With the development of the data-driven modeling techniques, using the neural network to simulate the transport process of atmospheric pollutants and constructing PM2.5 time-series prediction model have become a hot topic. The existing data-driven approaches often ignore the dynamical relationships among multiple sites in urban areas, which results in nonideal prediction accuracy. In response to this problem, this article proposes a long short-term memory (LSTM) autoencoder multitask learning model to predict PM2.5 time series in multiple locations city wide. The model could implicitly and automatically excavate the intrinsic relevance among the pollutants in different stations. And the meteorological information from the monitoring stations is fully utilized, which is beneficial for the performance of the proposed model. Specifically, multilayer LSTM networks can simulate the spatiotemporal characteristics of urban air pollution particles. And using the stacked autoencoder to encode the key evolution pattern of urban meteorological systems could provide important auxiliary information for PM2.5 time-series prediction. In addition, multitask learning could automatically discover the dynamical relationship between multiple key pollution time series and solve the problem of insufficient use of multisite information in the modeling process of the traditional data-driven methods. The simulation results of PM2.5 prediction in Beijing indicate the effectiveness of the proposed method.

Water quality prediction, a well-established field with broad implications across various sectors, is thoroughly examined in this comprehensive review. Through an exhaustive analysis of over 170 studies conducted in the last five years, we focus on the application of machine learning for predicting water quality. The review begins by presenting the latest methodologies for acquiring water quality data. Categorizing machine learning-based predictions for water quality into two primary segments—indicator prediction and water quality index prediction—further distinguishes between single-indicator and multi-indicator predictions. A meticulous examination of each method’s technical details follows. This article explores current cutting-edge research trends in machine learning algorithms, providing a technical perspective on their application in water quality prediction. It investigates the utilization of algorithms in predicting water quality and concludes by highlighting significant challenges and future research directions. Emphasis is placed on key areas such as hydrodynamic water quality coupling, effective data processing and acquisition, and mitigating model uncertainty. The paper provides a detailed perspective on the present state of application and the principal characteristics of emerging technologies in water quality prediction.

With the acceleration of urbanization, there is an increasing trend of heavy pollution. PM_2.5, also known as fine particulate matter, refers to particles in the atmosphere with a diameter of less than or equal to 2.5 microns. PM_2.5 has a serious impact on human life, a sustainable city, national economic development, and so on. How to forecast the PM_2.5 concentration accurately, and then formulate a scientific air pollution prevention and monitoring program is of great significance. This paper proposes a hybrid model based on echo state network (ESN) and an improved particle swarm optimization (IPSO) algorithm for the Beijing air pollution problem, and provides a method for PM_2.5 concentration forecasting. Firstly, the PSO algorithm is improved to speed up the search performance. Secondly, the optimal subset of the original data is selected by the convergence cross-mapping (CCM) method. Thirdly, the phase space reconstruction (PSR) process is combined with the forecasting model, and some parameters are optimized by the IPSO. Finally, the optimal variable subset is used to predict PM_2.5 concentration. The 11-dimensional air quality data in Beijing from January 1 to December 31, 2016 are analyzed by the proposed method. The experimental results show that the hybrid method is superior to other comparative models in several evaluation indicators, both in one-step and multi-step forecasting of PM_2.5 time series. The hybrid model has good application prospects in air quality forecasting and monitoring.

Air pollution has become a global environmental problem, because it has a great adverse impact on human health and the climate. One way to explore this problem is to monitor and predict air quality index in an economical way. Accurate monitoring and prediction of air quality index (AQI), e.g., PM_2.5 concentration, is a challenging task. In order to accurately predict the PM_2.5 time series, we propose a supplementary leaky integrator echo state network (SLI-ESN) in this paper. It adds the historical state term of the historical moment to the calculation of leaky integrator reservoir, which improves the influence of historical evolution state on the current state. Considering the redundancy and correlation between multivariable time series, minimum redundancy maximum relevance (mRMR) feature selection method is introduced to reduce redundant and irrelevant information, and increase computation speed. A variety of evaluation indicators are used to assess the overall performance of the proposed method. The effectiveness of the proposed model is verified by the experiment of Beijing PM_2.5 time series prediction. The comparison of learning time also shows the efficiency of the algorithm.

Evolving fuzzy system (EFS), a special adaptive model with Takagi-Sugeno (TS) fuzzy rules that can adaptively update internal parameters based on data streams, has been widely used in online learning scenarios. However, current EFSs are mainly single-layer models, which cannot adequately capture hidden information in multidimensional chaotic time series. To perform online prediction of multidimensional chaotic time series, a novel evolving fuzzy system, called hierarchical evolving fuzzy system with kernel conjugate gradient (HEFS-KCG), is proposed in this paper. HEFS-KCG excavates and captures latent evolutionary patterns concealed within dynamic systems through a layer-by-layer processing of multidimensional information. HEFS-KCG performs structural evolution based on data distribution in the antecedent part, and combines the sparse learning strategy and kernel conjugate gradient (KCG) to update the consequent parameters. Subsequently, we provide a theoretical analysis of HEFS-KCG, ensuring its convergence when applied to online prediction. The simulation results demonstrate that HEFS-KCG outperforms existing EFSs and other models for multidimensional chaotic time series online prediction.