Interpretation of black box for short-term predictions of pre-monsoon cumulonimbus cloud events over Kolkata

Dutta, Debashree; Pal, Sankar K.

doi:10.1007/s42488-022-00071-9

Cited by 7 publications

(3 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The larger the number is, the better the learning performance. Deep learning (DL) technique has been applied for a wide variety of problems such as object detection, weather prediction, motion modeling, image classification, natural language processing, speech recognition, and synthesis (Chakraborty & Pal, 2021 ; Dutta & Pal, 2022a ; Hinton et al, 2012 ; Krizhevsky et al, 2017 ; LeCun et al, 2015 ; Pal et al, 2021 ; Young et al, 2018 ; Zhang et al, 2013 ). Since the air pollution data is big in nature, the use of a DL-based data-driven model in conjunction with advanced artificial intelligence (AI) tools for accurate representation and prediction of the air quality depending on weather and several factors appears to be logical and appropriate.…”

Section: Introductionmentioning

confidence: 99%

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

Dutta

Pal

2022

Environ Monit Assess

Self Cite

View full text Add to dashboard Cite

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 (PM 10 and PM 2.5 ). However, the effect of the lockdown is most prominent on PM 2.5 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 PM 2.5 and PM 10 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 PM 2.5 and PM 10 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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Dutta

Pal

2022

Environ Monit Assess

Self Cite

View full text Add to dashboard Cite

show abstract

“…proposed an interpretable model architecture for Solar Irradiation forecasting using SHAP and Perturbation Feature Importance. The impact of individual feature values on the model outputs have been studied using SHAP framework and duration and radiation has been concluded as the most influential features[45] Dutta et al, (2022). produced SHAP explanations to analyze the feature importance towards the model output for thunderstorm prediction models.…”

mentioning

confidence: 99%

“…produced SHAP explanations to analyze the feature importance towards the model output for thunderstorm prediction models. XGBoost and Logistic Regression based NWP models are trained and SHAP package has been used to generate local and global explanations[46] Kondylatos et al, (2022). proposed a Recurrent Neural Network based model for Wildfire prediction and used SHAP explanations to analyze the marginal contributions of each of the features used in the model development.…”

mentioning

confidence: 99%

Hybrid Explainable SRNN-LSTM Architecture for Irradiance, Temperature and Wind Speed Forecasting

Rajasekaran,

et al. 2023

Preprint

View full text Add to dashboard Cite

Sustainable Energy alternatives such as Solar Energy, Wind Energy are the best alternatives to the harmful Non-Renewable energy sources like fossil fuels. With the increasing investment made in the Sustainable Energy alternatives, forecasting of Energy production from the farms plays a crucial in the structured design of Energy farms and for integrated smart grid management. In this research, we propose SRNN-LSTM hybrid models for univariate solar irradiance forecasting, multivariate temperature forecasting and univariate forecasting of Wind Speed. The proposed models are evaluated based on RMSE, MAE, r2 score and Index of Agreement error metrics. The SRNN16LSTM16 hybrid models achieves the best performance with r2 score of 0.97 for Solar Irradiance forecasting and SRNN8LSTM8 hybrid model achieves the best performance with the r2 Score of 0.989 and RMSE of 0.122 for Wind Speed forecasting. We have also proposed a simple approach to derive the prediction intervals based on the Median of the residual values. The higher values of PICP error metric indicate that the proposed models are efficient and perform better than the state-of-the-art models used in the forecasting frameworks. We have also performed the Model Analysis using Explainable Artificial Intelligence tools such as LIME and ELI5 to analyze the importance of features in the model development process, generating and analyzing local explanations.

show abstract

The two-stage integrated allocation model for local emergency supplies

Yang,

Xu,

Feng

et al. 2023

J. of Data, Inf. and Manag.

View full text Add to dashboard Cite

Interpretation of black box for short-term predictions of pre-monsoon cumulonimbus cloud events over Kolkata

Cited by 7 publications

References 53 publications

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

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

Hybrid Explainable SRNN-LSTM Architecture for Irradiance, Temperature and Wind Speed Forecasting

The two-stage integrated allocation model for local emergency supplies

Contact Info

Product

Resources

About