This thesis project aims at studying the complex relation between air quality, water quality, and the weather. We will analyze data on air quality index (AQI) and water quality/quantity, obtained by probes placed outdoors and in the sewages. The first step will be to obtain a proper data set for analysis, integrating several measurements from the pre-existing ARPA database. The second step will consist of using machine-learning and other techniques for the analysis of complex multivariate time series to obtain a model of the joint time evolution of water and air quality, and their modulation by key meteorological parameters (such as rainfall, temperature, and humidity), considered as external forcing factors. Finally, we will assess the model's performance in forecasting.

Modeling the weather's influence on air and water quality

CHATURVEDI, PANKHURI
2025/2026

Abstract

This thesis project aims at studying the complex relation between air quality, water quality, and the weather. We will analyze data on air quality index (AQI) and water quality/quantity, obtained by probes placed outdoors and in the sewages. The first step will be to obtain a proper data set for analysis, integrating several measurements from the pre-existing ARPA database. The second step will consist of using machine-learning and other techniques for the analysis of complex multivariate time series to obtain a model of the joint time evolution of water and air quality, and their modulation by key meteorological parameters (such as rainfall, temperature, and humidity), considered as external forcing factors. Finally, we will assess the model's performance in forecasting.
2025
This thesis project aims at studying the complex relation between air quality, water quality, and the weather. We will analyze data on air quality index (AQI) and water quality/quantity, obtained by probes placed outdoors and in the sewages. The first step will be to obtain a proper data set for analysis, integrating several measurements from the pre-existing ARPA database. The second step will consist of using machine-learning and other techniques for the analysis of complex multivariate time series to obtain a model of the joint time evolution of water and air quality, and their modulation by key meteorological parameters (such as rainfall, temperature, and humidity), considered as external forcing factors. Finally, we will assess the model's performance in forecasting.
Forecasting
LSTM, R
Prediction model
File in questo prodotto:
File Dimensione Formato  
Chaturvedi_Pankhuri-pdfa-1b.pdf

Accesso riservato

Dimensione 3.34 MB
Formato Adobe PDF
3.34 MB Adobe PDF

The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12608/113154