dataset. After that, the aging prediction model is built by using the LSTM and ACO (ACO-LSTM) method. Moreover, the convergence of the method is verified with previous studies. Finally, the fuel cell aging data provided by the Xiangyang Da’an Automotive Testing Center are used for verification. The results show that, compared with the traditional LSTM network, ACO-LSTM can predict the aging process of PEMFCs more accurately, and its prediction accuracy is improved by about 35%, especially when the training data are less. At the same time, the performance of the model trained by ACO-LSTM is also excellent under other operating conditions of the same fuel cell, and it has strong versatility.

Enhancing data-driven soil moisture modeling with physically-guided LSTM networks

In recent years, deep learning methods have shown significant potential in soil moisture modeling. However, a prominent limitation of deep learning approaches has been the absence of physical mechanisms. To address this challenge, this study introduces two novel loss functions designed around physical mechanisms to guide deep learning models in capturing physical information within the data. These two loss functions are crafted to leverage the monotonic relationships between surface water variables and shallow soil moisture as well as deep soil water. Based on these physically-guided loss functions, two physically-guided Long Short-Term Memory (LSTM) networks, denoted as PHY-LSTM and PHYs-LSTM, are proposed. These networks are trained on the global ERA5-Land dataset, and the results indicate a notable performance improvement over traditional LSTM models. When used for global soil moisture forecasting for the upcoming day, PHY-LSTM and PHYs-LSTM models exhibit closely comparable results. In comparison to conventional data-driven LSTM models, both models display a substantial enhancement in various evaluation metrics. Specifically, PHYs-LSTM exhibits improvements in several key performance indicators: an increase of 13.6% in Kling-Gupta Efficiency (KGE), a 20.7% increase in Coefficient of Determination (R2), an 8.2% reduction in Root Mean Square Error (RMSE), and a 4.4% increase in correlation coefficient (R). PHY-LSTM also demonstrates improvements, with a 14.8% increase in KGE, a 19.6% increase in R2, an 8.2% reduction in RMSE, and a 4.4% increase in R. Additionally, both models exhibit enhanced physical consistency over a wide geographical area. Experimental results strongly emphasize that the incorporation of physical mechanisms can significantly bolster the predictive capabilities of data-driven soil moisture models.

Residual LSTM-based short duration forecasting of polarization current for effective assessment of transformers insulation

The empirical application of polarization and depolarization current (PDC) measurement of transformers facilitates the extraction of critical insulation-sensitive parameters. This technique, rooted in time-domain dielectric response analysis, forms the bedrock for parameterization and insulation modeling. However, the inherently time-consuming nature of polarization current measurements renders them susceptible to data corruption. This article explores deep-learning-based short-duration techniques for forecasting polarization current to address this limitation. By incorporating spatial shortcuts, the residual long short-term memory (LSTM) network facilitates the seamless propagation of spatial and temporal gradients. Furthermore, the relative forecasting assessment of the proposed residual LSTM model’s performance is made against traditional LSTM, attention LSTM, gated recurrent units (GRU), and convolutional neural network (CNN) models. Thus, optimal model selection strategies are evaluated based on their capability to capture extended dependencies and short-term information present in the data. In addition, the Monte Carlo dropout prediction is employed to estimate uncertainty in polarization current forecasts. The findings demonstrate that the proposed residual LSTM network model for polarization current forecasting yields the lowest error metrics and maintains prediction consistency over the testing duration. Thus, the proposed approach significantly reduces PDC measurement time, providing an effective means to develop proactive maintenance strategies for evaluating the insulation condition of transformers.

Forecasting carbon price in China unified carbon market using a novel hybrid method with three-stage algorithm and long short-term memory neural networks

The forecasting of carbon prices is critical to understand China unified carbon market dynamics. In this study, in order to reduce the noise and modal aliasing of carbon price sequence, a novel hybrid forecasting model is presented to predict carbon price in China unified carbon market. First, a three-stage algorithm that combines the improved complete ensemble empirical mode decomposition with adaptive noise (iCEEMDAN), variational mode decomposition (VMD), and reconstruction of fine-to-coarse (REC) data is proposed. Time series data are decomposed and reconstructed by this three-stage algorithm into three subsequences. Secondly, the model which combines the long short-term memory (LSTM) and convolutional neural networks (CNN) is utilized for prediction. Finally, the empirical results indicate that the prediction accuracy of this hybrid forecasting model is improved around 65 % higher than that of traditional LSTM. The proposed hybrid forecasting model can help the enterprises to make decisions facing non-linear, non-stationary and irregular carbon price more effectively. It is conducive to the implementation of energy conservation and emission reduction policies for the governments.

Research on early warning model of electric submersible pump wells failure based on the fusion of physical constraints and data-driven approach

At present, there are too few characteristic parameters for early identification of electric submersible pump (ESP) wells failures. In addition, existing predictive models rely only on data-driven techniques, which do not provide a comprehensive understanding of the intrinsic mechanisms behind the occurrence of failures. This article presents the development of a health index calculation approach for evaluating the operational status of the ESP wells. The wellbore energy conservation equation and the health index calculation formula were employed to develop a physical constraints (PC) for the loss function in the network model of Long Short-Term Memory (LSTM). This constraint was then utilized to construct the PC-LSTM ESP health warning model. The study examines the health index trends associated with three types of faults: ESP clogging, sand production in oil wells, and reservoir pressure rise. The results indicate that the PC-LSTM network structure exhibits faster convergence during training. In relation to the accuracy of prediction, PC-LSTM demonstrates a notable enhancement. Specifically, when the ESP clogging fault, the traditional LSTM achieves a mean relative error (MRE) of 211.15%, whereas the PC-LSTM achieves a reduced MRE of 12.74%. Similarly, for sand production in oil wells, the traditional LSTM yields an MRE of 19.07%, while the PC-LSTM achieves a reduced MRE of 9.62%. Lastly, in the scenario of reservoir pressure rise, the traditional LSTM exhibits an MRE of 41.07%, whereas the PC-LSTM achieves a reduced MRE of 12.74%. In the meantime, the model demonstrates a high level of accuracy in capturing the pre- and post-trends of the health status of the ESP wells. This improved prediction accuracy and interpretability of the underlying mechanisms serve as valuable tools for analyzing the lift performance of ESP wells and providing early warning signals for potential failures.

Machine Learning Models: A Study of English Essay Text Content Feature Extraction and Automatic Scoring

Accurate automatic scoring of English essay is beneficial for both teachers and students in English teaching. This paper briefly introduced an XGBoost-based automated scoring algorithm for English essay. To improve the accuracy of the algorithm, a long short-term memory (LSTM) semantic model was introduced to extract semantic scoring features from essays. Finally, the improved XGBoost algorithm was compared with the traditional XGBoost and LSTM algorithms in a simulation experiment using five types of essay prompts. The results indicate that the improved XGBoost algorithm has the best performance for automatic scoring of English essay and also requires the shortest scoring time.

Ultrasonic lamination defects detection of carbon fiber composite plates based on multilevel LSTM

During the production of carbon fiber composites (CFC), various forming methods and complex processes can introduce different types of defects, with lamination defects being a major concern. In this paper, we propose a multilevel Long Short-Term Memory (LSTM) neural network combined with ultrasonic detection to identify the lamination defects in carbon fiber composites. Unlike conventional ultrasonic detection that requires multiple sets of probes, this method only employs a one-to-one transmission and reception mode. The COMSOL-Multiphysics finite element software is utilized to simulate the ultrasonic transmission and generate the necessary ultrasonic data. By incorporating multiple levels of learning, the accuracy and convergence of the traditional LSTM can be obviously enhanced. This approach uses ultrasound waveform data collected from a single set of probes to predict the locations and sizes of lamination defects. Based on fewer than 10,000 datasets where each dataset represents a waveform, the numerical results demonstrate a prediction accuracy of over 90% for defect position and size. Moreover, the multilevel LSTM method exhibits convergence, and incorporating more data can further promote the prediction accuracy. This method offers a time-saving, labor-saving, and cost-effective solution for detecting and analyzing defects in CFC.

Low-complexity characterized-long-short-term-memory-aided channel modeling for optical fiber communications

In this work, a low-complexity data-driven characterized-long-short-term-memory (C-LSTM)-aided channel modeling technique is proposed for optical single-mode fiber (SMF) communications. To fully utilize the sequence correlation learning ability of traditional long short-term memory (LSTM) networks and solve the gradient explosion problem, the feature information is introduced into the traditional LSTM input layer to better characterize the intersymbol interference caused by dispersion in SMF modeling. The simulation results show that the proposed C-LSTM can effectively alleviate the gradient explosion problem with a stable and ultimately lower mean square error (MSE) than traditional LSTM. Compared with the split-step Fourier method (SSFM) and the conditional generative adversarial network (CGAN), the proposed C-LSTM has superior computational complexity. Moreover, due to the sequence correlation learning ability inherent to C-LSTM, coupled with the flexibility of feature information selection, the proposed C-LSTM-aided modeling technique has a higher modeling accuracy than traditional LSTM. Moreover, the C-LSTM-aided modeling technique can be effectively extended to other channel modeling applications with strong sequence correlations.

Identification of wheat plant disease using hybrid model of pre-processing with CNN

Diagnosis is given top priority in terms of farm resource allocation, because it directly affects the GDP of the country. Crop analysis at an early stage is important for verifying the efficient crop output. Computer vision has a number of intriguing and demanding concerns, including disease detection. After China, India is the world’s second-largest creator of wheat. However, there exist algorithms that can accurately identify the most prevalent illnesses of wheat leaves. To help farmers keep track on a large area of wheat plantation, leaf image and data processing techniques have recently been deployed extensively and in pricey systems. In this study, a hybrid pre-processing practice is used to remove undesired distortions while simultaneously enhancing the images. Fuzzy C-Means (FCM) is used to segment the affected areas from the pre-processed images. The data is then incorporated into a disease classification model using a Convolutional Neural Network (CNN). It was tested using Kaggle data and several metrics to see how efficient the suggested approach was. This study demonstrates that the traditional Long-Short Term Memory (LSTM) technique achieved 91.94% accuracy on the input images, but the hybrid pre-processing model with CNN achieved 95.06 percent accuracy.

Automatic graph construction and Exploring different types of LSTMs for Asian Hindi languages for Medical review Sentiment Analysis

Sentiment Analysis (SA) of medical reviews is crucial for improving healthcare outcomes. However, analyzing sentiment in low-resource languages such as Asian Hindi presents significant challenges. In this study, we propose an automatic graph construction approach to extract relevant features from medical reviews in Asian Hindi languages. We explore different types of Long Short-Term Memory (LSTMs), including traditional LSTMs, bidirectional LSTMs, and attention-based LSTMs, to classify the sentiment of medical reviews. Our proposed approach uses attention-based LSTM architecture and pre-trained Word2Vec embeddings to achieve high accuracy. We compare the proposed approach with existing models using various evaluation metrics, including accuracy, precision, recall, and F1-score. The results demonstrate that our proposed approach outperforms all existing models in terms of accuracy, achieving an accuracy score of 81%. These findings could have implications for improving healthcare outcomes by enabling better monitoring of patient feedback and identifying areas for improvement in medical services.

Optimizing Long Short-Term Memory Network for Air Pollution Prediction Using a Novel Binary Chimp Optimization Algorithm

Elevated levels of fine particulate matter (PM2.5) in the atmosphere present substantial risks to human health and welfare. The accurate assessment of PM2.5 concentrations plays a pivotal role in facilitating prompt responses by pertinent regulatory bodies to mitigate air pollution. Additionally, it furnishes indispensable information for epidemiological studies concentrating on PM2.5 exposure. In recent years, predictive models based on deep learning (DL) have offered promise in improving the accuracy and efficiency of air quality forecasts when compared to other approaches. Long short-term memory (LSTM) networks have proven to be effective in time series forecasting tasks, including air pollution prediction. However, optimizing LSTM models for enhanced accuracy and efficiency remains an ongoing research area. In this paper, we propose a novel approach that integrates the novel binary chimp optimization algorithm (BChOA) with LSTM networks to optimize air pollution prediction models. The proposed BChOA, inspired by the social behavior of chimpanzees, provides a powerful optimization technique to fine-tune the LSTM architecture and optimize its parameters. The evaluation of the results is performed using cross-validation methods such as the coefficient of determination (R2), accuracy, the root mean square error (RMSE), and receiver operating characteristic (ROC) curve. Additionally, the performance of the BChOA-LSTM model is compared against eight DL architectures. Experimental evaluations using real-world air pollution data demonstrate the superior performance of the proposed BChOA-based LSTM model compared to traditional LSTM models and other optimization algorithms. The BChOA-LSTM model achieved the highest accuracy of 96.41% on the validation datasets, making it the most successful approach. The results show that the BChOA-LSTM architecture performs better than the other architectures in terms of the R2 convergence curve, RMSE, and accuracy.

Predicting Multiple Numerical Solutions to the Duffing Equation Using Machine Learning

This study addresses the problem of predicting convergence outcomes in the Duffing equation, a nonlinear second-order differential equation. The Duffing equation exhibits intriguing behavior in both undamped free vibration and forced vibration with damping, making it a subject of significant interest. In undamped free vibration, the convergence result oscillates randomly between 1 and −1, contingent upon initial conditions. For forced vibration with damping, multiple variables, including initial conditions and external forces, influence the vibration patterns, leading to diverse outcomes. To tackle this complex problem, we employ the fourth-order Runge–Kutta method to gather convergence results for both scenarios. Our approach leverages machine learning techniques, specifically the Long Short-Term Memory (LSTM) model and the LSTM-Neural Network (LSTM-NN) hybrid model. The LSTM-NN model, featuring additional hidden layers of neurons, offers enhanced predictive capabilities, achieving an impressive 98% accuracy on binary datasets. However, when predicting multiple solutions, the traditional LSTM method excels. The research encompasses three critical stages: data preprocessing, model training, and verification. Our findings demonstrate that while the LSTM-NN model performs exceptionally well in predicting binary outcomes, the LSTM model surpasses it in predicting multiple solutions.

Stock Market Forecasting Based on Spatiotemporal Deep Learning.

This study introduces the Spacetimeformer model, a novel approach for predicting stock prices, leveraging the Transformer architecture with a time-space mechanism to capture both spatial and temporal interactions among stocks. Traditional Long-Short Term Memory (LSTM) and recent Transformer models lack the ability to directly incorporate spatial information, making the Spacetimeformer model a valuable addition to stock price prediction. This article uses the ten minute stock prices of the constituent stocks of the Taiwan 50 Index and the intraday data of individual stock on the Taiwan Stock Exchange. By training the Timespaceformer model with multi-time-step stock price data, we can predict the stock prices at every ten minute interval within the next hour. Finally, we also compare the prediction results with LSTM and Transformer models that only consider temporal relationships. The research demonstrates that the Spacetimeformer model consistently captures essential trend changes and provides stable predictions in stock price forecasting. This article proposes a Spacetimeformer model combined with daily moving windows. This method has superior performance in stock price prediction and also demonstrates the significance and value of the space-time mechanism for prediction. We recommend that people who want to predict stock prices or other financial instruments try our proposed method to obtain a better return on investment.

Remaining useful life prediction method combining the life variation laws of aero-turbofan engine and auto-expandable cascaded LSTM model

The real-time status monitoring and health management of aero-turbofan engines (ATEs) can effectively reduce the risk of engine failure and ensure aircraft flight safety. Accurate prediction of the remaining useful life (RUL) of ATE is a vital tool for effectively monitoring the engine operating condition, in which long-short term memory (LSTM) networks are often applied to RUL prediction. However, because of the complex mechanical structure and operation mode of the aero-engine, the prediction accuracy of the LSTM network is not enough to meet the actual demand. This paper proposes an auto-expandable cascaded long-short term memory (ACLSTM) prediction model that incorporates the lifetime variation laws of ATE, which is mainly applied for the degradation assessment of ATEs and the accurate prediction of RUL. The ACLSTM model adopts the network structure of multiple LSTM modules connected step by step to continuously set the prediction error of the previous module as the training outputs of the latter module. This data processing method transforms the prediction process of the original data into that of the output error, effectively reducing the prediction error and improving the prediction effect. In addition, to further improve the prediction accuracy, this paper comprehensively proposes several empirical formulas for further correction of the prediction effect obtained by the ACLSTM model. In the experimental part, the prediction effectiveness of the proposed method is tested based on four subsets of the C-MAPSS dataset published by the National Aeronautics and Space Administration. The experimental results on the four datasets show that the root mean square error (RMSE) of the ACLSTM prediction model decreases by 95.44% on average compared to the traditional LSTM network. In addition, the RMSE of the model decreases by 96.48% on average after incorporating the empirical formula. The proposed method has the lowest RMSE compared to other methods with the highest prediction accuracy. The experiments thoroughly verify that the ACLSTM model and the proposed empirical formula are feasible and effective for improving the prediction accuracy of the RUL of ATE.

Water Quality Prediction Based on the KF-LSTM Encoder-Decoder Network: A Case Study with Missing Data Collection

This paper focuses on water quality prediction in the presence of a large number of missing values in water quality monitoring data. Current water quality monitoring data mostly come from different monitoring stations in different water bodies. As the duration of water quality monitoring increases, the complexity of water quality data also increases, and missing data is a common and difficult to avoid problem in water quality monitoring. In order to fully exploit the valuable features of the monitored data and improve the accuracy of water quality prediction models, we propose a long short-term memory (LSTM) encoder-decoder model that combines a Kalman filter (KF) with an attention mechanism. The Kalman filter in the model can quickly complete the reconstruction and pre-processing of hydrological data. The attention mechanism is added between the decoder and the encoder to solve the problem that traditional recursive neural network models lose long-range information and fully exploit the interaction information among high-dimensional covariate data. Using original data from the Haimen Bay water quality monitoring station in the Lianjiang River Basin for analysis, we trained and tested our model using detection data from 1 January 2019 to 30 June 2020 to predict future water quality. The results show that compared with traditional LSTM models, KF-LSTM models reduce the average absolute error (MAE) by 10%, the mean square error (MSE) by 21.2%, the root mean square error (RMSE) by 13.2%, while increasing the coefficient of determination (R2) by 4.5%. This model is more suitable for situations where there are many missing values in water quality data, while providing new solutions for real-time management of urban aquatic environments.

Optimal Postprocessing Strategies With LSTM for Global Streamflow Prediction in Ungauged Basins

AbstractStreamflow prediction in ungauged basins (PUB) is challenging, and Long Short‐Term Memory (LSTM) is widely used to for such predictions, owing to its excellent migration performance. Traditional LSTM forced by meteorological data and catchment attribute data barely highlight the optimum data integration strategy for LSTM and its migration from data‐rich basins to ungauged ones. In this study, we experimented with 1,897 global catchments and found that LSTM‐corrected Global Hydrological Models (GHMs) outperformed uncorrected GHMs, improving the median Nash‐Sutcliff efficiency (NSE) from 0.03 to 0.66. Notably, there was a large gap between traditional LSTM modeling in ungauged basins and autoregressive modeling in data‐rich basins, and GHM‐forced LSTM were an effective way to close this gap in ungauged basins. The spatial heterogeneity of the performance of GHM‐forced LSTM was mainly influenced by three metrics (dryness, the leaf area index and latitude), which described the hydrological similarity among catchments. Weaker hydrological similarity among continental catchments results in larger variability in GHM‐forced LSTM, with the best performance in Siberia (NSE, 0.54) and the worst in North America (NSE, 0.10). However, the migration performance of GHM‐forced LSTM was significantly improved (NSE, 0.63) in ungauged basins when hydrological similarity was considered. This study stressed the advantages of GHM‐forced LSTM and due significance should be attached to hydrological similarities among catchments to improve hydrological prediction in ungauged catchments.