AIR QUALITY INDEX FORECASTING USING HYBRID NEURAL NETWORK MODEL WITH LSTM ON AQI SEQUENCES

Apply

AIR QUALITY INDEX FORECASTING USING HYBRID NEURAL NETWORK MODEL WITH LSTM ON AQI SEQUENCES

Journal Title: Proceedings on Engineering Sciences - Year 2020, Vol 2, Issue 4

Abstract

This paper presents an approach to forecasting air pollution levels measured as Air Quality Index (AQI) metric using hybrid Long Short-Term Memory (LSTM) models. The pollution levels have been found to vary in a particular pattern that depends on both the overall climate or season as well as the hour of the day. The hybrid model captures these 2 patterns and makes the prediction of AQI of some future hour. It employs 2 separate LSTM models that are trained on time-series data of AQI gathered at different time lags i.e. hourly and daily. The final output is given as a weighted sum of the 2 outputs produced by LSTM model. Upon comparing the performance of the standalone hour-wise forecasting LSTM model and the hybrid model it was found the latter gives the minimum error metric given an appropriate weight is chosen.

Authors and Affiliations

Shirshendu Roy, Pratyay Mukherjee

Keywords

LSTM; Hybrid model; AQI forecast; Time series

ANALYSIS OF THE OVERALL EQUIPMENT EFFECTIVENESS TO MINIMIZE SIX BIG LOSSES OF COOKIE CAPPER MACHINE-A CASE STUDY IN MANUFACTURING INDUSTRY

Overall Equipment Effectiveness (OEE) is a method of measuring the effectiveness of the use of equipment. This method is known as an application of a Total Productive Maintenance (TPM) program. The ability to clearly ide...

EP ID EP690460
DOI 10.24874/PES0204.010
Views 167
Downloads 0