Asosiy kontentga oʻtish
AkademIndex

Mahsulotlar

Ishlab chiquvchilar uchun

AkademBasetez oradaEkotizim uchun ochiq API
Lotin
Maqola

Air Quality Prediction by deep learning using Multimodal Data

S. ThangalakshmiSchool of Marine Engineering and Technology Indian Maritime University Mumbai Port Campus,Mumbai,Maharashtra,IndiaS. ManikandanSaveetha Engineering College,Department of ECE,Chennai,IndiaPerla AnithaKalasalingam Academy of Research and Education,Department of Computer Application,Srivillipudur,IndiaKhaja MannanuddinSchool of CS&AI SR University,Department of CSE,Warangal,IndiaHayitov Abdulla NurmatovichUrgench State University,Department of Transports Systems,Urgench,UzbekistanP. ShanthiAMET University,Department of EEE,Chennai,IndiaB. VenkataramanaiahVel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology,Department of ECE,Chennai,India
2025
ABI

Annotatsiya

Air pollution is one of the most serious environmental and health problems faced globally, and the problem is expected to worsen with rapid industrialization and urbanization. Leveraging multi-modal data sources — such as historical air pollution data, satellite data, weather, and socioeconomic factors — this project aims to predict real time and future air quality levels. Machine learning methods, particularly Convolutional Neural Networks (CNNs) will be applied to key pollutants such as NO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> and CO, to construct pollution forecasting trends and pinpoint areas of higher risk. Moreover, by taking the spatial and temporal variations in pollution levels into account, statistical and deep learning methods will be integrated into the system to further enhance prediction accuracy.The phenomenon study will assess these issues alongside the effects of air pollution on human health in general, with respiratory diseases as the overarching health indicator, as well as on all-cause mortality. By pin-pointing pollution hotspots, the project plans to alert affected populations in advance and propose possible interventions. Additionally, global forecasts will allow policymakers to design evidence-based policies for reducing the detrimental effects of air pollution. As socio-economic parameters will be induced, we will be able to explore the relationship of industrialisation, population density and urban development with pollution trends.This project aims to provide actionable insights for environmental agencies and urban planners through large-scale data analysis and predictive modelling. The results will contribute to the design of effective policies for pollution control, increase public awareness, and foster sustainable urban development. Overall, this study adds a more comprehensive and transcendental perspective of pollution, its development through time, as well as its definitive health and environmental impacts.

Mavzular

Identifikatorlar

Iqtiboslar va manbalar

Koʻrsatkichlar — AkademScholar · Tez orada