Skip to content

Machine Learning and Statistical Tests for Coastal Dune Classification

Notifications You must be signed in to change notification settings

GOItPadma/coastal_dune_analysis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

Coastal Dune Analysis using Machine Learning

This code is part of Master's Thesis titled Investigating the Dune Systems of Coastal Bangladesh Using Unmanned Aerial Vehicle (UAV): A Case Study at Sonadia Island.

Supervisor: Dr. M. Shahidul Islam , Professor, Department of Geography and Environment, University of Dhaka, Bangladesh

Synopsis

One of the main objectives of my research was to analyze the factors contributing to changes in coastal dunes. To achieve this goal:

  • I applied a one-way ANOVA test on 22 morphological, oceanographic, meteorological and anthropogenic factors to identify which factors have significant variations among four coastal dune classes.

  • Furthermore, I conducted a Jackknife Test with XGBoost machine learning model to determine the sensitive factors which have the highest contributions in classifying coastal dunes.

About

Machine Learning and Statistical Tests for Coastal Dune Classification

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published