Air Quality Dataset Research Articles

Spatio-Temporal Changes in Air Quality of the Urban Area of Chongqing from 2015 to 2021 Based on a Missing-Data-Filled Dataset

Air pollution is one of the severe environmental issues in Chongqing. Many measures made by the government for improving air quality have been put into use these past few years, while the influence of these measures remains unknown. This study analyzed the changes in the air quality of the urban area of Chongqing between 2015 and 2021 using a complete in situ observation dataset that all missing data were filled by the interpolation of a low-rank tensor completion model with truncate nuclear norm minimization (LRTC-TNN). The results include: (1) the LRTC-TNN model robustly performs to reconstruct missing data of pollutant concentrations with an R2 of 0.93 and an RMSE of 7.78; (2) the air quality index (AQI) decreases by 15.96%, and the total polluted days decrease by 21.05% from 2015 to 2021, showing an obvious promotion in air quality; and (3) the changing air quality is attributed to decreasing concentrations of PM2.5 (34.10%), PM10 (25.03%), and NO2 (5.53%) from 2015 to 2021, whereas an increasing concentration of O3 (10.49%) is observed. The processing method for missing data, intact AQI datasets, and analysis of changes are beneficial to policy-making for environmental improvement and fill the gap in the field of data interpolation for air quality datasets in mountainous areas.

Air quality prediction using spatio-temporal deep learning

With the rapid urbanization, many developing countries are suffering from heavy air pollution. Predicting air quality accurately is critical for people’s outside planning and governments’ policy-making in these countries. This paper studies the air quality dataset collected in 22 stations of Beijing city, China, and reveals the spatial correlations, the temporal dependencies and feature correlations hidden in the dataset. Different from existing shallow or deep learning models that do not fully consider these correlations, we propose a spatio-temporal deep learning model called Conv1D-LSTM, which unifies 1-dimensional convolutional neural network (1D CNN) and long short-term memory (LSTM) for spatial and temporal correlation feature extraction, and uses a fully connected network (FCN) to exploit these features for air quality prediction. Moreover, this study investigates the problem of data missing in the air quality dataset and impute the missing values from spatial and temporal views. Extensive experiments are conducted by applying the proposed model to hourly PM2.5 and PM10 with single and multi-step predictions over the study area during 2014–2015. The results show the effectiveness of the proposed model and its superiority over other baseline models.

Spatiotemporal data partitioning for distributed random forest algorithm: Air quality prediction using imbalanced big spatiotemporal data on spark distributed framework

Spatiotemporal air quality datasets are typically collected hourly in monitoring stations deployed non-uniformly across a metropolitan city. These datasets are not only big, which poses challenges on the storage and processing capacity of centralized computing systems but also imbalanced and spatially heterogeneous, which may result in biased air quality prediction. To address these challenges, we designed and developed a parallel air quality prediction system equipped with a spatiotemporal data partitioning method, a distributed machine learning algorithm, Hadoop’s distributed data storage platform and its resource scheduler/manager, and Spark’s efficient and in-memory execution environment, which is suitable for running iterative algorithms, e.g., machine learning. Our proposed spatiotemporal partitioning method accounted for imbalance and spatial heterogeneity features of big air quality data in predictive models, which comply with the load-balancing requirement of distributed computing systems. Distributed Random Forest algorithm in the H2O library of the Spark framework was selected as the distributed machine learning algorithm to develop the air quality predictive model. This algorithm is an ensemble forest with algorithm-level adjustments to perform as efficiently as possible for big imbalanced datasets. An application of the parallel quality prediction system for Tehran, Iran showed that the parallel prediction system had considerable speedup gain and improved both the overall accuracy and class precision of air quality prediction when working with imbalanced big spatiotemporal air quality datasets. A future research direction is to add data streaming and visualization functions to the system to provide rapid and reliable air quality prediction for supporting environmental health management. • A parallel air quality prediction system based on Spark and Hadoop frameworks. • A spatiotemporal big data partitioning method based on location and year of data. • Implemented H2O Distributed Random Forest Algorithm using Sparkling Water library. • Achieved overall accuracy of 68% and precision improvements for minority classes. • Observed an increasing trend in speedup gain when adding more parallel processors.

Perfomance analysis of Naive Bayes method with data weighting

Classification using naive bayes algorithm for air quality dataset has an accuracy rate of 39.97%. This result is considered not good and by using all existing data attributes. By doing pre-processing, namely feature selection using the gain ratio algorithm, the accuracy of the Naive Bayes algorithm increases to 61.76%. This proves that the gain ratio algorithm can improve the performance of the naive bayes algorithm for air quality dataset classification. Classification using naive bayes algorithm for air quality dataset. While the Water Quality dataset has an accuracy rate of 93.18%. These results are considered good and by using all the existing data attributes. By doing pre-processing, namely feature selection using the gain ratio algorithm, the accuracy of the Naive Bayes algorithm increases to 95.73%. This proves that the gain ratio algorithm can improve the performance of the naive bayes algorithm for air quality dataset classification. Classification using Naive Bayes algorithm for Water Quality dataset. Based on the tests that have been carried out on all data, it can be seen that the Weight nave Bayes classification model can provide better accuracy values ​​because there is a change in the weighting of the attribute values ​​in the dataset used. The value of the weighted Gain ratio is used to calculate the probability in Nave Bayes, which is a parameter to see the relationship between each attribute in the data, and is used as the basis for the weighting of each attribute of the dataset. The higher the Gain ratio of an attribute, the greater the relationship to the data class. So that the accuracy value increases than the accuracy value generated by the Naïve Bayes classification model. The increase in accuracy in the Naïve Bayes classification model is due to the number of weights from the attribute selection in the Gain ratio.

An Intelligent Time Series Model Based on Hybrid Methodology for Forecasting Concentrations of Significant Air Pollutants

Rapid industrialization and urban development are the main causes of air pollution, leading to daily air quality and health problems. To find significant pollutants and forecast their concentrations, in this study, we used a hybrid methodology, including integrated variable selection, autoregressive distributed lag, and deleted multiple collinear variables to reduce variables, and then applied six intelligent time series models to forecast the concentrations of the top three pollution sources. We collected two air quality datasets from traffic and industrial monitoring stations and weather data to analyze and compare their results. The results show that a random forest based on selected key variables has better classification metrics (accuracy, AUC, recall, precision, and F1). After deleting the collinearity of the independent variables and adding the lag periods using the autoregressive distributed lag model, the intelligent time-series support vector regression was found to have better forecasting performance (RMSE and MAE). Finally, the research results could be used as a reference by all relevant stakeholders and help respond to poor air quality.

Dynamic graph convolution neural network based on spatial-temporal correlation for air quality prediction

Air pollution is a serious threat to both the ecological environment and the physical health of individuals. Therefore, accurate air quality prediction is urgent and necessary for pollution mitigation and residents’ travel. However, few existing models are established based on the dynamic spatiotemporal correlation of air pollutants to predict air quality. In this paper, a novel deep learning model combining the dynamic graph convolutional network and the multi-channel temporal convolutional network (DGC-MTCN) is proposed for air quality prediction. To efficiently represent the time-varying spatial dependencies, a new spatiotemporal dynamic correlation calculation method based on gray relation analysis is proposed to construct dynamic adjacency matrices. Then, the spatiotemporal features are sufficiently extracted by the graph convolutional network and the multi-channel temporal convolutional network. Two real-world air quality datasets collected from Beijing and Fushun are applied to verify the performance of our proposed model. The experimental results show that compared with other baselines, the DGC-MTCN model has excellent prediction accuracy. Especially for the prediction of multi-step and different stations, our model performs better temporal stability and generalization ability.

A Novel Missing Data Imputation Approach for Time Series Air Quality Data Based on Logistic Regression

Missing values in air quality datasets bring trouble to exploration and decision making about the environment. Few imputation methods aim at time series air quality data so that they fail to handle the timeliness of the data. Moreover, most imputation methods prefer low-missing-rate datasets to relatively high-missing-rate datasets. This paper proposes a novel missing data imputation method, called FTLRI, for time series air quality data based on the traditional logistic regression and a presented “first Five & last Three” model, which can explain relationships between disparate attributes and extract data that are extremely relevant, both in terms of time and attributes, to the missing data, respectively. To investigate the performance of FTLRI, it is benchmarked with five classical baselines and a new dynamic imputation method using a neural network with average hourly concentration data of pollutants from three disparate stations in Lanzhou in 2019 under different missing rates. The results show that FTLRI has a significant advantage over the compared imputation approaches, both in the particular short-term and long-term time series air quality data. Furthermore, FTLRI has good performance on datasets with a relatively high missing rate, since it only selects the data extremely related to the missing values instead of relying on all the other data like other methods.

The Impact of Air Pollution on Pulmonary Diseases: A Case Study from Brasov County, Romania

Air pollution is considered one of the most significant risk factors for human health. To ensure air quality and prevent and reduce the harmful impact on human health, it is necessary to identify and measure the main air pollutants (sulfur and nitrogen oxides, PM10 and PM2.5 particles, lead, benzene, carbon monoxide, etc.), their maximum values, as well as the impact they have on mortality/morbidity rates caused by respiratory diseases. This paper aims to assess the influence of air pollution on respiratory diseases based on an analysis of principal pollutants and mortality/morbidity data sets. In this respect, four types of data are used: pollution sources inventory, air quality data sets, mortality/morbidity data at the local and national level, and clinical data of patients diagnosed with different forms of lung malignancies. The results showed an increased number of deaths caused by respiratory diseases for the studied period, correlated with the decreased air quality due to industrial and commercial activities, households, transportation, and energy production.

Air Pollution Exposure and the Relative Risk of Sudden Sensorineural Hearing Loss in Taipei.

(1) Background: The etiologies of sudden sensorineural hearing loss (SSHL) remain unclear. The level of mean particulate matter with a diameter of 2.5 μm or less (PM2.5) was not associated with SSHL, but the maximum PM2.5 level exhibited a negative association with SSHL in Korea. Exposure to nitrogen dioxide (NO2) for 2 weeks increased the risk of SSHL. The lag effects of SSHL after air pollution exposure were limited. We aimed to evaluate the association of SSHL with air pollution exposure to determine whether air pollution exposure caused delayed effects. (2) Methods: This observational study used inpatient data obtained from electronic health records at the Tri-Service General Hospital from 2011 to 2019. The data of all SSHL patients were retrieved. The air quality dataset from Songshan station from 2011 to 2019 was used. The main outcomes were the relative risks (RRs) of SSHL associated with PM2.5, O3, and NO2 exposures within 1 month. The relationships between these factors were examined using distributed lag nonlinear time series models. (3) Results: The RR of SSHL associated with PM2.5 exposure was 1.195 (95% confidence interval (C.I.: 1.047–1.363) for a 10 unit increase at a lag of 7 days. The RR of SSHL associated with O3 exposure was 1.14 (95% C.I.: 1.003–1.3) for a 10 unit increase at a lag of 9 days. The RR of SSHL associated with NO2 exposure was 1.284 (95% C.I.: 1.05–1.57) for a 10 unit increase at a lag of 23 days. (4) Conclusions: In our study, SSHL was confirmed to be associated with air pollution exposure with a lag effect. We discussed possible mechanisms to explore possible biological hypotheses and support further research. Large-scale studies including participants with other ethnicities and causal relationships are needed to confirm our findings.

Information-aware attention dynamic synergetic network for multivariate time series long-term forecasting

Multivariate time series forecasting is widely used in a variety of fields, such as cyber-physical systems and financial market analysis. Recently, attention-based recurrent neural networks (RNNs) have been paid attention by scholars for its ability to reduce the accumulative errors. Although attention-based RNNs are proved effective, there are still some challenges: 1) the noise in raw data will hurt model performance, 2) the traditional attentions are easy to discard low-weight input vectors, thereby leading to poor accuracy, and 3) encoder-focused attentions are not conducive to maintaining the trend consistency between the prediction and the original sequence. To tackle these problems, we propose a novel Information-aware Attention Dynamic Synergy Network (IADSN), which contains a specially designed information-aware long short-term memory network (IALSTM), a multi-dimensional attention (MA) that fine-grainedly assigns weight to your attention, and an attention dynamic synergy strategy. The novelty of MA lies in assigning a weight vector to the input instead of a single scalar. Therefore, it can identify the importance of each dimension of the input vector, thus alleviating the problem of ignoring low-weight inputs. IALSTM employs internal MA and a gated fusion unit to weaken the influence of input untrusted features on prediction. The attention dynamic synergy strategy maintains the similarity between the predicted and the original series by establishing an association among the current decoder unit, the previous decoder units, and the encoder. Experiments on three fields of energy, air quality, and ecological datasets demonstrate that IADSN not only achieves the state-of-the-art performance, but also effectively maintains the dynamic tendency of the forecast series.

Deep neural networks for spatiotemporal PM2.5 forecasts based on atmospheric chemical transport model output and monitoring data

Reliable long-horizon PM2.5 forecasts are crucial and beneficial for health protection through early warning against air pollution. However, the dynamic nature of air quality makes PM2.5 forecasts at long horizons very challenging. This study proposed a novel machine learning-based model (MCNN-BP) that fused multiple convolutional neural networks (MCNN) with a back-propagation neural network (BPNN) for making spatiotemporal PM2.5 forecasts for the next 72 h at 74 stations covering the whole Taiwan simultaneously. Model configuration involved an ensemble of massive hourly air quality and meteorological monitoring datasets and the existing publicly-available PM2.5 simulated (forecasted) datasets from an atmospheric chemical transport (ACT) model. The proposed methodology collaboratively constructed two CNNs to mine the observed data (the past) and the forecasted data from ACT (the future) separately. The results showed that the MCNN-BP model could significantly improve the accuracy of spatiotemporal PM2.5 forecasts and substantially reduce the forecast biases of the ACT model. We demonstrated that the proposed MCNN-BP model with effective feature extraction and good denoising ability could overcome the curse of dimensionality and offer satisfactory regional long-horizon PM2.5 forecasts. Moreover, the MCNN-BP model has considerably shorter computational time (5 min) and lower computational load than the compute-intensive ACT model. The proposed approach hits a milestone in multi-site and multi-horizon forecasting, which significantly contributes to early warning against regional air pollution.

Machine learning methods to predict particulate matter PM 2.5.

Introduction Pollution of air in urban cities across the world has been steadily increasing in recent years. An increasing trend in particulate matter, PM 2.5, is a threat because it can lead to uncontrollable consequences like worsening of asthma and cardiovascular disease. The metric used to measure air quality is the air pollutant index (API). In Malaysia, machine learning (ML) techniques for PM 2.5 have received less attention as the concentration is on predicting other air pollutants. To fill the research gap, this study focuses on correctly predicting PM 2.5 concentrations in the smart cities of Malaysia by comparing supervised ML techniques, which helps to mitigate its adverse effects. Methods In this paper, ML models for forecasting PM 2.5 concentrations were investigated on Malaysian air quality data sets from 2017 to 2018. The dataset was preprocessed by data cleaning and a normalization process. Next, it was reduced into an informative dataset with location and time factors in the feature extraction process. The dataset was fed into three supervised ML classifiers, which include random forest (RF), artificial neural network (ANN) and long short-term memory (LSTM). Finally, their output was evaluated using the confusion matrix and compared to identify the best model for the accurate prediction of PM 2.5. Results Overall, the experimental result shows an accuracy of 97.7% was obtained by the RF model in comparison with the accuracy of ANN (61.14%) and LSTM (61.77%) in predicting PM 2.5. Discussion RF performed well when compared with ANN and LSTM for the given data with minimum features. RF was able to reach good accuracy as the model learns from the random samples by using decision tree with the maximum vote on the predictions.

Examination of the Performance of a Three-Phase Atmospheric Turbulence Model for Line-Source Dispersion Modeling Using Multiple Air Quality Datasets

One of the weaknesses of current line-source models for predicting downwind concentrations from mobile sources is accounting for the dispersion of effluents. Most of the investigators in the field have taken different approaches over the last 50 years, ranging from the use of Pasquill–Gifford (P-G) dispersion curves to the use of equations based on atmospheric turbulence for point source dispersion. Madiraju and Kumar (2021) proposed a three-phase turbulence (TPT) model using the key features of mobile source dispersion that appear in the existing literature. This paper examines the performance of line-source models using an updated TPT model. The generic dispersion equations were considered from the SLINE 1.1, CALINE 4, ADMS, and SLSM models. Multiple air quality field data sets collected by other investigators near the roadways were used during this study. These include field data collected from the Idaho Falls Tracer Experiment 2008 (used as the dataset to compare with the initial model), the CALTRANS Highway 99 Tracer experiment, and the Raleigh 2006 experiment. The predicted concentrations were grouped under unstable and stable atmospheric conditions. The evaluation of the model was performed using several statistical parameters such as FB, NMSE, R2, MG, VG, MSLE, and MAPE. The results indicate that the ADMS and SLINE 1.1 models perform better than CALINE4 and SLSM. SLINE 1.1 tends to overpredict for stable atmospheric conditions and underpredict for unstable atmospheric conditions. A trial test was performed to implement the TPT model in the basic line-source model (SLSM). The results indicate that the majority (FB, NMSE, R2, and MSLE) of the indicators have improved and are in the satisfactory range of a good model performance level.

Real-time image-based air quality estimation by deep learning neural networks

Air quality profoundly impacts public health and environmental equity. Efficient and inexpensive air quality monitoring instruments could be greatly beneficial for human health and air pollution control. This study proposes an image-based deep learning model (CNN−RC) that integrates a convolutional neural network (CNN) and a regression classifier (RC) to estimate air quality at areas of interest through feature extraction from photos and feature classification into air quality levels. The models were trained and tested on datasets with different combinations of the current image, the baseline image, and HSV (hue, saturation, value) statistics for increasing model reliability and estimation accuracy. A total of 3549 hourly air quality datasets (including photos, PM2.5, PM10, and the air quality index (AQI)) collected at the Linyuan air quality monitoring station of Kaohsiung City in Taiwan constituted the case study. The main breakthrough of this study is to timely produce an accurate image-based estimation of several pollutants simultaneously by using only one single deep learning model. The test results show that estimation accuracy in terms of R2 for PM2.5, PM10, and AQI based on daytime (nighttime) images reaches 76% (83%), 84% (84%), and 76% (74%), respectively, which demonstrates the great capability of our method. The proposed model offers a promising solution for rapid and reliable multi-pollutant estimation and classification based solely on captured images. This readily scalable measurement approach could address major gaps between air quality data acquired from expensive instruments worldwide.

Synthetic time series data generation for edge analytics

Background: Internet of Things (IoT) edge analytics enables data computation and storage to be available adjacent to the source of data generation at the IoT system. This method improves sensor data handling and speeds up analysis, prediction, and action. Using machine learning for analytics and task offloading in edge servers could minimise latency and energy usage. However, one of the key challenges in using machine learning in edge analytics is to find a real-world dataset to implement a more representative predictive model. This challenge has undeniably slowed down the adoption of machine learning methods in IoT edge analytics. Thus, the generation of realistic synthetic datasets can leverage the need to speed up methodological use of machine learning in edge analytics. Methods: We create synthetic data with features that are like data from IoT devices. We use an existing air quality dataset that includes temperature and gas sensor measurements. This real-time dataset includes component values for the Air Quality Index (AQI) and ppm concentrations for various polluting gases. We build a JavaScript Object Notation (JSON) model to capture the distribution of variables and the structure of this real dataset to generate the synthetic data. Based on the synthetic dataset and original dataset, we create a comparative predictive model. Results: Analysis of synthetic dataset predictive model shows that it can be successfully used for edge analytics purposes, replacing real-world datasets. There is no significant difference between the real-world dataset compared the synthetic dataset. The generated synthetic data requires no modification to suit the edge computing requirements. Conclusions: The framework can generate representative synthetic datasets based on JSON schema attributes. The accuracy, precision, and recall values for the real and synthetic datasets indicate that the logistic regression model is capable of successfully classifying data.

A New Collaborative Multi-Agent Monte Carlo Simulation Model for Spatial Correlation of Air Pollution Global Risk Assessment

Air pollution risk assessment is complex due to dynamic data change and pollution source distribution. Air quality index concentration level prediction is an effective method of protecting public health by providing the means for an early warning against harmful air pollution. However, air quality index-based prediction is challenging as it depends on several complicated factors resulting from dynamic nonlinear air quality time-series data, such as dynamic weather patterns and the verity and distribution of air pollution sources. Subsequently, some minimal models have incorporated a time series-based predicting air quality index at a global level (for a particular city or various cities). These models require interaction between the multiple air pollution sensing sources and additional parameters like wind direction and wind speed. The existing methods in predicting air quality index cannot handle short-term dependencies. These methods also mostly neglect the spatial correlations between the different parameters. Moreover, the assumption of selecting the most recent part of the air quality time series is not valid considering that pollution is cyclic behavior according to various events and conditions due to the high possibility of falling into the trap of local minimum and poor generalization. Therefore, this paper proposes a new air pollution global risk assessment (APGRA) prediction model for an air quality index of spatial correlations to address these issues. The APGRA model incorporates an autoregressive integrated moving average (ARIMA), a Monte Carlo simulation, a collaborative multi-agent system, and a prediction algorithm for reducing air quality index prediction error and processing time. The proposed APGRA model is evaluated based on Malaysia and China real-world air quality datasets. The proposed APGRA model improves the average root mean squared error by 41%, mean and absolute error by 47.10% compared with the conventional ARIMA and ANFIS models.

The Influence of Air Pollution on Pulmonary Disease Incidence Analyzed Based on Grey Correlation Analysis.

Air pollution is a primary health threat issue worldwide because it is closely concerned with respiratory diseases. A random survey reported that around 7 million people died because of ambient and household air pollution. Especially, the people suffering from asthma and chronic obstructive pulmonary disease (COPD) are highly affected by air pollutants. The air pollution components induce asthma onset and COPD acute exacerbation, which leads to maximized mortality and morbidity rate. Therefore, the influence of air pollution on COPD should be examined continuously to minimize the mortality rate. Several methods are presented in this field to investigate the relationship between health and pollutants. However, the existing approaches are only predicting the short-term data and have difficulties such as computation time, redundant data in large data analysis, and data continuity. Then, this research introduced the meta-heuristic optimized grey correlation analysis (MH-GCA) to solve the research difficulties. The correlation analysis has several models that identify the relationship between the pollution factors with COPD disease. The method analysis of the particulate matter (〖PM〗_10) in air pollution is more relevant to COPD and lung cancer disease. The grey analysis uses the uncertainty concept to identify the particle influence on air pollution. In the analysis, the cuttlefish optimization algorithm was applied to select more relevant features from the pollutant list that reduces the computation time and correlation analysis rate. The introduced system was evaluated using the air quality dataset and COPD dataset developed with the help of the MATLAB tool. The system increases the influence recognition accuracy (2.48%) and MCC (3.11%) and decreases the error rate (55.89%) for different pollutants.

Impact of Climate Change and Air Pollution Forecasting Using Machine Learning Techniques in Bishkek

During recent years, severe air-pollution problems have garnered worldwide attention due to their effects on human health and the environment. Air pollution in Bishkek, Kyrgyz Republic, is an ever-increasing problem with little research conducted on the impact of air pollutants on public health. We evaluate the performance of several machine learning algorithms applied to air quality and meteorology datasets and compare prediction accuracies of Bishkek air quality given its significant public importance. Data on 16 synoptic atmospheric process were collected by Kyrgyzhydromet from 2016 to 2018 and used to train and build a forecasting model. The model was then tested using data collected in 2020. Climate change in Bishkek and the impact on air pollution was assessed via the frequency of days characterized by daytime temperature inversions and air stagnation. Atmospheric stability increased from 2015 to 2020 with ongoing climate change leading to more temperature inversions. About 80%–90% of days with temperature inversions are associated with winter heating seasons and these numbers increased two-fold during the past 5 years. The impact of lockdown during COVID-19 (22 March–11 May 2020) on air quality in Bishkek is also shown. During the lockdown period, CO, NO, NO2, SO2, and PM2.5 decreased by 64%, 1.5%, 75%, 24%, and 54%, respectively, compared to concentrations of these pollutants in 2019. Where identified, emissions from vehicles make up a significant part of the air pollution.

Air Quality Index Prediction Based on Multilayer Perceptron

Taking the comprehensive evaluation index AQI as the research goal, the data of Beijing is studied, and an AQI prediction model based on multilayer perceptron neural network (MLP neural network) is proposed. First, the Beijing air quality dataset is constructed, and the AQIs from 2014 to 2019 are extracted as input features. Then, the air quality index of Beijing in 2020 is predicted based on MLP. After that, through parameter adjustment and model comparison, the final prediction accuracy reached 0.861.

A Novel Model Based on DA-RNN Network and Skip Gated Recurrent Neural Network for Periodic Time Series Forecasting

Deep learning models are playing an increasingly important role in time series forecasting with their excellent predictive ability and the convenience of not requiring complex feature engineering. However, the existing deep learning models still have shortcomings in dealing with periodic and long-distance dependent sequences, which lead to unsatisfactory forecasting performance on this type of dataset. To handle these two issues better, this paper proposes a novel periodic time series forecasting model based on DA-RNN, called DA-SKIP. Using the idea of task decomposition, the novel model, based on DA-RNN, GRU-SKIP and autoregressive component, breaks down the prediction of periodic time series into three parts: linear forecasting, nonlinear forecasting and periodic forecasting. The results of the experiments on Solar Energy, Electricity Consumption and Air Quality datasets show that the proposed model outperforms the three comparison models in capturing periodicity and long-distance dependence features of sequences.