READ ME File For 'Dataset in support of the Southampton doctoral thesis 'Machine learning for optimal unexploded ordnance mitigation'

Dataset DOI: 10.5258/SOTON/D2786

ReadMe Author: Sara Underhay, University of Southampton ORCID ID

This dataset supports the thesis entitled Machine learning for optimal unexploded ordnance mitigation'
AWARDED BY: Univeristy of Southampton
DATE OF AWARD: 2023

DESCRIPTION OF THE DATA


This dataset contains:

Python code for Magnetic Modeling and Machine Learning of Spheroids
The code is sub-divided into 3 folders:
Custom Packages: These are packages which will be called by the other scripts. 
Forward Modelling: This folder contains code for three stages.
- 01_Forward_Model_Perfect_Data: Use the parameter input file to determine the range of parameters to create in the dataset
-02_Realistic_Data_Conversion.py: Converts the newly created perfect dataset into a realistic dataset. The user can define multiple parameters within this script.
- 03_Feature_Extraction.py: This will extract features from the gridded data to be used in the machine learning.

Machine Learning: This folder contains code set up to train the Random Forest and Deep Learning examples models of both regression and classification.


Date of data collection: 12/11/2018-15/09/2023

Information about geographic location of data collection: 

Licence:
CC-BY


Date that the file was created: April, 2024

--------------