Predictive Analysis on Drought in North America using Deep Learning

Dubey, Sadhvi Rajkumar (2022) Predictive Analysis on Drought in North America using Deep Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (4MB) | Preview
Preview	PDF (Configuration manual) Download (2MB) | Preview

Abstract

The devastating effects of previous drought episodes around the world have prompted considerable drought monitoring and forecast efforts. Various drought information systems with various indicators have already been developed to provide early drought warning. The United States Drought Monitor (USDM), which uses numerous drought categories to classify drought severity and has been used to evaluate and manage by a variety of users such as natural resource managers and authorities, has played a critical part in drought monitoring. The development of drought prediction using USDM drought categories will significantly improve decision-making due to the numerous applications of USDM. This study presented a cross region drought prediction using machine learning model as we can see different climatic condition in different part of United states. To conduct this research we have used USDM dataset which will provide us reliable data from 2000 to present date. The results of USDM drought classification forecasts in the United States show the system’s potential, which is projected to contribute to operational early drought warning in the United States. In this paper we put forward a novel cross region drought predicting model in which we will do comparative study using statistical model and machine learning model which will intern provide us most accurate drought prediction. This model can also be used for predicting drought for any country. In comparison to ANN and KNN-based models, LSTM-based models were able to capture the temporal and spatial properties of droughts over the United States better in validation. KNN, which was used for the first time in constructing drought models, performed badly as compared to LSTM and ANNbased drought models.

Item Type:	Thesis (Masters)
Subjects:	G Geography. Anthropology. Recreation > GE Environmental Sciences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	24 Jan 2023 12:27
Last Modified:	03 Mar 2023 13:54
URI:	https://norma.ncirl.ie/id/eprint/6112

Actions (login required)

View Item