With the economic development in China, haze risks are frequent. It is important to study the urban haze risk assessment to manage the haze disaster. The haze risk assessment indexes of 11 cities in Fenwei Plain were selected from three aspects: the sensitivity of disaster-inducing environments, haze component hazards and the vulnerability of disaster-bearing bodies, combined with regional disaster system theory. The haze hazard risk levels of 11 cities in Fenwei Plain were evaluated using the matter-element extension (MEE) model, and the indicator weights were determined by improving the principal component analysis (PCA) method using the entropy weight method, and finally, five haze hazard risk assessment models were established by improving the particle swarm optimization (IPSO) light gradient boosting machine (LightGBM) algorithm. It is used to assess the risk of affected populations, transportation damage risk, crop damage area risk, direct economic loss risk and comprehensive disaster risk before a disaster event occurs. The experimental comparison shows that the haze risk index of Xi’an city is the highest, and the full index can improve the evaluation accuracy by 4–16% compared with only the causative factor index, which indicates that the proposed PCA-MEE-ISPO-LightGBM model evaluation results are more realistic and reliable.

Air pollution has become a serious problem threatening human health. Effective prediction models can help reduce the adverse effects of air pollutants. Accurate predictions of air pollutant concentration can provide a scientific basis for air pollution prevention and control. However, the previous air pollution-related prediction models mainly processed air quality prediction, or the prediction of a single or two air pollutants. Meanwhile, the temporal and spatial characteristics and multiple factors of pollutants were not fully considered. Herein, we establish a deep learning model for an atmospheric pollutant memory network (LSTM) by both applying the one-dimensional multi-scale convolution kernel (ODMSCNN) and a long-short-term memory network (LSTM) on the basis of temporal and spatial characteristics. The temporal and spatial characteristics combine the respective advantages of CNN and LSTM networks. First, ODMSCNN is utilized to extract the temporal and spatial characteristics of air pollutant-related data to form a feature vector, and then the feature vector is input into the LSTM network to predict the concentration of air pollutants. The data set comes from the daily concentration data and hourly concentration data of six atmospheric pollutants (PM_2.5, PM₁₀, NO₂, CO, O₃, SO₂) and 17 types of meteorological data in Xi’an. Daily concentration data prediction, hourly concentration data prediction, group data prediction and multi-factor prediction were used to verify the effectiveness of the model. In general, the air pollutant concentration prediction model based on ODMSCNN-LSTM shows a better prediction effect compared with multi-layer perceptron (MLP), CNN, and LSTM models.

With the rapid development of China’s industrialization, air pollution is becoming more and more serious. Predicting air quality is essential for identifying further preventive measures to avoid negative impacts. The existing prediction of atmospheric pollutant concentration ignores the problem of feature redundancy and spatio-temporal characteristics; the accuracy of the model is not high, the mobility of it is not strong. Therefore, firstly, extreme gradient lifting (XGBoost) is applied to extract features from PM_2.5, then one-dimensional multi-scale convolution kernel (MSCNN) is used to extract local temporal and spatial feature relations from air quality data, and linear splicing and fusion is carried out to obtain the spatio-temporal feature relationship of multi-features. Finally, XGBoost and MSCNN combine the advantages of LSTM in dealing with time series. Genetic algorithm (GA) is applied to optimize the parameter set of long-term and short-term memory network (LSTM) network. The spatio-temporal relationship of multi-features is input into LSTM network, and then the long-term feature dependence of multi-feature selection is output to predict PM_2.5 concentration. A XGBoost-MSCGL of PM_2.5 concentration prediction model based on spatio-temporal feature selection is established. The data set comes from the hourly concentration data of six kinds of atmospheric pollutants and meteorological data in Fen-Wei Plain in 2020. To verify the effectiveness of the model, the XGBoost-MSCGL model is compared with the benchmark models such as multilayer perceptron (MLP), CNN, LSTM, XGBoost, CNN-LSTM with before and after using XGBoost feature selection. According to the forecast results of 12 cities, compared with the single model, the root mean square error (RMSE) decreased by about 39.07%, the average MAE decreased by about 42.18%, the average MAE decreased by about 49.33%, but R² increased by 23.7%. Compared with the model after feature selection, the root mean square error (RMSE) decreased by an average of about 15%. On average, the MAPE decreased by 16%, the MAE decreased by 21%, and R² increased by 2.6%. The experimental results show that the XGBoost-MSCGL prediction model offer a more comprehensive understanding, runs deeper levels, guarantees a higher prediction accuracy, and ensures a better generalization ability in the prediction of PM_2.5 concentration.

Fine particulate matter (PM_2.5) has a continuing impact on the environment, climate change and human health. In order to improve the accuracy of PM_2.5 estimation and obtain a continuous spatial distribution of PM_2.5 concentration, this paper proposes a LUR-GBM model based on land-use regression (LUR), the Kriging method and LightGBM (light gradient boosting machine). Firstly, this study modelled the spatial distribution of PM_2.5 in the Chinese region by obtaining PM_2.5 concentration data from monitoring stations in the Chinese study region and established a PM_2.5 mass concentration estimation method based on the LUR-GBM model by combining data on land use type, meteorology, topography, vegetation index, population density, traffic and pollution sources. Secondly, the performance of the LUR-GBM model was evaluated by a ten-fold cross-validation method based on samples, stations and time. Finally, the results of the model proposed in this paper are compared with those of the back propagation neural network (BPNN), deep neural network (DNN), random forest (RF), XGBoost and LightGBM models. The results show that the prediction accuracy of the LUR-GBM model is better than other models, with the R² of the model reaching 0.964 (spring), 0.91 (summer), 0.967 (autumn), 0.98 (winter) and 0.976 (average for 2016–2021) for each season and annual average, respectively. It can be seen that the LUR-GBM model has good applicability in simulating the spatial distribution of PM_2.5 concentrations in China. The spatial distribution of PM_2.5 concentrations in the Chinese region shows a clear characteristic of high in the east and low in the west, and the spatial distribution is strongly influenced by topographical factors. The seasonal variation in mean concentration values is marked by low summer and high winter values. The results of this study can provide a scientific basis for the prevention and control of regional PM_2.5 pollution in China and can also provide new ideas for the acquisition of data on the spatial distribution of PM_2.5 concentrations within cities.

As VOCs pose a threat to human health, it is important to accurately capture changes in VOCs concentrations and sense VOCs concentrations in relevant areas. Therefore, it is necessary to improve the accuracy of VOCs concentration prediction and realise the VOCs aggregation situation sensing. Firstly, on the basis of regional grid division, the inverse distance spatial interpolation method is used for spatial interpolation to collect regional VOCs data information. Secondly, extreme gradient boosting (XGBoost) is used for spatio-temporal feature selection, combined with graph convolutional neural network (GCN) to construct regional spatial relationships of VOCs, and multiple linear regression (MLR) to process VOCs time series data and predict the VOCs concentration in the grid. Finally, the aggregation potential values of VOCs are calculated based on the prediction results, and the potential perception results are visualised. A VOCs aggregation perception method based on concentration prediction is proposed, using the XGBoost-GCN-MLR method with a scenario-aware approach for VOCs to perceive the VOCs aggregation in the relevant region. VOCs concentration prediction and VOCs aggregation trend perception were carried out in Xi’an, Baoji, Tongchuan, Weinan and Xianyang. The results show that compared with the GCN model, XGBoost model, MLR model and GCN-MLR model, the XGBoost-GCN-MLR model reduces the input variables, achieves the optimisation of the input parameters of the VOCs concentration prediction model, reduces the complexity of the prediction model and improves the prediction accuracy. Intelligent sensing of VOCs aggregation can visualise the regional VOCs. The intelligent sensing of VOCs aggregation can visualise the development trend and status of regional VOCs aggregation and convey more information, which has practical value.

As energy demand continues to increase, the environmental pollution problem is becoming more severe. Governments and researchers have made great efforts to avoid and reduce air pollution. The prediction of PM_2.5, as an important index affecting air quality, has great significance. However, PM_2.5 concentration has a complex change process that makes its prediction challenging. By calculating both PM_2.5 concentration and that of other pollutants in the atmosphere and meteorological factors, it is evident that the variation in PM_2.5 concentration is influenced by multiple factors, and that relevant features also influence each other. To reduce the calculated loss, with full consideration given to the influencing factors, we used the maximum correlation and minimum redundancy (MRMR) algorithm to calculate the correlation and redundancy between features. In addition, it is known from the Brock–Dechert–Scheinman (BDS) statistical results that the change in PM_2.5 is nonlinear. Due to the outstanding performance of bidirectional long short-term memory (BiLSTM) neural networks in nonlinear prediction, we constructed an encoder–decoder model based on BiLSTM, named ED-BiLSTM, to predict the PM_2.5 concentration at monitoring stations. For areas without monitoring sites, due to the lack of historical data, the application of neural networks is limited. To obtain the pollutant concentration distribution in the study area, we divided the study area into a 1 km × 1 km grid and combined the ED-BiLSTM model via the use of the inverse distance weighting (IDW) algorithm to obtain the PM_2.5 concentration values in a region without monitoring stations. Finally, ArcGIS was used to visualize the results. The data for the case study were obtained from Xi’an. The results show that, compared with the standard long short-term memory (LSTM) model, the RMSE, MAE, and MAPE of our proposed model were reduced by 24.06%, 24.93%, and 22.9%, respectively. The proposed model has a low error for PM_2.5 prediction and can provide a theoretical basis for the formulation of environmental protection policies.