Assessing the effectiveness of long short-term memory and artificial neural network in predicting daily ozone concentrations in Liaocheng City | Scientific Reports

Scientific Reports volume 15, Article number: 6798 (2025) Cite this article

Metrics details

Ozone pollution affects food production, human health, and the lives of individuals. Due to rapid industrialization and urbanization, Liaocheng has experienced increasing of ozone concentration over several years. Therefore, ozone has become a major environmental problem in Liaocheng City. Long short-term memory (LSTM) and artificial neural network (ANN) models are established to predict ozone concentrations in Liaocheng City from 2014 to 2023. The results show a general improvement in the accuracy of the LSTM model compared to the ANN model. Compared to the ANN, the LSTM has an increase in determination coefficient (R2), value from 0.6779 to 0.6939, a decrease in root mean square error (RMSE) value from 27.9895 μg/m3 to 27.2140 μg/m3 and a decrease in mean absolute error (MAE) value from 21.6919 μg/m3 to 20.8825 μg/m3. The prediction accuracy of the LSTM is superior to the ANN in terms of R, RMSE, and MAE. In summary, LSTM is a promising technique for predicting ozone concentrations. Moreover, by leveraging historical data and LSTM enables accurate predictions of future ozone concentrations on a global scale. This model will open up new avenues for controlling and mitigating ozone pollution.

Air pollution affects climate change, food production, and human life1,2,3,4,5,6,7,8. Poor air quality annually leads to about 6.5 million premature deaths worldwide, accounting for about 11.6% of global deaths9. Ozone (O3) exposure annually causes about 400 thousand premature deaths worldwide10. Although air quality in China is improving year by year, Ozone (O3) still cause about 69 thousand deaths per year11. Therefore, it is important to accurate predict ozone (O3) concentrations for human life and air quality management.

Air pollution prediction approaches mainly includes numerical simulations and data-driven methods. The numerical simulations consider the physical and chemical processes, such as the diffusion and transportation of air pollutants. These numerical models require sophisticated parameterizations. The widely used numerical simulations contain the Weather Research and Forecasting (WRF) model and the WRF-CMAQ12,13. Besides, the complexity of numerical simulations leads to high computational costs and difficulty in finding the optimal solution. In contrast, data-driven methods have the characteristics of simplicity, speed, and economy. Data-driven approaches includes regression analysis and machine learning11. Among these machine learning models, artificial neural network (ANN) has improved prediction accuracy compared to linear models, and compared to numerical simulations, ANN does not require the precise chemical and physical processes14. Furthermore, ANN has been widely used in air pollution prediction15,16,17,18,19. Ambient ozone concentrations is modelled using ANN with optimal inputs at Limbayat of Surat city (India)20. Results show that ANN modelling appears to be a promising method for modelling ozone concentrations. In recent years, Deep learning is broadly used for time series prediction problems21,22,23,24. Recurrent neural networks (RNNs) are particularly suitable for modeling time series data. Compared with ANN, RNNs can directly receive the original data as input and learn useful time correlations from training time series data25. However, the gradient issue in traditional RNN limits its ability to capture long-term dependencies, resulting in poor air pollution forecast performance26. Hence, long short-term memory (LSTM) is a RNN architecture and it further alleviates the vanishing gradient problem of vanilla27. So, LSTM has become the most popular deep learning approach for air pollution prediction28,29. The performance metrics of different methods are evaluated for the air pollution dataset. LSTM has the lowest MSE (mean square error) of 0.298, followed by DBN and RNN. In terms of MAE (mean absolute error), LSTM has the lowest value of 0.192, followed by RNN and DBN30. LSTMs are used to predict air quality in in the city of Madrid. Fully connected LSTM (FC-LSTM) when predicting ozone, has the lowest RMSE (root mean squared error) of 9.43831.

Therefore, this research was aimed to evaluate and identify the reliable model to predict ozone concentrations in Liaocheng City in China. Appropriate model architecture was selected to predict ozone concentrations by selected inputs. This study suggests that LSTM is a potential solution for predicting ozone concentrations.

The research on predicting ozone (O3) concentrations using artificial intelligence (AI) techniques has significantly advanced in recent years, offering robust models for air quality forecasting32,33,34,35,36,37,38,39,40. ANN achieves a RMSE of 33.46 μg/m3 with a coefficient of determination (R2) of 0.52. the ANN model for prediction of 1-day ahead ozone concentration is far more accurate than the multiple linear regression (MLR) model41. The multi-layer perceptron (MLP) neural network model is effective for forecasting O3 concentrations in Zagreb, with the highest R2 of 0.9 and the lowest RMSE of 10.86 µg/m3. The optimized MLP model outperforms other approaches, including persistence models and linear regression, which rely on simpler assumptions and fail to capture the complexities of atmospheric dynamics42. ANN models generally outperform multivariate regression (MR) models when using additional inputs like lag values or moving averages, with a correlation coefficient (R) of 0.9243. Combination of principal component analysis (PCA) and ANN is used to forecast daily total ozone concentrations and performs well for Mumbai and Kolkata with high correlation and low prediction errors44. Both SVM and ANN models performed well in predicting ozone concentrations, with R2 of 0.9152 and 0.9122, and RMSE of 7.85 and 7.66, respectively45. MLPANN is used for forecasting maximum daily 1-h ozone concentrations with nonlinear data assimilation. The RMSE improves from approximately 29 µg/m3 (3D photochemical model) to 17–18 µg/m3 with the upgraded MLP model46. ANN is used to predict ozone concentrations in Jinan, China, based on meteorological parameters and temporal covariates. In the testing phase, the ANN achieves an R2 of 0.8224, the RMSE is calculated as 22.2157 μg/m3, and the MAE is 17.6010 μg/m347. The MLR model achieved an R2 of 0.491, while the ANN model achieved an R2 of 0.767, indicating that the ANN model performed better in predicting O3 concentrations48. For forecasting maximum daily 8-h average ozone (MDA8-O3) 1 day in advance, the CEEMD + CRJ + MLR model achieved a MAE of 12.84 μg/m3, and a RMSE of 17.81 μg/m349. The ANN model demonstrates strong performance for O3 forecasting, with a R2 ranging from 0.49 to 0.68 over the forecast period from Day 0 to Day 4, in highly polluted regions like Delhi, India50. Feedforward neural network is used for a day ahead predictions of 8-h average ozone concentration (8hO3) in Novi Sad, Serbia. For 8hO3 forecasting, RMSE and correlation coefficient (R) are 12.962 μg/m3 and 0.910, respectively for the station Dnevnik51. A General Regression ANN (GRANN) was used to predict SOMO35 (the sum of means O3 over 35 ppb) for 24 European countries, with R2 = 0.8752. The Back Propagation (BP) ANN shows a lower average R (correlation coefficient) of 0.64, RMSE of 67.89 μg/m3, indicating moderate accuracy but instability in predictions, particularly with large O3 datasets in Beijing. The SVM-GABPNN model outperformed both BPANN and GABPANN by significantly improving the prediction accuracy for ozone concentrations, with an average R of 0.94, RMSE of 18.01 μg/m353. ANN performs better than linear and SVM models for modelling ozone. The R2 values for linear and SVM models are 0.757, 0.79, respectively, for Delhi. Conversely, the ANN yields R2 value of 0.9154. LR, Support Vector Regression (SVR), Gaussian Process Regression (GPR) and ANN are able to give the highest R2 (83% and 89%), respectively55. A Damped Least Squares (DLS) ANN is used to estimate the concentration of ozone based on meteorological parameters. The DLSNN model demonstrates very low RMSE and MAE, relatively high R (0.83), confirming the accuracy of the predictions56. A Chaotic ANN (CANN) is used to predict ozone levels in Lanzhou. CANN showed RMSE between 2.90 and 4.81 μg/m3 across stations and R2 between 0.9511 and 0.9728, outperforming ANN, BP, and MLR models57. Wavelet Transform (WT) is applied to remove noise and enhance the quality of input data before feeding it to an ANN model. WT-ANN is shown to be more accurate for predicting ozone concentrations compared to the ANN alone with RMSE of 0.9313 ppm, MAE of 0.6531 ppm, R of 0.9956 ppm58. At the DJ-3 station, the WFANN model achieved a correlation coefficient (R) of 0.97, with a MAPE of 18.42%, compared to the FANN model’s R of 0.93 and MAPE of 20.03%59.The RFNN-GWO model outperforms the others (RMLP-ANN and RFNN) in forecasting O3 concentrations with RMSE of 2.11 μg/m3, correlation coefficient (R) of 95.21% (Testing). By combining the strengths of ANNs and optimization algorithms, RFNN-GWO achieves high accuracy and stability, making it suitable for predicting air quality in regions with complex meteorological and pollutant data60.The ANN with k-means clustering shows improved performance in predicting ozone concentrations while reducing the training data in Seoul, South Korea61. Compared to the RFNN, RFNN-GOA demonstrates superior accuracy in predicting surface ozone levels in Osijek city62. FFBP model with 5 neurons in the hidden layer (M-5) has the best performance with R2 of 0.8344, and RMSE of 36.37%. Similarly, the LRNN model with 8 neurons in the hidden layer (M-8) shows good performance with R2 of 0.8268, and RMSE of 37.14%. Both FFBP and LRNN models performed well, but the FFBP model outperformed the LRNN model slightly in terms of statistical indices63.

In recent years, researchers have attempted various deep learning architectures to enhance the predictive ability of ozone concentration64,65,66. A deep convolutional neural network (CNN) is used to predict next-day 24-h ozone levels based on meteorological data and previous air pollution measurements. The CNN model could accurately predict ozone concentrations, with a strong performance (index of agreement (IOA) greater than 0.85 for 19 of 21 stations)67. The CNN model achieved a Pearson correlation coefficient (R) of 0.79, indicating reasonably good prediction accuracy68. RNN outperforms the traditional WRF-CMAQ model in predicting ozone levels in hangzhou, with R (0.91), and RMSE (19.87 μg/m3). RNN captures the temporal patterns of ozone accumulation and decay better than extreme learning machine (ELM), MLP, and random forest (RF) methods69. RNN is more effective than MLP model for forecasting O3 concentrations.is used for forecasting ozone (O3) concentrations 3 h ahead with a higher correlation coefficient (0.8967) and a lower NMSE (0.1174) in Pescara, Italy70.

LSTM (Long Short-Term Memory) networks have seen significant progress in predicting ozone (O3) levels, particularly due to their ability to capture long-term dependencies in time series data. When compared to other algorithms like ANN and Stochastic Gradient Descent (SGD), LE-LSTM exhibits superior performance with higher accuracy and lower error in ozone concentration predictions, particularly on sequential and time-series datasets71. The CNN-LSTM hybrid model significantly improves prediction accuracy compared to simpler models like MLP, with a reduction in RMSE, MAE, and MAPE72. A hybrid sequence-to-sequence deep learning model with attention mechanism (HSA-Net) is proposed for O₃ prediction in Beijing. The HSA-Net model outperforms other baseline models (such as Seq2Seq, LSTM, GRU) in terms of RMSE (22.08 μg/m3), MAE (16.11 μg/m3), and R (0.82)73. CNN-Transformer for ozone concentration prediction outperforms other models (ARIMA, CNN), with an RMSE value of 7.7574. The TLSTM for ozone pollution prediction achieves the best RMSE (15.5), followed by the TFF, and LSTM models75. In O3 prediction, the PSO-LSTM’s R2 value is higher than the RF and LSTM models, showing improvements of 10.39% and 10.69%, respectively76. OzoneNet based on LSTM model integrated the self-attention mechanism is used for ozone concentrations prediction. OzoneNet has higher reliability and validity, outperforming benchmark models77. Bi-LSTM is the most effective for predicting nationwide ozone trends, achieving an R2 of 0.66, and an RMSE of 15.32. In contrast, transformer is the poorest performing model, with an R2 of 0.57, and an RMSE of 17.3478.

In summary, the ANN and LSTM models demonstrate strong performance in predicting ozone concentrations, the models maintain acceptable levels of prediction accuracy, as evidenced by the low RMSE and MAE values and the high R2. The success of ANN and LSTM models indicate that data-driven models have shown good generalization ability and efficiency in dealing with ozone concentration prediction. Especially when dealing with complex meteorological and pollutant data, these models can learn patterns directly from a large amount of historical data without excessive physical assumptions. These studies have demonstrated the potential of these methods to predict ozone levels, benefiting environmental monitoring and public health. These studies suggest that the ANN and LSTM models are reliable tools for forecasting ambient ozone concentrations, even when applied to new, unseen data.

However, most in-depth researches on artificial intelligence methods for predicting ozone pollution have overlooked the use of information from past data. Therefore, this study aims to investigate the impact of incorporating lagged data on the performance of two artificial intelligence methods in predicting ozone pollution.

Liaocheng is located in the North China Plain, and has been included in major national strategies such as the coordinated development of ecological protection and high-quality development of the Yellow River basin (Fig. 1). In 2023, Liaocheng achieved a gross domestic product of CNY 292.636 billion, with a proportion of 14.1:37.1:48.8 in the industrial structure. The annual total solar radiation in Liaocheng is 120.1–127.1 kcal/cm2. The solar radiation is highest in summer, followed by spring, and lowest in winter. The average annual sunshine hours in Liaocheng are 2567 h, with a maximum of 274 h in May and a minimum of 170 h in January.

Location of Liaocheng.The map is generated using ArcGIS Pro 2.5 (ArcGIS Pro), URL: https://www.esriuk.com.

From January 1, 2014 to December 27, 2023, the ozone concentrations in Liaocheng in China are investigated (http://www.aqistudy.cn/)8,79. These ozone data are divided into three subsets: training period (from January 1, 2014 to December 27, 2021); verification period (from December 28, 2021 to December 27, 2022); prediction period (from December 28, 2022 to December 27, 2023).

ANN is constructed by one or several intermediate layers, an output neural layer, and an input neural layer80. ANN is characterised by a set of processing neurons, an activation function for each neuron, and learning. ANN has the network topology and parameters, such as hidden layers, nodes (neurons), learning rules, and activated functions. The structure of ANN has shown in Fig. 2.

ANN architecture for ozone concentrations predicting.

Backpropagation is a widely used method for training artificial neural networks by minimizing the global error function (E). This process involves calculating the error in the network’s predictions and adjusting the weights accordingly to reduce this error. The E is generally defined as the sum of squared differences between the desired outputs (Ai) and the predicted outputs (Bi) from the network, as shown in Eq. (1)81.

The factor is commonly used to simplify the derivative calculations that occur later during backpropagation. To minimize the global error function, the gradient descent algorithm is employed to update the weights of the network. The weight update rule is based on the negative gradient of the error function with respect to each weight, as expressed in Eq. (2):

where △Dji is the change in the weight between neuron j and neuron i; and η is the learning rate, which controls the step size for each weight update. \(\frac{\partial E}{{\partial D_{ji} }}\) represents the gradient of the error function with respect to the weight △Dji. This gradient is computed during the backpropagation process.

The training algorithm’s goal is to optimize the weights (w) and biases (b) of each neuron to maximize accuracy between predicted and actual outputs. The backpropagation algorithm includes six categories: self-adaptive learning rate, adaptive momentum, resilient backpropagation, quasi-Newton, conjugate gradient, and Bayesian regularization. we compare 13 key training algorithms for improving ANN performance, specifically in terms of accuracy in Table 1. The best training algorithm is determined through a trial-and-error approach82,83,84.

The choice of transfer function is crucial for output prediction, as it helps meet the specific requirements of the network neurons. Four types of transfer functions (activation functions) are logarithmic sigmoid transfer function (logsig,or sigmoid), hyperbolic tangent activation function (tansig,or tanh), linear transfer function (purelin), and rectified linear units (relu, or poslin), respectively67,82. Equations (3)–(6) represent the transfer functions:

where c represents the corresponding input variable.

The learning rate is an important parameter in the back-propagation algorithm, used to adjust the weights after each iteration. It determines the speed at which the weights are updated. If it is set too high, the results may overshoot the optimal value. If it is set too low, the descent might be too slow, making the optimization process inefficient85. In the ANN, the learning rate is chosen to be from 0.001 to 0.1. After testing, the learning rate is 0.01, optimal batch size is 16, and the number of epochs is 200.

LSTM is a revised RNN model with strong long data processing capability. The LSTM unit consists of three gate units and one storage (memory) unit, each playing a vital role in controlling the flow of information. These gate units are the input, forgetting and output gates (it, ft,ot), which are employed to control the input, forgetting and output of information. The memory unit is employed to store and update the information. Together, these gates allow the LSTM to selectively store, forget, and output information, making it possible to learn from both short-term and long-term dependencies86. The structure of the LSTM unit is shown in Fig. 3. Ct-1 is the previous memory state, ht-1 denotes the previous output information, xt denotes the new input information, σ represents the sigmoid function used in the gating operations87,88. The operations of these gates are described below:

where b is coefficient (Weight) and W is bias vector.

The network structure diagram of LSTM.

LSTMs are particularly popular in O3 time series prediction because of their ability to capture long-range temporal dependencies in O3 data. This is a significant advantage over traditional RNNs, which often struggle with long-term dependencies. LSTMs also excel at capturing nonlinear patterns in O3 data, making them highly effective for forecasting O3. By using both long-term memory (Ct-1) and short-term memory (ht-1), LSTMs are able to recall relevant information at different time scales. This makes them particularly suitable for tasks like O3 prediction, where understanding both long-term trends and short-term fluctuations is essential89.

Optimization is crucial in LSTM training to find the optimal parameters that minimize the loss function. The Adaptive Moment Estimation (ADAM) optimizer is widely used due to its combination of momentum and adaptive learning rates, making it efficient for stochastic optimization. It only requires first-order gradients, consumes little memory, and computes adaptive learning rates for each parameter using estimates of the first and second moments of the gradients. ADAM can converge faster and outperform stochastic gradient descent (SGD)90,91. Therefore, the ADAM optimizer is used in the LSTM. Selecting the correct learning rate is essential for training deep learning model effectively. The learning rate is 0.01, batch size is 16, and the number of epochs is 200.

Ozone Concentrations data were normalized using the Eq. (5)92:

where, Y denotes the normalized ozone data of Xj, \(X_{\max }\) denotes the maximum value of the raw ozone sequence, \(X_{\min }\) denotes the minimum value of the raw ozone sequence.

After model training, the predicted ozone concentrations are reversely normalized using the Eq. (6):

In order to appraise the predicting performance of the ozone concentration models, determination coefficient (R2), root mean square error (RMSE), and mean absolute error (MAE)15 are defined as follows:

where Pm denotes the value of observed ozone concentrations; Km denotes the predicted ozone concentrations; and I is the length of data. \(\mathop P\limits^{ - }\) denotes the average of the observed ozone concentrations, \(\mathop K\limits^{ - }\) denotes the average of the forecasted ozone concentrations.

Cross-validation (CV) is a successful approach to acquire the optimum parameters of ANN and LSTM models93. The process of Ten-Fold Cross Validation involves splitting the dataset into 10 equally sized subsets. One subset is reserved for testing, while the remaining nine are used for training the model. This procedure is repeated ten times, each time using a different subset for testing and the remaining subsets for training. By the end of the process, each fold has been used once for testing and nine times for training. The model’s performance is evaluated by calculating a performance metric for each iteration. The final performance score is the average of the individual scores across all folds. This approach helps reduce the variance in performance results and provides a more reliable estimate of how the model will perform on unseen data. One of the main advantages of Ten-Fold Cross Validation is its ability to reduce model bias. Since the model is trained and tested on different data subsets, the results are less likely to be skewed by a specific data partition. This method also helps to ensure that the model can generalize well to new data, rather than memorizing or overfitting to a particular subset. Additionally, Ten-Fold Cross Validation provides a comprehensive evaluation by using all available data for both training and testing, which is particularly valuable when working with small datasets94. Due to the superior performance of the tenfold-cross-validation, the results of ANN and LSTM models based on the tenfold-cross-validation technique are tested.

Various input variables were tested to determine the most accurate network structure for predicting ozone concentrations. Table 2 shows simulation results of ozone concentrations during the three periods. We have tried using 1–21 days as input and obtained different results. The trend of simulation results with input values of 1–18 days gradually improves, but deteriorates again after 18 days. It is important that using only the most recent 18 days simulates the best ozone concentrations. 18 variables were selected for the model input. Moreover, the hidden layer of the ANN model has 6 neurons. The activation functions of the ANN are logsig and purelin. The prediction accuracy levels of different neural network structures are shown in Table 2. The R2, RMSE, MAE during the predicting period are 0.6779, 27.9895 μg/m3, 21.6919 μg/m3, respectively. Figure 4 illustrates the simulation of ANN output and target values of predicting ozone concentrations. In the forecast period, ozone concentrations in the next day are predicted employing previous days’ ozone concentrations. The training and verifying values are from December 28, 2021 to December 27, 2022. and then we began to predict from December 28, 2022 to December 27, 2023. In the year, the forecasting ozone concentrations are similar to the actual ozone values.

The predicting results with the ANN model.

The statistical tests of the different algorithms in the ANN are displayed in Table 3. Comparing the tests, trainbr yields the highest R2 (0.7365), the lowest RMSE (28.5095), and the lowest MAE (21.7649) in training period. The trainbr algorithm also finishs well in the validation phase, with R2 (0.6816), RMSE (28.5514) and MAE (22.2194), respectively. In the prediction stage, R2, RMSE, and MAE of trainbr are respectively 0.6779, 27.9895, and 21.6919, explaining its predictive power.

The statistical tests of different unions of transfer functions (purelin (PU), tansig (TA), logsig (LO), poslin (PO)) are displayed in Table 4. The results of union (LO-PU) have the lowest RMSE and MAE values, and the highest R value, proving a successful union. In addition, this configuration also completes well in validation phase and has good predictive ability in the prediction period.

LSTM analysis was conducted to predict ozone concentrations in Liaocheng City. Optimization of hyperparameters is necessary as these values depend on the ozone concentrations. The outcomes for the input variables and statistical analysis of simulation results can be seen in Table 5. Similarly, Table 5 represent the R2, MAE and RMSE of the LSTM model. When the input value changes from 1 to 18 days, the O3 simulation results also improve, and then, from 18 to 21 days, the O3 simulation results deteriorate again. The analysis identified 18 day delays as significant factors in predicting the daily ozone concentrations. Therefore, the input number of the ozone time step is 18. The batch size and epochs selected for LSTM are 16 and 200, respectively. The activation functions of LSTM are tanh and sigmoid, and learning rate is 0.01. In addition, the optimizer is Adam for this experiment.

Figure 5 depicts the plot comparing the observed and predicted ozone concentrations for LSTM. It is seen that there is a high correlation between output and target ozone values.The figure shows clearly that the overall performance of LSTM is superior to that of ANN. The trend of LSTM has better agreement with observations than the ANN model.

The predicting results with the LSTM model.

We used the tenfold validation method to calculate all data (2014–2023) and obtained the average of 10 calculation results. From Table 6, it can be seen that LSTM and ANN have good generalization ability through cross validation.

Firstly, the input variables have a significant impact on both ANN and LSTM models for O3 prediction. By comparing the O3 prediction performance of both models with different input variables, we optimized the network structures of both models. Secondly, the activation functions also have a certain impact on the performance of the ANN O3 prediction model. By training different activation functions, ANN model can handle nonlinear relationships between complex input variables. However, ANN lacks a memory mechanism, ANN performs poorly in capturing the long-term dependencies of O3 time series, making it difficult to capture the dynamic changes of O3. The structure of LSTM enables it to consider past long and short-term information in O3 prediction, therefore, LSTM is a better choice.

In this research, we employed both LSTM and ANN models to predict ozone concentrations in Liaocheng City and compared their generalization ability and performance accuracy. The comparative analysis demonstrated that the LSTM (with R2 = 0.6939, RSME = 27.2140 μg/m3, MAE = 20.8825 μg/m3) outperformed the ANN (with R2 = 0.6779, RSME = 27.9895 μg/m3, MAE = 21.6919 μg/m3) in predicting ozone concentrations, as indicated in Table 1 and 2. The error values (MAE and RMSE) achieved by the proposed LSTM model are very less when compared to the ANN. The MAE and RMSE values achieved by the proposed LSTM model in predicting period are 20.8825 μg/m3 and 27.214 μg/m3, respectively. The R2 value of the proposed LSTM model is 0.6939 which is larger compared to the ANN model. LSTM has the smaller absolute difference between its predicted values and actual values. The LSTM technique exhibits superior generalization ability compared to the ANN model.

This finding is highly consistent with the complex and nonlinear nature of ozone concentrations, making the LSTM the preferred model for predicting O3 index95,96. These outcomes are also consistent with another study’s outcomes that compared the performance of multi-layer perceptron (MLP) and LSTM in developing effective ozone prediction models97. Similar to our outcomes, their investigation shows that MLR has poorer performance compared to LSTM. LSTM utilizes the dependencies of time series to generate better generalization ability and higher accuracy97. Both ANN and MLR were used to predict ozone concentrations in Lanzhou. RMSE and R2 of ANN were 7.8275 and 0.9238; while RMSE and R2 of MLR were 21.5847 and 0.5328 . ANN showed a better fit. The RMSE of ANN was much lower than that of MLR, which verified its accuracy and effectiveness. The results showed that ANN had better performance than MLR57. Back-propagation ANNs (BPANNs) were used for the prediction of O3 concentrations in Hyderabad, India during 2014–2016. The efficiency and performance of BPANNs showed higher R2 (0.9999)98. ANN, RNN (recurrent neural network), RFR (random forest regression) and LR (linear regression) were used to predict air ozone in Sichuan Province, China. R2, RMSE, and MAE of LR are 0.7271, 29.94, and 24.4891. R2, RMSE, and MAE of BPANN are 0.87274, 25.7923, and 20.189. R2, RMSE, and MAE of RNN are 0.9,0 25.8317, and 20.0169. R2, RMSE, and MAE of RFR are 0.8215, 24.9195, and 19.619399. ANN and RNN models outperform RFR and LR models across various variable sets. Both ANN and RNN can capture nonlinear relationships between input features and O3 concentrations. So, ANN and RNN can model intricate complex interactions and patterns. Recently, LSTM models were applied to estimate daily surface ozone concentrations in three urban agglomerations in China (Sichuan Basin, North China Plain, and Yangtze River Delta), with the accuracy of RMSE = 14.543–16.916, R2 = 0.636–0.737, MAE = 11.130–12.687100. LSTM was employed to obtain the predicted values of O3 in Beijing. The LSTM achieved the smallest error. The values of MAE, and RMSE, R2 are 10.43 µg/m3, 15.557 µg/m3, and 0.931101. LSTM method was applied to forecast hourly ozone levels in Turkey. For hidden neurons = 20 and epoch size = 1000, RMSE takes a value between 10.86 and 13.38, MAE takes values in the range of 7.45 and 7.672 and R2 value varies from 0.92 to 0.94102. Furthermore, RF-CEEMDAN-Attention-LSTM was proposed to predict three-hourly O3 concentrations in Chengdu. The model integrated random forest (RF), complete ensemble empirical mode decomposition with adaptive noise (CEEMADN) method and LSTM model. The simulation results showed that the hybrid model not only had a better fitting effect on O3 concentration values than other comparable models11. LSTM and MLR were used to predict ozone at the two stations in Shenzhen, China. RMSE, MAE, and R2 of the LSTM at HQC station are 14.0588, 9.8924, and 0.6068, respectively; while those values of the MLR are 16.8589, 12.0243, 0.4347, respectively. RMSE, MAE, and R2 of the LSTM at HQC station are 14.0588, 9.8924, and 0.6068, respectively; while those values of the MLR are 16.8589, 12.0243, 0.4347, respectively. Moreover, RMSE, MAE, and R2 of the LSTM at NA station are 12.2361, 9.3810, and 0.5226, respectively; while those values of the MLR are 12.9509, 10.0415, and 0.4915, respectively103. The prediction results of the LSTM are better than those of the MLR. The LSTM has excellent performance in dealing with ozone concentration forecasting problems, and it has good robustness and generalization performance. Overall, the findings of this research strengthen the advantages of deep learning models, particularly the LSTM method in accurately forecasting ozone concentrations, and highlight the potential for addressing the complexity of air pollution modeling.

Continuous improvement of air quality can meet people’s expectations for a better life. ozone concentration prediction is an important issue for researchers. Predicting ozone concentrations is a complex issue because Many parameters affect ozone formation. To achieve the objective, LSTM and ANN were built in this research paper to predict ozone concentrations in Liaocheng City. To check the performances of the proposed LSTM and ANN models, comparative analysis of both models with previous related works was completed using evaluation indicators. During the training phase, the R2, RMSE, and MAE of the LSTM model are 0.7577, 27.2747 μg/m3, and 20.9027 μg/m3, respectively, while during the verification phase, they are 0.6989, 27.7139 μg/m3, and 21.6309 μg/m3. Meanwhile, during the predicting phase, they are 0.6939, 27.2140 μg/m3, and 20.8825 μg/m3. The LSTM model provides more accurate results than the ANN. The results show that the LSTM model not only had a better fitting effect on O3 than ANN model in the training phase, but the model also had the higher R2 value for O3 at the predicting phase. This proposed LSTM model outperforms the ANN technique. Compared with the ANN, the LSTM model exhibits superior performance for high ozone concentration values, which has an important effect on early warning. Government administrators can use the LSTM to plan and implement effective strategies to reduce ozone concentrations and protect people’s health.

In the future, multi-day ahead prediction models of daily ozone concentrations will be investigated. There are some other considered factors, such as meteorological factors, air pollutants, terrain, and location, etc. We will use new methods to predict ozone in other regions, such as bidirectional LSTM (BiLSTM), convolutional neural network (CNN),CNN-LSTM, CNN- BiLSTM, TCN and transformer.

Data and materials are available from the corresponding author upon request.

Xu, Y. et al. A quantitative assessment and process analysis of the contribution from meteorological conditions in an O3 pollution episode in Guangzhou. China Atmos. Environ. 303, 119757. https://doi.org/10.1016/j.atmosenv.2023.119757 (2023).

Article CAS MATH Google Scholar

Wang, L., Zhao, B., Zhang, Y. & Hu, H. Correlation between surface PM2.5 and O3 in eastern China during 2015–2019: Spatiotemporal variations and meteorological impacts. Atmos. Environ. 294, 119520. https://doi.org/10.1016/j.atmosenv.2022.119520 (2023).

Article CAS Google Scholar

Qi, Q., Wang, S., Zhao, H., Kota, S. H. & Zhang, H. Rice yield losses due to O3 pollution in China from 2013 to 2020 based on the WRF-CMAQ model. J. Clean. Prod. https://doi.org/10.1016/j.jclepro.2023.136801 (2023).

Article Google Scholar

Mo, S. et al. Sex disparity in cognitive aging related to later-life exposure to ambient air pollution. Sci. Total Environ. 886, 163980. https://doi.org/10.1016/j.scitotenv.2023.163980 (2023).

Article CAS PubMed Google Scholar

Lyu, Y. et al. Tracking long-term population exposure risks to PM2.5 and ozone in urban agglomerations of China 2015–2021. Sci. Total Environ. 854, 158599. https://doi.org/10.1016/j.scitotenv.2022.158599 (2023).

Article CAS PubMed MATH Google Scholar

Guo, Q., He, Z. & Wang, Z. Long-term projection of future climate change over the twenty-first century in the Sahara region in Africa under four Shared Socio-Economic Pathways scenarios. Environ. Sci. Pollut. Res. 30, 22319–22329. https://doi.org/10.1007/s11356-022-23813-z (2023).

Article Google Scholar

Guo, Q., He, Z. & Wang, Z. The characteristics of air quality changes in Hohhot City in China and their relationship with meteorological and socio-economic factors. Aerosol Air Qual. Res. 24, 230274. https://doi.org/10.4209/aaqr.230274 (2024).

Article CAS Google Scholar

Guo, Q., He, Z. & Wang, Z. Change in air quality during 2014–2021 in Jinan City in China and its influencing factors. Toxics 11, 210. https://doi.org/10.3390/toxics11030210 (2023).

Article CAS PubMed PubMed Central MATH Google Scholar

Shams, S. R. et al. Assessing the effectiveness of artificial neural networks (ANN) and multiple linear regressions (MLR) in forcasting AQI and PM10 and evaluating health impacts through AirQ+ (case study: Tehran). Environ. Pollut. 338, 122623. https://doi.org/10.1016/j.envpol.2023.122623 (2023).

Article CAS PubMed MATH Google Scholar

Xue, T. et al. Estimating the exposure-response function between long-term ozone exposure and under-5 mortality in 55 low-income and middle-income countries: a retrospective, multicentre, epidemiological study. Lancet Planet. Health 7, e736–e746. https://doi.org/10.1016/S2542-5196(23)00165-1 (2023).

Article PubMed Google Scholar

Chu, Y. et al. Three-hourly PM25 and O3 concentrations prediction based on time series decomposition and LSTM model with attention mechanism. Atmos. Pollut. Res. 14, 101879. https://doi.org/10.1016/j.apr.2023.101879 (2023).

Article CAS MATH Google Scholar

Huang, C. et al. Study on the assimilation of the sulphate reaction rates based on WRF-Chem/DART. Sci. China Earth Sci. 66, 2239–2253. https://doi.org/10.1007/s11430-023-1153-9 (2023).

Article ADS CAS MATH Google Scholar

Wang, Y. et al. Ultra-high-resolution mapping of ambient fine particulate matter to estimate human exposure in Beijing. Commun. Earth Environ. 4, 451. https://doi.org/10.1038/s43247-023-01119-3 (2023).

Article ADS PubMed PubMed Central MATH Google Scholar

Mirzavand Borujeni, S., Arras, L., Srinivasan, V. & Samek, W. Explainable sequence-to-sequence GRU neural network for pollution forecasting. Sci. Rep. 13, 9940. https://doi.org/10.1038/s41598-023-35963-2 (2023).

Article ADS CAS PubMed PubMed Central MATH Google Scholar

Guo, Q., He, Z. & Wang, Z. Simulating daily PM2.5 concentrations using wavelet analysis and artificial neural network with remote sensing and surface observation data. Chemosphere 340, 139886. https://doi.org/10.1016/j.chemosphere.2023.139886 (2023).

Article CAS PubMed Google Scholar

Guo, Q., He, Z. & Wang, Z. Prediction of Hourly PM2.5 and PM10 Concentrations in Chongqing City in China Based on Artificial Neural Network. Aerosol Air Qual. Res. 23, 220448. https://doi.org/10.4209/aaqr.220448 (2023).

Article CAS Google Scholar

Guo, Q., He, Z. & Wang, Z. Predicting of daily PM2.5 concentration employing wavelet artificial neural networks based on meteorological elements in Shanghai China. Toxics 11, 51. https://doi.org/10.3390/toxics11010051 (2023).

Article PubMed PubMed Central MATH Google Scholar

He, Z., Guo, Q., Wang, Z. & Li, X. Prediction of monthly PM2.5 concentration in Liaocheng in China employing artificial neural network. Atmosphere 13, 1221. https://doi.org/10.3390/atmos13081221 (2022).

Article ADS CAS MATH Google Scholar

Guo, Q. et al. Air pollution forecasting using artificial and wavelet neural networks with meteorological conditions. Aerosol Air Qual. Res. 20, 1429–1439. https://doi.org/10.4209/aaqr.2020.03.0097 (2020).

Article CAS MATH Google Scholar

Kapadia, D. & Jariwala, N. Prediction of tropospheric ozone using artificial neural network (ANN) and feature selection techniques. Model. Earth Syst. Environ. 8, 2183–2192. https://doi.org/10.1007/s40808-021-01220-6 (2022).

Article MATH Google Scholar

Guo, Q., He, Z. & Wang, Z. Prediction of monthly average and extreme atmospheric temperatures in Zhengzhou based on artificial neural network and deep learning models. Front. Forests Glob. Change 6, 1249300. https://doi.org/10.3389/ffgc.2023.1249300 (2023).

Article Google Scholar

He, Z. & Guo, Q. Comparative analysis of multiple deep learning models for forecasting monthly ambient PM2.5 concentrations: A case study in Dezhou City, China. Atmosphere 15, 1432. https://doi.org/10.3390/atmos15121432 (2024).

Article MATH Google Scholar

Guo, Q. et al. A performance comparison study on climate prediction in Weifang city using different deep learning models. Water 16, 2870. https://doi.org/10.3390/w16192870 (2024).

Article MATH Google Scholar

Guo, Q., He, Z. & Wang, Z. Monthly climate prediction using deep convolutional neural network and long short-term memory. Sci. Rep. 14, 17748. https://doi.org/10.1038/s41598-024-68906-6 (2024).

Article CAS PubMed PubMed Central Google Scholar

Zhang, Y. et al. Prediction and cause investigation of ozone based on a double-stage attention mechanism recurrent neural network. Front. Environ. Sci. Eng. 17, 21. https://doi.org/10.1007/s11783-023-1621-4 (2022).

Article ADS MATH Google Scholar

Barthwal, A. & Goel, A. K. Advancing air quality prediction models in urban India: a deep learning approach integrating DCNN and LSTM architectures for AQI time-series classification. Model. Earth Syst. Environ. 10, 2935–2955. https://doi.org/10.1007/s40808-023-01934-9 (2024).

Article MATH Google Scholar

Ding, W. & Sun, H. Prediction of PM2.5 concentration based on the weighted RF-LSTM model. Earth Sci. Inform. 16, 3023–3037. https://doi.org/10.1007/s12145-023-01111-7 (2023).

Article ADS MATH Google Scholar

Xu, S., Li, W., Zhu, Y. & Xu, A. A novel hybrid model for six main pollutant concentrations forecasting based on improved LSTM neural networks. Sci. Rep. 12, 14434. https://doi.org/10.1038/s41598-022-17754-3 (2022).

Article ADS CAS PubMed PubMed Central MATH Google Scholar

Duan, J., Gong, Y., Luo, J. & Zhao, Z. Air-quality prediction based on the ARIMA-CNN-LSTM combination model optimized by dung beetle optimizer. Sci. Rep. 13, 12127. https://doi.org/10.1038/s41598-023-36620-4 (2023).

Article ADS CAS PubMed PubMed Central MATH Google Scholar

Zhu, L., Husny, Z. J. B. M., Samsudin, N. A., Xu, H. & Han, C. Deep learning method for minimizing water pollution and air pollution in urban environment. Urban Clim. 49, 101486. https://doi.org/10.1016/j.uclim.2023.101486 (2023).

Article MATH Google Scholar

Navares, R. & Aznarte, J. L. Predicting air quality with deep learning LSTM: Towards comprehensive models. Ecol. Inform. 55, 101019. https://doi.org/10.1016/j.ecoinf.2019.101019 (2020).

Article MATH Google Scholar

Masood, A. & Ahmad, K. A review on emerging artificial intelligence (AI) techniques for air pollution forecasting: Fundamentals, application and performance. J. Clean. Prod. 322, 129072. https://doi.org/10.1016/j.jclepro.2021.129072 (2021).

Article CAS MATH Google Scholar

Cabaneros, S. M., Calautit, J. K. & Hughes, B. R. A review of artificial neural network models for ambient air pollution prediction. Environ. Model. Softw. 119, 285–304. https://doi.org/10.1016/j.envsoft.2019.06.014 (2019).

Article Google Scholar

Pan, Q., Harrou, F. & Sun, Y. A comparison of machine learning methods for ozone pollution prediction. J. Big Data 10, 63. https://doi.org/10.1186/s40537-023-00748-x (2023).

Article MATH Google Scholar

Zhang, B., Zhang, Y. & Jiang, X. Feature selection for global tropospheric ozone prediction based on the BO-XGBoost-RFE algorithm. Sci. Rep. 12, 9244. https://doi.org/10.1038/s41598-022-13498-2 (2022).

Article ADS CAS PubMed PubMed Central MATH Google Scholar

Zhang, W. et al. Parsimonious estimation of hourly surface ozone concentration across China during 2015–2020. Sci. Data 11, 492. https://doi.org/10.1038/s41597-024-03302-3 (2024).

Article CAS PubMed PubMed Central MATH Google Scholar

Chen, Y. et al. Seasonal predictability of the dominant surface ozone pattern over China linked to sea surface temperature. npj Clim. Atmos. Sci. 7, 17. https://doi.org/10.1038/s41612-023-00560-7 (2024).

Article CAS MATH Google Scholar

Liao, Q. et al. Deep learning for air quality forecasts: A review. Curr. Pollut. Rep. https://doi.org/10.1007/s40726-020-00159-z (2020).

Article MATH Google Scholar

Malhotra, M., Walia, S., Lin, C.-C., Aulakh, I. K. & Agarwal, S. A systematic scrutiny of artificial intelligence-based air pollution prediction techniques, challenges, and viable solutions. J. Big Data 11, 142. https://doi.org/10.1186/s40537-024-01002-8 (2024).

Article Google Scholar

Kaur, M. et al. Computational deep air quality prediction techniques: a systematic review. Artif. Intell. Rev. 56, 2053–2098. https://doi.org/10.1007/s10462-023-10570-9 (2023).

Article MATH Google Scholar

Chaloulakou, A., Saisana, M. & Spyrellis, N. Comparative assessment of neural networks and regression models for forecasting summertime ozone in Athens. Sci. Total Environ. 313, 1–13. https://doi.org/10.1016/S0048-9697(03)00335-8 (2003).

Article ADS CAS PubMed Google Scholar

Hrust, L., Klaić, Z. B., Križan, J., Antonić, O. & Hercog, P. Neural network forecasting of air pollutants hourly concentrations using optimised temporal averages of meteorological variables and pollutant concentrations. Atmos. Environ. 43, 5588–5596. https://doi.org/10.1016/j.atmosenv.2009.07.048 (2009).

Article ADS CAS Google Scholar

Mahapatra, A. Prediction of daily ground-level ozone concentration maxima over New Delhi. Environ. Monit. Assess. 170, 159–170. https://doi.org/10.1007/s10661-009-1223-z (2010).

Article CAS PubMed MATH Google Scholar

Chattopadhyay, G., Chattopadhyay, S. & Chakraborthy, P. Principal component analysis and neurocomputing-based models for total ozone concentration over different urban regions of India. Theor. Appl. Climatol. 109, 221–231. https://doi.org/10.1007/s00704-011-0569-7 (2012).

Article ADS MATH Google Scholar

Luna, A. S., Paredes, M. L. L., de Oliveira, G. C. G. & Corrêa, S. M. Prediction of ozone concentration in tropospheric levels using artificial neural networks and support vector machine at Rio de Janeiro, Brazil. Atmos. Environ. 98, 98–104. https://doi.org/10.1016/j.atmosenv.2014.08.060 (2014).

Article ADS CAS Google Scholar

Božnar, M. Z., Grašič, B., Mlakar, P., Gradišar, D. & Kocijan, J. Nonlinear data assimilation for the regional modeling of maximum ozone values. Environ. Sci. Pollut. Res. 24, 24666–24680. https://doi.org/10.1007/s11356-017-0059-2 (2017).

Article Google Scholar

Gao, M., Yin, L. & Ning, J. Artificial neural network model for ozone concentration estimation and Monte Carlo analysis. Atmos. Environ. https://doi.org/10.1016/j.atmosenv.2018.03.027 (2018).

Article MATH Google Scholar

Sayahi, T. et al. Long-term calibration models to estimate ozone concentrations with a metal oxide sensor. Environ. Pollut. 267, 115363. https://doi.org/10.1016/j.envpol.2020.115363 (2020).

Article CAS PubMed MATH Google Scholar

Mo, Y. et al. A novel framework for daily forecasting of ozone mass concentrations based on cycle reservoir with regular jumps neural networks. Atmos. Environ. 220, 117072. https://doi.org/10.1016/j.atmosenv.2019.117072 (2020).

Article CAS MATH Google Scholar

Agarwal, S. et al. Air quality forecasting using artificial neural networks with real time dynamic error correction in highly polluted regions. Sci. Total Environ. 735, 139454. https://doi.org/10.1016/j.scitotenv.2020.139454 (2020).

Article CAS PubMed Google Scholar

Malinović-Milićević, S. et al. Prediction of tropospheric ozone concentration using artificial neural networks at traffic and background urban locations in Novi Sad, Serbia. Environ. Monit. Assess. 193, 84. https://doi.org/10.1007/s10661-020-08821-1 (2021).

Article CAS PubMed Google Scholar

Antanasijević, D., Pocajt, V., Perić-Grujić, A. & Ristić, M. Urban population exposure to tropospheric ozone: A multi-country forecasting of SOMO35 using artificial neural networks. Environ. Pollut. 244, 288–294. https://doi.org/10.1016/j.envpol.2018.10.051 (2019).

Article CAS PubMed Google Scholar

Feng, Y., Zhang, W., Sun, D. & Zhang, L. Ozone concentration forecast method based on genetic algorithm optimized back propagation neural networks and support vector machine data classification. Atmos. Environ. 45, 1979–1985. https://doi.org/10.1016/j.atmosenv.2011.01.022 (2011).

Article ADS CAS MATH Google Scholar

Meda, B. N. M., Mathew, A., Sarwesh, P., Shekar, P. R. & Sharma, K. V. Machine learning-based modeling of ground level ozone formation in Bangalore and New Delhi cities in India. Stochastic Environ. Res. Risk Assess. https://doi.org/10.1007/s00477-024-02845-6 (2024).

Article Google Scholar

Yafouz, A. et al. Comprehensive comparison of various machine learning algorithms for short-term ozone concentration prediction. Alex. Eng. J. 61, 4607–4622. https://doi.org/10.1016/j.aej.2021.10.021 (2022).

Article MATH Google Scholar

Balram, D., Lian, K.-Y. & Sebastian, N. A novel soft sensor based warning system for hazardous ground-level ozone using advanced damped least squares neural network. Ecotoxicol. Environ. Saf. 205, 111168. https://doi.org/10.1016/j.ecoenv.2020.111168 (2020).

Article CAS PubMed Google Scholar

Jia, B., Dong, R. & Du, J. Ozone concentrations prediction in Lanzhou, China, using chaotic artificial neural network. Chemometr. Intell. Lab. Syst. 204, 104098. https://doi.org/10.1016/j.chemolab.2020.104098 (2020).

Article CAS MATH Google Scholar

AlOmar, M. K., Hameed, M. M. & AlSaadi, M. A. Multi hours ahead prediction of surface ozone gas concentration: Robust artificial intelligence approach. Atmos. Pollut. Res. 11, 1572–1587. https://doi.org/10.1016/j.apr.2020.06.024 (2020).

Article CAS Google Scholar

Dunea, D., Pohoata, A. & Iordache, S. Using wavelet–feedforward neural networks to improve air pollution forecasting in urban environments. Environ. Monit. Assess. 187, 477. https://doi.org/10.1007/s10661-015-4697-x (2015).

Article CAS PubMed MATH Google Scholar

Braik, M., Sheta, A. & Al-Hiary, H. Hybrid neural network models for forecasting ozone and particulate matter concentrations in the Republic of China. Air Qual. Atmos. Health 13, 839–851. https://doi.org/10.1007/s11869-020-00841-7 (2020).

Article CAS MATH Google Scholar

Park, J. Efficient ozone concentration trend prediction using ANN and K-means clustering. Earth Sci. Inform. 18, 163. https://doi.org/10.1007/s12145-024-01676-x (2025).

Article MATH Google Scholar

Braik, M. et al. Predicting surface ozone levels in eastern Croatia: Leveraging recurrent fuzzy neural networks with grasshopper optimization algorithm. Water Air Soil Pollut. 235, 655. https://doi.org/10.1007/s11270-024-07378-w (2024).

Article CAS MATH Google Scholar

Gorai, A. K. & Mitra, G. A comparative study of the feed forward back propagation (FFBP) and layer recurrent (LR) neural network model for forecasting ground level ozone concentration. Air Qual. Atmos. Health 10, 213–223. https://doi.org/10.1007/s11869-016-0417-0 (2017).

Article CAS MATH Google Scholar

Mu, L., Bi, S., Ding, X. & Xu, Y. Transformer-based ozone multivariate prediction considering interpretable and priori knowledge: A case study of Beijing, China. J. Environ. Manag. 366, 121883. https://doi.org/10.1016/j.jenvman.2024.121883 (2024).

Article CAS Google Scholar

Zhou, J., Zhou, L., Cai, C. & Zhao, Y. Multi-step ozone concentration prediction model based on improved secondary decomposition and adaptive kernel density estimation. Process Saf. Environ. Prot. 190, 386–404. https://doi.org/10.1016/j.psep.2024.08.044 (2024).

Article CAS MATH Google Scholar

Wang, S. et al. A deep learning model integrating a wind direction-based dynamic graph network for ozone prediction. Sci. Total Environ. 946, 174229. https://doi.org/10.1016/j.scitotenv.2024.174229 (2024).

Article CAS PubMed Google Scholar

Sayeed, A. et al. Using a deep convolutional neural network to predict 2017 ozone concentrations, 24 hours in advance. Neural Netw. 121, 396–408. https://doi.org/10.1016/j.neunet.2019.09.033 (2020).

Article PubMed MATH Google Scholar

Eslami, E., Choi, Y., Lops, Y. & Sayeed, A. A real-time hourly ozone prediction system using deep convolutional neural network. Neural Comput. Appl. 32, 8783–8797. https://doi.org/10.1007/s00521-019-04282-x (2020).

Article MATH Google Scholar

Feng, R. et al. Unveiling tropospheric ozone by the traditional atmospheric model and machine learning, and their comparison: A case study in hangzhou, China. Environ. Pollut. 252, 366–378. https://doi.org/10.1016/j.envpol.2019.05.101 (2019).

Article CAS PubMed MATH Google Scholar

Biancofiore, F. et al. Analysis of surface ozone using a recurrent neural network. Sci. Total Environ. 514, 379–387. https://doi.org/10.1016/j.scitotenv.2015.01.106 (2015).

Article ADS CAS PubMed MATH Google Scholar

Hu, F., Zhu, Y., Liu, J. & Li, L. An efficient Long Short-Term Memory model based on Laplacian Eigenmap in artificial neural networks. Appl. Soft Comput. 91, 106218. https://doi.org/10.1016/j.asoc.2020.106218 (2020).

Article Google Scholar

Pak, U., Kim, C., Ryu, U., Sok, K. & Pak, S. A hybrid model based on convolutional neural networks and long short-term memory for ozone concentration prediction. Air Qual. Atmos. Health 11, 883–895. https://doi.org/10.1007/s11869-018-0585-1 (2018).

Article CAS MATH Google Scholar

Wang, H.-W. et al. Regional prediction of ground-level ozone using a hybrid sequence-to-sequence deep learning approach. J. Clean. Prod. 253, 119841. https://doi.org/10.1016/j.jclepro.2019.119841 (2020).

Article CAS Google Scholar

Chen, Y., Chen, X., Xu, A., Sun, Q. & Peng, X. A hybrid CNN-Transformer model for ozone concentration prediction. Air Qual. Atmos. Health 15, 1533–1546. https://doi.org/10.1007/s11869-022-01197-w (2022).

Article CAS MATH Google Scholar

Jiménez-Navarro, M. J., Martínez-Ballesteros, M., Martínez-Álvarez, F. & Asencio-Cortés, G. Explaining deep learning models for ozone pollution prediction via embedded feature selection. Appl. Soft Comput. 157, 111504. https://doi.org/10.1016/j.asoc.2024.111504 (2024).

Article Google Scholar

Chen, M. et al. Air Pollution prediction based on optimized deep learning neural networks: PSO-LSTM. Atmos. Pollut. Res. 16, 102413. https://doi.org/10.1016/j.apr.2025.102413 (2025).

Article CAS MATH Google Scholar

Tian, W., Ge, Z. & He, J. OzoneNet: A spatiotemporal information attention encoder model for ozone concentrations prediction with multi-source data. Air Qual. Atmos. Health 17, 2223–2234. https://doi.org/10.1007/s11869-024-01568-5 (2024).

Article CAS MATH Google Scholar

Lin, G., Zhao, H. & Chi, Y. A comprehensive evaluation of deep learning approaches for ground-level ozone prediction across different regions. Ecol. Inform. 86, 103024. https://doi.org/10.1016/j.ecoinf.2025.103024 (2025).

Article Google Scholar

Guo, Q. et al. Changes in Air Quality from the COVID to the Post-COVID Era in the Beijing-Tianjin-Tangshan Region in China. Aerosol Air Qual. Res. 21, 210270. https://doi.org/10.4209/aaqr.210270 (2021).

Article CAS MATH Google Scholar

Goudarzi, G., Hopke, P. K. & Yazdani, M. Forecasting PM2.5 concentration using artificial neural network and its health effects in Ahvaz, Iran. Chemosphere 283, 131285. https://doi.org/10.1016/j.chemosphere.2021.131285 (2021).

Article CAS PubMed Google Scholar

Nunnari, G. et al. Modelling SO2 concentration at a point with statistical approaches. Environ. Model. Softw. 19, 887–905. https://doi.org/10.1016/j.envsoft.2003.10.003 (2004).

Article MATH Google Scholar

Lim, C. E. et al. Predicting microbial fuel cell biofilm communities and power generation from wastewaters with artificial neural network. Int. J. Hydrogen Energy 52, 1052–1064. https://doi.org/10.1016/j.ijhydene.2023.08.290 (2024).

Article ADS CAS MATH Google Scholar

Chinatamby, P. & Jewaratnam, J. A performance comparison study on PM2.5 prediction at industrial areas using different training algorithms of feedforward-backpropagation neural network (FBNN). Chemosphere 317, 137788. https://doi.org/10.1016/j.chemosphere.2023.137788 (2023).

Article CAS PubMed Google Scholar

Khoshraftar, Z. Modeling of CO2 solubility and partial pressure in blended diisopropanolamine and 2-amino-2-methylpropanol solutions via response surface methodology and artificial neural network. Sci. Rep. 15, 1800. https://doi.org/10.1038/s41598-025-86144-2 (2025).

Article CAS PubMed PubMed Central MATH Google Scholar

Rene, E. R., Estefanía López, M., Veiga, M. C. & Kennes, C. Neural network models for biological waste-gas treatment systems. New Biotechnol. 29, 56–73. https://doi.org/10.1016/j.nbt.2011.07.001 (2011).

Article CAS Google Scholar

Luo, J. & Gong, Y. Air pollutant prediction based on ARIMA-WOA-LSTM model. Atmos. Pollut. Res. 14, 101761. https://doi.org/10.1016/j.apr.2023.101761 (2023).

Article CAS MATH Google Scholar

Ma, J., Ding, Y., Cheng, J. C. P., Jiang, F. & Wan, Z. A temporal-spatial interpolation and extrapolation method based on geographic Long Short-Term Memory neural network for PM2.5. J. Clean. Prod. 237, 117729. https://doi.org/10.1016/j.jclepro.2019.117729 (2019).

Article CAS Google Scholar

Mathivanan, S. K., Rajadurai, H., Cho, J. & Easwaramoorthy, S. V. A multi-modal geospatial–temporal LSTM based deep learning framework for predictive modeling of urban mobility patterns. Sci. Rep. 14, 31579. https://doi.org/10.1038/s41598-024-74237-3 (2024).

Article CAS PubMed PubMed Central Google Scholar

Al Mehedi, M. A. et al. Predicting the performance of green stormwater infrastructure using multivariate long short-term memory (LSTM) neural network. J. Hydrol. 625, 130076. https://doi.org/10.1016/j.jhydrol.2023.130076 (2023).

Article MATH Google Scholar

Toh, S. C., Lai, S. H., Mirzaei, M., Soo, E. Z. X. & Teo, F. Y. Sequential data processing for IMERG satellite rainfall comparison and improvement using LSTM and ADAM optimizer. Appl. Sci. 13, 7237. https://doi.org/10.3390/app13127237 (2023).

Article CAS Google Scholar

Chang, Z., Zhang, Y. & Chen, W. Electricity price prediction based on hybrid model of adam optimized LSTM neural network and wavelet transform. Energy 187, 115804. https://doi.org/10.1016/j.energy.2019.07.134 (2019).

Article MATH Google Scholar

Zhang, J. & Li, S. Air quality index forecast in Beijing based on CNN-LSTM multi-model. Chemosphere 308, 136180. https://doi.org/10.1016/j.chemosphere.2022.136180 (2022).

Article CAS PubMed Google Scholar

Wang, Z. et al. Enhanced RBF neural network metamodelling approach assisted by sliced splitting-based K-fold cross-validation and its application for the stiffened cylindrical shells. Aerosp. Sci. Technol. 124, 107534. https://doi.org/10.1016/j.ast.2022.107534 (2022).

Article MATH Google Scholar

Sejuti, Z. A. & Islam, M. S. A hybrid CNN–KNN approach for identification of COVID-19 with 5-fold cross validation. Sensors Int. 4, 100229. https://doi.org/10.1016/j.sintl.2023.100229 (2023).

Article MATH Google Scholar

Hong, F., Ji, C., Rao, J., Chen, C. & Sun, W. Hourly ozone level prediction based on the characterization of its periodic behavior via deep learning. Process Saf. Environ. Prot. 174, 28–38. https://doi.org/10.1016/j.psep.2023.03.059 (2023).

Article CAS MATH Google Scholar

Zhang, B., Song, C., Li, Y. & Jiang, X. Spatiotemporal prediction of O3 concentration based on the KNN-Prophet-LSTM model. Heliyon 8, e11670. https://doi.org/10.1016/j.heliyon.2022.e11670 (2022).

Article CAS PubMed PubMed Central Google Scholar

Ehteram, M., Najah Ahmed, A., Khozani, Z. S. & El-Shafie, A. Graph convolutional network – Long short term memory neural network- multi layer perceptron- Gaussian progress regression model: A new deep learning model for predicting ozone concertation. Atmos. Pollut. Res. 14, 101766. https://doi.org/10.1016/j.apr.2023.101766 (2023).

Article CAS Google Scholar

Suraboyina, S., Allu, S. K., Anupoju, G. R. & Polumati, A. A comparative predictive analysis of back-propagation artificial neural networks and non-linear regression models in forecasting seasonal ozone concentrations. J. Earth Syst. Sci. 131, 189. https://doi.org/10.1007/s12040-022-01912-2 (2022).

Article ADS CAS Google Scholar

Zhou, Z., Qiu, C. & Zhang, Y. A comparative analysis of linear regression, neural networks and random forest regression for predicting air ozone employing soft sensor models. Sci. Rep. 13, 22420. https://doi.org/10.1038/s41598-023-49899-0 (2023).

Article ADS CAS PubMed PubMed Central Google Scholar

Zhang, X. et al. Estimation of lower-stratosphere-to-troposphere ozone profile using long short-term memory (LSTM). Remote Sens. https://doi.org/10.3390/rs13071374 (2021).

Article Google Scholar

Seng, D., Zhang, Q., Zhang, X., Chen, G. & Chen, X. Spatiotemporal prediction of air quality based on LSTM neural network. Alex. Eng. J. 60, 2021–2032. https://doi.org/10.1016/j.aej.2020.12.009 (2021).

Article MATH Google Scholar

Ekinci, E., İlhan Omurca, S. & Özbay, B. Comparative assessment of modeling deep learning networks for modeling ground-level ozone concentrations of pandemic lock-down period. Ecol. Model. 457, 109676. https://doi.org/10.1016/j.ecolmodel.2021.109676 (2021).

Article CAS MATH Google Scholar

Cheng, Y., Zhu, Q., Peng, Y., Huang, X.-F. & He, L.-Y. Multiple strategies for a novel hybrid forecasting algorithm of ozone based on data-driven models. J. Clean. Prod. 326, 129451. https://doi.org/10.1016/j.jclepro.2021.129451 (2021).

Article CAS MATH Google Scholar

Download references

This research was supported by Shandong Provincial Natural Science Foundation (Grant No. ZR2023MD075), State Key Laboratory of Loess and Quaternary Geology Foundation (Grant No. SKLLQG2419), LAC/CMA (Grant No. 2023B02), Shandong Province Higher Educational Humanities and Social Science Program (Grant No. J18RA196), the National Natural Science Foundation of China (Grant No. 41572150), and the Junior Faculty Support Program for Scientific and Technological Innovations in Shandong Provincial Higher Education Institutions (Grant No. 2021KJ085).

School of Geography and Environment, Liaocheng University, Liaocheng, 252000, China

Qingchun Guo & Zhenfang He

Institute of Huanghe Studies, Liaocheng University, Liaocheng, 252000, China

Qingchun Guo & Zhenfang He

State Key Laboratory of Loess and Quaternary Geology, Institute of Earth Environment, Chinese Academy of Sciences, Xi’an, 710061, China

Qingchun Guo

Key Laboratory of Atmospheric Chemistry, China Meteorological Administration, Beijing, 100081, China

Qingchun Guo

Key Laboratory of Ecosystem Network Observation and Modeling, Institute of Geographic Sciences and Natural Resources Research, National Ecosystem Science Data Center, Chinese Academy of Sciences, Beijing, 100101, China

Zhaosheng Wang

You can also search for this author in PubMed Google Scholar

You can also search for this author in PubMed Google Scholar

You can also search for this author in PubMed Google Scholar

All authors contributed to the study conception and design. Writing and editing Q.G. and Z.H.; preliminary data collection: Q.G., Z.H. and Z.W. All authors read and approved the final manuscript.

Correspondence to Qingchun Guo.

The authors declare no competing interests.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

Guo, Q., He, Z. & Wang, Z. Assessing the effectiveness of long short-term memory and artificial neural network in predicting daily ozone concentrations in Liaocheng City. Sci Rep 15, 6798 (2025). https://doi.org/10.1038/s41598-025-91329-w

Download citation

Received: 24 April 2024

Accepted: 19 February 2025

Published: 25 February 2025

DOI: https://doi.org/10.1038/s41598-025-91329-w

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative