Back Propagation Neural Network Model Research Articles

Quantitative evaluation of surface crack depth on notched bars with laser-infrared detection technology

ABSTRACT To achieve non-destructive detection of crack depth in the process of notching and cracking of metal bars in low-stress cropping, a quantitative detection method for crack depth of notched bars based on infrared thermography technology under laser excitation is proposed in this paper. Combined with physical experiments, a simulation model of the temperature distribution of the laser-excited bar is established for efficient data acquisition, and the temperature curves of the bar surface under laser excitation are analysed from the perspective of space and time. On this basis, the study selects the feature parameters of the three types of defects on the surface of the metal bar, namely notch, surface crack and crack of notch bottom. A backpropagation (BP) neural network model is established for crack depth by dividing the crack into two types of a notch with crack and unnotched crack, and compared with other common prediction models. The results show that the selected features can accurately characterise the cracks in this BP neural network model, and the detected error in crack depth assessment is less than 3%. Performance metrics are established to evaluate the model, which has good reliability under different noises.

A data-driven state identification method for intelligent control of the joint station export system

As a necessary part of intelligent control of a joint station, the automatic identification of abnormal conditions and automatic adjustment of operation schemes need to judge the running state of the system. In this paper, a combination of Particle Swarm Optimization (PSO) and Gray Wolf Optimizer (GWO) is proposed to optimize the Backpropagation Neural Network (BP) model (PSO-GWO-BP) and a pressure drop prediction model for the joint station export system is established using PSO-GWO-BP. Compared with the traditional hydraulic calculation modified (THCM) models and other machine learning algorithms, the PSO-GWO-BP model has significant advantages in prediction accuracy. Based on the PSO-GWO-BP pressure drop prediction model, the determination method of state identification threshold is established, and a state identification method based on dynamic threshold is proposed, which realizes the intelligent identification of the system operation state by automatically adjusting the threshold. Through the analysis of the production and operation data of the joint station, the abnormal working conditions are successfully identified, and the effectiveness and accuracy of the method are verified. This method not only enhances the ability to discriminate abnormal working conditions but also adaptively adjusts the operation scheme, which effectively improves the intelligence level of the joint station export system.

A direct conversion model from ZTD to PWV based on the random forest

Abstract Precipitable Water Vapor (PWV) is crucial for weather forecasting and climate change research. However, accurate PWV estimation is challenging, especially in the absence of measured meteorological data. In this study, we develop a conversion model based on the random forest algorithm, called RPWV, which can directly derive PWV from zenith total delay (ZTD) without measured meteorological data. The results indicate that the RPWV model demonstrates high accuracy and reliability for PWV retrieval across North America. Specifically, using global navigation satellite system (GNSS) PWV as a reference, the bias and root mean square (RMS) values for RPWV are 0.01 mm and 1.87 mm, respectively. Moreover, compared with the conventional linear model and backpropagation neural network model, the accuracy of the RPWV is improved by 81.3% and 13.4%, respectively. In contrast to radiosonde (RS) PWV, the bias and RMS values of the RPWV are 1.85 mm and 3.40 mm, respectively. This model provides a straightforward and efficient method for estimating PWV and has potential for weather forecasting and climate research in environments where meteorological data is scarce.

Assessment of Mango Canopy Water Content Through the Fusion of Multispectral Unmanned Aerial Vehicle (UAV) and Sentinel-2 Remote Sensing Data

This study proposes an Additive Wavelet Transform (AWT)-based method to fuse Multispectral UAV (MS UAV, 5 cm resolution) and Sentinel-2 satellite imagery (10–20 m resolution), generating 5 cm resolution fused images with a focus on near-infrared and shortwave infrared bands to enhance the accuracy of mango canopy water content monitoring. The fused Sentinel-2 and MS UAV data were validated and calibrated using field-collected hyperspectral data to construct vegetation indices, which were then used with five machine learning (ML) models to estimate Fuel Moisture Content (FMC), Equivalent Water Thickness (EWT), and canopy water content (CWC). The results indicate that the addition of fused Sentinel-2 data significantly improved the estimation accuracy of all parameters compared to using MS UAV data alone, with the Genetic Algorithm Backpropagation Neural Network (GABP) model performing best (R2 = 0.745, 0.859, and 0.702 for FMC, EWT, and CWC, respectively), achieving R2 improvements of 0.066, 0.179, and 0.210. Slope, canopy coverage, and human activities were identified as key factors influencing the spatial variability of FMC, EWT, and CWC, with CWC being the most sensitive to environmental changes, providing a reliable representation of mango canopy water status.

Multi-dimensional failure risk load prediction of electric motor based on physical model and data-driven approach

Dynamic prediction of failure risk loads is a critical prerequisite for system damage monitoring and service life evaluation. As the failure mechanism of electric vehicle drive motors under multi-source load excitations is complex, and the risk load poses challenges in rapid acquisition, a physics-based and data-driven method for multi-dimensional failure risk load prediction of motors is proposed. Based on actual operational data collected from users, we analyze the failure risk loads of various components of a motor. A physical simulation model of the motor is established to extract multi-dimensional failure risk load time history, and the effectiveness of the simulation model is verified using data from bench tests. Moreover, using the physical model simulation data as a foundation, a two-stage data-driven model is constructed. In the first stage, the genetic algorithm optimized back propagation neural network (GA-BPNN) model is implemented for multi-dimensional loss prediction of the motor, and serves as the primary input for the second stage model, which integrates prediction accuracy and training efficiency. In the second stage, by comprehensively considering the spatial and temporal correlation features with the input layer reconstructed using correlation matrix weights, an improved convolutional neural network with bidirectional long short-term memory (CNN-BiLSTM) model is employed to predict multi-scale loads. Compared with traditional models, the proposed method exhibits significantly improved prediction accuracy, with R2 greater than 0.95. Furthermore, the damage error between the predicted load and the expected load is within 10%, which provides technical support for reliability evaluation and life prediction of electric motor.

Multi-Temporal Image Fusion-Based Shallow-Water Bathymetry Inversion Method Using Active and Passive Satellite Remote Sensing Data

In the active–passive fusion-based bathymetry inversion method using single-temporal images, image data often suffer from errors due to inadequate atmospheric correction and interference from neighboring land and water pixels. This results in the generation of noise, making high-quality data difficult to obtain. To address this problem, this paper introduces a multi-temporal image fusion method. First, a median filter is applied to separate land and water pixels, eliminating the influence of adjacent land and water pixels. Next, multiple images captured at different times are fused to remove noise caused by water surface fluctuations and surface vessels. Finally, ICESat-2 laser altimeter data are fused with multi-temporal Sentinel-2 satellite data to construct a machine learning framework for coastal bathymetry. The bathymetric control points are extracted from ICESat-2 ATL03 products rather than from field measurements. A backpropagation (BP) neural network model is then used to incorporate the initial multispectral information of Sentinel-2 data at each bathymetric point and its surrounding area during the training process. Bathymetric maps of the study areas are generated based on the trained model. In the three study areas selected in the South China Sea (SCS), the validation is performed by comparing with the measurement data obtained using shipborne single-beam or multi-beam and airborne laser bathymetry systems. The root mean square errors (RMSEs) of the model using the band information after image fusion and median filter processing are better than 1.82 m, and the mean absolute errors (MAEs) are better than 1.63 m. The results show that the proposed method achieves good performance and can be applied for shallow-water terrain inversion.

Construction of intelligent coal blending system based on BP neural network and genetic algorithm

The quality of coke is crucial to the steel-making process, and advanced coal blending technology can effectively improve the stability of coke and reduce production costs. However, some of the current coal blending systems lack expertise and are out of touch with the actual situation of the factory, unable to meet production requirements. In the research process, this paper combined the conventional indicators measured in Chinese factories with actual data, and established a reliable database. In the back propagation neural network modeling process, several parameters were optimised, significantly improving the prediction performance compared to traditional regression methods. An evolutionary algorithm with a penalty matrix is used to optimise the coal blending ratio, resulting in a reduction in the ash and sulphur content of the coke, as well as a cost reduction of approximately 44 RMB per tonne. Based on the initial research results, an intelligent coal blending system was developed, which has been successfully applied in the production process of a coke plant, with simple operation and stable operation, providing important reference for the development of coal blending systems in other coke plants.

Design of a Novel Fractional Whale Optimization-Enhanced Support Vector Regression (FWOA-SVR) Model for Accurate Solar Energy Forecasting

This study presents a novel Fractional Whale Optimization Algorithm-Enhanced Support Vector Regression (FWOA-SVR) framework for solar energy forecasting, addressing the limitations of traditional SVR in modeling complex relationships within data. The proposed framework incorporates fractional calculus in the Whale Optimization Algorithm (WOA) to improve the balance between exploration and exploitation during hyperparameter tuning. The FWOA-SVR model is comprehensively evaluated against traditional SVR, Long Short-Term Memory (LSTM), and Backpropagation Neural Network (BPNN) models using training, validation, and testing datasets. Experimental results show that FWOA-SVR achieves superior performance with the lowest MSE values (0.036311, 0.03942, and 0.03825), RMSE values (0.19213, 0.19856, and 0.19577), and the highest R2 values (0.96392, 0.96104, and 0.96192) for training, validation, and testing, respectively. These results highlight the significant improvements of FWOA-SVR in prediction accuracy and efficiency, surpassing benchmark models in capturing complex patterns within the data. The findings highlight the effectiveness of integrating fractional optimization techniques into machine learning frameworks for advancing solar energy forecasting solutions.

A Symmetrical Leech-Inspired Soft Crawling Robot Based on Gesture Control.

This paper presents a novel soft crawling robot controlled by gesture recognition, aimed at enhancing the operability and adaptability of soft robots through natural human-computer interactions. The Leap Motion sensor is employed to capture hand gesture data, and Unreal Engine is used for gesture recognition. Using the UE4Duino, gesture semantics are transmitted to an Arduino control system, enabling direct control over the robot's movements. For accurate and real-time gesture recognition, we propose a threshold-based method for static gestures and a backpropagation (BP) neural network model for dynamic gestures. In terms of design, the robot utilizes cost-effective thermoplastic polyurethane (TPU) film as the primary pneumatic actuator material. Through a positive and negative pressure switching circuit, the robot's actuators achieve controllable extension and contraction, allowing for basic movements such as linear motion and directional changes. Experimental results demonstrate that the robot can successfully perform diverse motions under gesture control, highlighting the potential of gesture-based interaction in soft robotics.

Arrears behavior prediction of power users based on BP neural network and multi-scale feature learning: a refined risk assessment framework

This study aims to develop an efficient model to predict the arrears behavior of electricity users by integrating multi-scale feature learning with a backpropagation (BP) neural network. The goal is to provide accurate early warning systems and enhanced risk management tools for power companies. The BP neural network algorithm adjusts weights to minimize prediction errors, while multi-scale feature learning captures the diversity and regularity of user behavior by extracting data from various time dimensions, such as daily, weekly, and monthly intervals. First, electricity usage and weather data from the UMass Smart Dataset are preprocessed, including steps such as data cleaning, standardization, and normalization. Next, features are extracted across three time scales—daily, weekly, and monthly. These features are then input into the BP neural network model using the multi-scale feature learning method. A hierarchical neural network structure is designed to address the characteristics of different scales in distinct layers. Key model parameters are optimized, and a sensitivity analysis is conducted. The experimental results demonstrate that the BP neural network model incorporating multi-scale features outperforms traditional BP neural network models and other control models in several evaluation metrics. Specifically, the Gini coefficient is 0.55, the Kolmogorov-Smirnov statistic is 0.60, the Matthews correlation coefficient is 0.45, and specificity is 0.82. These results indicate that the proposed method offers significant improvements in capturing user behavior patterns and enhancing prediction accuracy. The study concludes that the effective fusion of multi-scale features not only enhances the model’s prediction performance but also strengthens its generalization ability. This method provides an advanced risk management tool for power companies, helping to increase the operational efficiency of smart grids and encouraging further research toward greater intelligence in the field.

Co-pyrolysis behaviors and reaction mechanism analyses of coal slime and moso bamboo based on GC/MS and backpropagation neural network

The pyrolysis behaviors and gaseous products of coal slime (CS) and moso bamboo (MB) mixture were investigated by Thermogravimetric analyses, Thermogravimetric-Fourier transform infrared spectrometer (TG-FTIR), and Gas chromatogram/mass spectrum (GC/MS). Data showed that the synergistic effect of co-pyrolysis between CS and MB was more prominent above 200 °C. The release of alcohols and esters was inhibited after adding MB to CS. Dominant reactions and pyrolysis stages of CS and MB co-pyrolysis were determined based on principal component analysis. The average apparent activation energy (Eα) of a sample with 70% MB ratio was at its lowest and 29.7% lower than CS pyrolysis alone. Reaction mechanisms of co-pyrolysis varied with MB blending ratio, and the diffusion model was used to describe the mechanism of mixtures except CS. The Eα prediction model had high accuracy, the variation curve of Eα with conversion rate and blending ratio was obtained using backpropagation neural network models.

MEMS infrared light source stress optimization and reliable package design.

Aiming at the effects caused by stress and deformation on Micro-Electro-Mechanical System (MEMS) sensors, the stress distribution in the radiation area of the MEMS infrared light source is investigated, and by simulating and optimizing the thickness of the composite support film of the chip structure in COMSOL, a film layer thickness matching with lower stress and deformation for the MEMS infrared light source is derived. The utilization of the particle swarm algorithm and backpropagation neural network model allowed for the optimization of simulation data, enabling regression prediction over a broader range of thicknesses and providing a more precise depiction of the stress distribution trend. In addition, the specifications of the MEMS device help us to analyze the design of the support film thickness in the processing of the residual stress within the controllable range. To ensure the long-term stability and functionality of MEMS infrared light source chips in harsh environments, a comprehensive set of packaging schemes has been devised. Through simulations, it has been demonstrated that these packaging schemes effectively enhance the thermal efficiency of the light source while mitigating thermal stress and deformation that may arise during its operation. Consequently, this packaged configuration proves to be more advantageous for the sensor's normal operation under challenging conditions such as rain and temperature fluctuations, as compared to utilizing a bare chip. Finally, the manufacturing flow and layout design for the MEMS infrared light source chip are provided to guide the process of chip fabrication.

Trace Determination of Hormones in Peptide Powders Based on Multi-Molecular Infrared Spectroscopic and Multivariate Data Fusion

A direct, high-throughput and accurate method, multi-molecular infrared spectroscopic (MMIR) data fusion, was established for the detection of trace of estrone, diethylstilbestrol, betamethasone and prednisone acetate in peptide powders based on near-infrared and mid-infrared fusion datasets. Tri-step MMIR with progressively improved resolution captured key fingerprint features of hormones in the regions of 3430-3250, 2950-2850, 1750-1550 and 1335-1050 cm-1 which were exclusively selected as the datasets. The back propagation neural network (BPNN) model with the best performance used a mid-level fusion strategy and achieved excellent root mean square error of prediction (RMSEP, 1.101 mg kg-1) and residual prediction deviation (RPD, 9.890). Compared to those of single dataset models, the RMSEP was reduced by more than 82.03%. This method had remarkable practical significance for the direct and accurate quality evaluation of peptide powder products with favorable limit of detection (LOD) but without pretreatment and chemical agents, verifying the feasibility of multiple analytical instruments for rapid and comprehensive detection of powdered foods.

Prediction of Compressive Strength of Fly Ash-Recycled Mortar Based on Grey Wolf Optimizer-Backpropagation Neural Network.

The evaluation of the mechanical performance of fly ash-recycled mortar (FARM) is a necessary condition to ensure the efficient utilization of recycled fine aggregates. This article describes the design of nine mix proportions of FARMs with a low water/cement ratio and screens six mix proportions with reasonable flowability. The compressive strengths of FARMs were tested, and the influence of the water/cement ratio (w/c) and age on the compressive strength was analyzed. Meanwhile, a backpropagation neural network (BPNN) model optimized by the grey wolf optimizer (GWO), namely the GWO-BPNN model, was established to predict the compressive strength of FARM. The input layer of the model consisted of w/c, a cement/sand ratio, water reducer, age, and fly ash content, while the output layer was the compressive strength. The data set consisted of 150 sets from this article and existing research in the literature, of which 70% is used for model training and 30% for model validation. The results show that compared with the traditional BPNN, the coefficient of determination (R2) of GWO-BPNN increases from 0.85 to 0.93, and the mean squared error (MSE) of model training decreases from 0.018 to 0.015. Meanwhile, the convergence iterations of model validation decrease from 108 to 65. This indicates that GWO improved the prediction accuracy and computational efficiency of BPNN. The model results of characteristic heat, kernel density estimation, scatter matrix, and the SHAP value all indicated that the w/c was strongly negatively correlated with compressive strength, while the sand/cement ratio and age were strongly positively correlated with compressive strength. However, the relationship between the contents of fly ash, the water reducer, and the compressive strength was not obvious.

Solar Energy Datasets of Deep Learning Models Incorporating with GK-2A and ASOS Ground Measurements

This study presents the construction and evaluation of a dataset for estimating solar energy using the GK<sup>-2</sup>A satellite and deep learning. The GK<sup>-2</sup>A is currently utilized in real-time for weather observations over the Korean Peninsula. The GK<sup>-2</sup>A satellite features 16 channels, producing radiative channel images at spatial resolutions ranging from 500 m to 2 km, with temporal intervals as short as 2 minutes depending on the area. These satellite data are used in various fields, including meteorology, oceanography, vegetation monitoring, and renewable energy. In this study, we used spectral channel data from the GK<sup>-2</sup>A expended local area satellite from January 2021 to December 2022. For training and evaluating the accuracy of the deep learning model, we utilized data from 98 automated synoptic observing system ground observation sites operated by the Korea Meteorological Administration. A back-propagation neural network model, which showed meaningful results in estimating solar energy, was applied. Various hyperparameters were optimized, and data preprocessing and separation were conducted to optimize the model. The study also compared the performance of the deep learning model with physical models. The BPNN deep learning model achieved a statistical accuracy of root mean squared error (RMSE) 77.32 Wm<sup>-2</sup>, mean bias error (MBE) -0.48 Wm<sup>-2</sup>, and R<sup>2</sup> 0.91, indicating high accuracy. In contrast, the physical model showed an RMSE of 132.01 Wm<sup>-2</sup>, MBE -76.51 Wm<sup>-2</sup>, and an R<sup>2</sup> of 0.74, displaying relatively lower accuracy compared to the deep learning model. Additionally, the spatio-temporal map of solar energy generated by the deep learning model successfully captured the attenuation of radiation due to clouds and the variation in solar energy based on the position of the sun. The solar energy data produced in this study are expected to be useful as input data for various fields such as meteorology, agriculture, environmental monitoring, and marine sciences.

Embedded Rough-Neck Helmholtz Resonator Low-Frequency Acoustic Attenuator

In various practical noise control scenarios, such as duct noise mitigation, industrial machinery, architectural acoustics, and underwater applications, it is essential to develop noise absorbers that deliver effective low-frequency attenuation while maintaining compact dimensions. To achieve low-frequency absorption within a limited spatial volume, this study proposes an embedded Helmholtz resonator featuring a roughened neck and establishes a numerical computational model that incorporates thermos viscous effects. A quantitative investigation is conducted on three types of embedded rough-neck geometries (rectangular-grooved, triangular-grooved, and undulated) to elucidate their acoustic performance, with particular attention to differences in acoustic transmission loss and acoustic impedance characteristics. In response to the practical demand for even lower-frequency attenuation, this work further focuses on optimizing the structural parameters of an embedded rectangular-grooved Helmholtz resonator (ERHR). A back-propagation (BP) neural network models and predicts how structural parameters impact the acoustic transmission coefficient, elucidating the effects of geometric variations. Moreover, by coupling the BP network with the Golden Jackal Optimization (GJO) algorithm, a BP-GJO optimization model is developed to refine the structural parameters. The findings reveal that the proposed method significantly improves resonator spatial utilization at a specific noise frequency while preserving acoustic transmission loss performance. This work thereby provides a promising strategy for designing low-frequency, compact Helmholtz resonators suitable for a wide range of noise control applications.

Prediction of China’s Carbon Price Based on the Genetic Algorithm–Particle Swarm Optimization–Back Propagation Neural Network Model

Traditional BP neural networks frequently encounter local optima during carbon price forecasts. This study adopts a hybrid approach, combining a genetic algorithm and particle swarm optimization (GA-PSO) to improve the BP neural network, resulting in the creation of a GA-PSO-BP neural network model. Seven critical factors were identified affecting carbon prices, and we utilized data on carbon emission trading prices from China for the analysis. Compared to traditional BP neural network models, including GA-BP neural network models optimized solely with genetic algorithms and PSO-BP neural network models enhanced through particle swarm optimization, the findings reveal that the GA-PSO-BP neural network model demonstrates superior performance in terms of precision and robustness. Furthermore, it demonstrates advancements across various error evaluation metrics, thus delivering more accurate forecasts. Offering precise carbon price predictions, the enhanced GA-PSO-BP neural network model proves to be a valuable tool for analyzing the market and making decisions in the carbon pricing sector.

Mixed-effects neural network modelling to predict longitudinal trends in fasting plasma glucose

BackgroundAccurate fasting plasma glucose (FPG) trend prediction is important for management and treatment of patients with type 2 diabetes mellitus (T2DM), a globally prevalent chronic disease. (Generalised) linear mixed-effects (LME) models and machine learning (ML) are commonly used to analyse longitudinal data; however, the former is insufficient for dealing with complex, nonlinear data, whereas with the latter, random effects are ignored. The aim of this study was to develop LME, back propagation neural network (BPNN), and mixed-effects NN models that combine the 2 to predict FPG levels.MethodsMonitoring data from 779 patients with T2DM from a multicentre, prospective study from the shared platform Figshare repository were divided 80/20 into training/test sets. The first 10 important features were modelled via random forest (RF) screening. First, an LME model was built to model interindividual differences, analyse the factors affecting FPG levels, compare the AIC and BIC values to screen the optimal model, and predict FPG levels. Second, multiple BPNN models were constructed via different variable sets to screen the optimal BPNN. Finally, an LME/BPNN combined model, named LMENN, was constructed via stacking integration. A 10-fold cross-validation cycle was performed using the training set to build the model and evaluate its performance, and then the final model was evaluated on the test set.ResultsThe top 10 variables screened by RF were HOMA-β, HbA1c, HOMA–IR, urinary sugar, insulin, BMI, waist circumference, weight, age, and group. The best-fitting random-intercept mixed-effects (lm22) model showed that each patient’s baseline glucose levels influenced subsequent glucose measurements, but the trend over time was consistent. The LMENN model combines the strengths of LME and BPNN and accounts for random effects. The RMSE of the LMENN model ranges were 0.447–0.471 (training set), 0.525–0.552 (validation set), and 0.511–0.565 (test set). It improves the prediction performance of the single LME and BPNN models and shows some advantages in predicting FPG levels.ConclusionsThe LMENN model built by integrating LME and BPNN has several potential applications in analysing longitudinal FPG monitoring data. This study provides new ideas and methods for further research in the field of blood glucose prediction.

Research on Tool Wear Monitoring Technology Based on Variational Mode Decomposition and Back Propagation Neural Network Model.

Accurately predicting tool wear during the machining process not only saves machining time and improves efficiency but also ensures the production of good-quality parts and automation. This paper proposes a combined variational mode decomposition (VMD) and back propagation (BP) neural network model (VMD-BP), which maps spindle power to tool wear. The model is trained using both historical and real-time data. To improve accuracy, the internal power data from the machine tool are used to calibrate the model's input data. Data collected from milling experiments are used to test the model, with sensor-collected power being compared to the model's predicted power. The average error was 1.1256%, which confirms the reliability of the model. In practical applications, the model enables the real-time monitoring of spindle power, helping prevent excessive tool wear during machining. This offers significant guidance for actual production processes.

Prediction of areas of Oncomelania hupensis snail spread in Anhui Province based on five machine learning models

To predict the areas of Oncomelania hupensis snail spread in Anhui Province from 1977 to 2023 using machine learning models, and to compare the effectiveness of different machine learning models for prediction of areas of O. hupensis snail spread, so as to provide insights into investigating the trends in areas of O. hupensis snail spread. Data pertaining to O. hupensis snail spread in Anhui Province from 1977 to 2023 were collected and a database was created. Five machine learning models were created using the software Matlab R2019b, including support vector regression (SVR), nonlinear autoregressive (NAR) neural network, back propagation (BP) neural network, gated recurrent unit (GRU) neural network and long short-term memory (LSTM) neural network models, and the model fitting effect was evaluated with mean absolute error (MAE), root mean squared error (RMSE) and coefficient of determination (R2). Following model training, the areas of O. hupensis snail spread were predicted in Anhui Province from 2024 to 2030. The cumulative areas of O. hupensis snail spread were 40 241.32 hm2 in Anhui Province from 1977 to 2023, and the area of O. hupensis snail spread varied greatly among years, with a periodic peak every 4 to 6 years. The fitting curves of SVR, NAR neural network, BP neural network, GRU neural network and LSTM neural network models were increasingly closer to the real curves for areas of O. hupensis snail spread in Anhui Province. The trends in areas of O. hupensis snail spread in Anhui Province from 2024 to 2030 appeared approximately "M"-shaped curves by SVR and NAR neural network models, approximately "W"-shaped curves by BP and GRU neural network models, and a unimodal conical curve by the LSTM neural network model. The LSTM neural network model had the best effect for predicting areas of O. hupensis snail spread in Anhui Province, with the RMSE of 1 277 480, MAE of 797 422 and R2 of 0.978 9, respectively. Among the five models, The LSTM neural network model has a high efficiency for predicting areas of O. hupensis snail spread in Anhui Province, which may serve as a tool to investigate the trends in areas of O. hupensis snail spread.