Prediction and assessment of the impact of COVID-19 lockdown on air quality over Kolkata: a deep transfer learning approach.

The present study focuses on the prediction and assessment of the impact of lockdown because of coronavirus pandemic on the air quality during three different phases, viz., normal periods (1 January 2018-23 March 2020), complete lockdown (24 March 2020-31 May 2020), and partial lockdown (1 June 2020-30 September 2020). We identify the most important air pollutants influencing the air quality of Kolkata during three different periods using Random Forest, a tree-based machine learning (ML) algorithm. It is found that the ambient air quality of Kolkata is mainly affected with the aid of particulate matter or PM (PM10 and PM2.5). However, the effect of the lockdown is most prominent on PM2.5 which spreads in the air of Kolkata due to diesel-driven vehicles, domestic and commercial combustion activities, road dust, and open burning. To predict urban PM2.5 and PM10 concentrations 24 h in advance, we use a deep learning (DL) model, namely, stacked-bidirectional long short-term memory (stacked-BDLSTM). The model is trained during the normal periods, and it shows the superiority over some supervised ML models, like support vector machine, K-nearest neighbor classifier, multilayer perceptron, long short-term memory, and statistical time series forecasting model autoregressive integrated moving average. This pre-trained stacked-BDLSTM is applied to predict the concentrations of PM2.5 and PM10 during the pandemic situation of two cases, viz., complete lockdown and partial lockdown using a deep model-based transfer learning (TL) approach (TLS-BDLSTM). Transfer learning aims to utilize the information gained from one problem to improve the predictive performance of a learning model for a different but related problem. Our work helps to demonstrate how TL is useful when there is a scarcity of data during the COVID-19 pandemic regarding the drastic change in concentration of pollutants. The results reveal the best prediction performance of TLS-BDLSTM with a lead time of 24 h as compared to some well-known traditional ML and statistical models and the pre-trained stacked-BDLSTM. The prediction is then validated using the real-time data obtained during the complete lockdown due to COVID second wave (16 May-15 June 2021) with different time steps, e.g., 24 h, 48 h, 72 h, and 96-120 h. TLS-BDLSTM involving transfer learning is seen to outperform the said comparing methods in modeling the long-term temporal dependency of multivariate time series data and boost the forecast efficiency not only in single step, but also in multiple steps. The proposed methodologies are effective, consistent, and can be used by operational organizations to utilize in monitoring and management of air quality.

Fuzzy rough sets, and a granular neural network for unsupervised feature selection.

A granular neural network for identifying salient features of data, based on the concepts of fuzzy set and a newly defined fuzzy rough set, is proposed. The formation of the network mainly involves an input vector, initial connection weights and a target value. Each feature of the data is normalized between 0 and 1 and used to develop granulation structures by a user defined α-value. The input vector and the target value of the network are defined using granulation structures, based on the concept of fuzzy sets. The same granulation structures are also presented to a decision system. The decision system helps in extracting the domain knowledge about data in the form of dependency factors, using the notion of new fuzzy rough set. These dependency factors are assigned as the initial connection weights of the proposed network. It is then trained using minimization of a novel feature evaluation index in an unsupervised manner. The effectiveness of the proposed network, in evaluating selected features, is demonstrated on several real-life datasets. The results of FRGNN are found to be statistically more significant than related methods in 28 instances of 40 instances, i.e., 70% of instances, using the paired t-test.