The streams provide numerous downstream and upstream benefits, some of which are maintaining the quality and quantity of drinking water, filtering pollutants, supplying food and providing habitat for wildlife and plants, and flood protection. The main characteristic of intermittent streams is the water flow during certain times of the year when groundwater and runoff from precipitation provide water for streamflow. Between July 2018 and October 2021, 509 nodes that were stationed along the Valfredda stream and monitored the spatio-temporal dynamics of the active river network were observed on 30 occasions. In this study, climatic and geomorphic datasets and machine learning are used to predict the existence of intermittent streams along the Valfredda river in northern Italy. The prediction is made by performing the classification of the node's state where various sets of features are explored in order to determine the measurable characterization of the fundamental geomorphoclimatic causes and effects. Different time ranges were used to test the sensitivity of the nodes and the influence of time-series data.
The streams provide numerous downstream and upstream benefits, some of which are maintaining the quality and quantity of drinking water, filtering pollutants, supplying food and providing habitat for wildlife and plants, and flood protection. The main characteristic of intermittent streams is the water flow during certain times of the year when groundwater and runoff from precipitation provide water for streamflow. Between July 2018 and October 2021, 509 nodes that were stationed along the Valfredda stream and monitored the spatio-temporal dynamics of the active river network were observed on 30 occasions. In this study, climatic and geomorphic datasets and machine learning are used to predict the existence of intermittent streams along the Valfredda river in northern Italy. The prediction is made by performing the classification of the node's state where various sets of features are explored in order to determine the measurable characterization of the fundamental geomorphoclimatic causes and effects. Different time ranges were used to test the sensitivity of the nodes and the influence of time-series data.
Applying Machine Learning Models for predicting stream network dynamics
KARTALOVIC, SARA
2022/2023
Abstract
The streams provide numerous downstream and upstream benefits, some of which are maintaining the quality and quantity of drinking water, filtering pollutants, supplying food and providing habitat for wildlife and plants, and flood protection. The main characteristic of intermittent streams is the water flow during certain times of the year when groundwater and runoff from precipitation provide water for streamflow. Between July 2018 and October 2021, 509 nodes that were stationed along the Valfredda stream and monitored the spatio-temporal dynamics of the active river network were observed on 30 occasions. In this study, climatic and geomorphic datasets and machine learning are used to predict the existence of intermittent streams along the Valfredda river in northern Italy. The prediction is made by performing the classification of the node's state where various sets of features are explored in order to determine the measurable characterization of the fundamental geomorphoclimatic causes and effects. Different time ranges were used to test the sensitivity of the nodes and the influence of time-series data.File | Dimensione | Formato | |
---|---|---|---|
Sara Kartalovic_Data_Science_MsC_Thesis.pdf
accesso aperto
Dimensione
2.31 MB
Formato
Adobe PDF
|
2.31 MB | Adobe PDF | Visualizza/Apri |
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
https://hdl.handle.net/20.500.12608/43123