Can AI Predict Delhi’s Air Quality? LSTM Models Explained | Hindi скачать в хорошем качестве

Can AI Predict Delhi’s Air Quality? LSTM Models Explained | Hindi

Air quality modelling using long short-term memory (LSTM) over NCT-Delhi, India Author: Mrigank Krishan, Srinidhi Jha, Jew Das, Avantika Singh, Manish Kumar Goyal, Chandrra Sekar Air pollution monitoring and prediction have become critical challenges in rapidly urbanizing and industrializing cities. In recent years, NCT-Delhi has experienced a sharp rise in air pollution, frequently ranking among the most polluted cities in the world. Accurate forecasting of air quality is therefore essential for public health protection and effective policy planning. This video explores how Long Short-Term Memory (LSTM) neural networks can be used to predict key air pollutants—including O₃, PM₂.₅, NOₓ, and CO—at an urban location in Delhi. Unlike traditional machine-learning methods, LSTM models are capable of capturing long-term dependencies arising from the complex interaction of meteorology, traffic patterns, vehicular emissions, and human activities. The study evaluates LSTM performance using hourly air quality data from 2008 to 2010, testing five different combinations of input variables such as meteorological conditions, traffic data, and pollutant concentrations. Results demonstrate that LSTM models effectively handle the complexity of urban air pollution dynamics and provide highly reliable forecasts of ambient air quality. These findings highlight the potential of AI-driven air quality forecasting to support governments and policymakers in designing timely mitigation strategies, improving urban planning, and reducing the health impacts of worsening air pollution. DOI: https://doi.org/10.1007/s11869-019-00696-7 This video is created by Saral AI https://saral.democratiseresearch.in/