EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

805. Greenhouse gases levels prediction using artificial neural networks

Invited abstract in session WC-28: Advancements of OR-analytics in statistics, machine learning and data science 10, stream Advancements of OR-analytics in statistics, machine learning and data science.

Wednesday, 12:30-14:00
Room: 065 (building: 208)

Authors (first author is the speaker)

1. Hugo Valadares Siqueira
Instituto Brasileiro de Informação em Ciência e Tecnologia
2. Thiago Antonini Alves
Department of Mechanical Engineering, Federal University of Technology - Parana
3. Tiago Emmanuel Nunes Braga
Instituto Brasileiro de Informação em Ciência e Tecnologia
4. Ricardo Godoi
Federal University of Parana
5. Yara Tadano
Federal University of Technology - Parana

Abstract

The increase of greenhouse gas (GHG) levels alters the energy balance between the atmosphere and the Earth surface, leading to temperature changes that modifies the atmosphere chemical composition. Then, the air pollution represents one important index to be analyzed, as it is directly related to climate changes mitigation goals. The development of a public tool that allows future predictions of potential GHG environmental impacts are essential to the economy, environment and social and health aspects. In this sense, the development of systems for monitoring, forecasting, and controlling emissions plays an important role. The main objective of this research is to apply trainable and non-trainable combination methods for air pollution forecasting in Brazil. Trainable ensembles based on Artificial Neural Networks (ANN) and linear regression are compared with non-trainable combinations, single ANN, and linear statistical approaches. Different models are considered so far, including Autoregressive Model, Autoregressive and Moving Average Model, Infinite Impulse Response Filters, Multilayer Perceptron, Radial Basis Function Networks, Extreme Learning Machines, and Echo State Networks. The use of trainable ensembles led to a better performance. The use of robust tools is paramount to help governments in managing air pollution issues like hospital collapse during adverse air quality situations.

Keywords

Status: accepted

Back to the list of papers