IBM Z and LinuxONE - Software - Group home

NASA Project; Plastic Marine Debris Classification-Machine Learning Software

By Emirhan BULUT posted Thu October 21, 2021 12:41 PM

NASA Project; I Developed Plastic Marine Debris Classification-Machine Learning Software. Plastic, metal, etc. in this software. various waste and garbage; Classified by seasons, by photos they have, by country, by date (year) and shoreline name, with high accuracy, precision, sharpness and f1 results. The models were carefully prepared and examined one by one. Damages in the data have been corrected and made suitable for artificial intelligence. Some (.dot) files have a high number of megabytes and strings, so (.png) was uploaded unformatted due to my insufficient resources. This software has been prepared by me personally for the NASA Project.

With this project, plastic, metal, etc. found in marine debris. I have provided the classification of derivative wastes according to various parameters (date, country, etc.). The machine learning software I have created works with high accuracy (The highest classification model accuracy rate is about 97%). The project regularizes the irregularity of the various data and solves the complex plastic proportions in which country they occur, in what year.

The values you enter should be (respectively):

Example: model_nasa_emirhan = ExtraTreesClassifier(criterion="gini",

Outpot :
0.9788235294117648 x 1 0.978506841585555 0.9788235294117648 0.9783583602026715
Index(['Country_Change'], dtype='object') Extra Trees in forest :)
1 saved as dot file 0 Extra Trees in forest :)
2 saved as dot file 1 Extra Trees in forest :)
3 saved as dot file 2 Extra Trees in forest :)
4 saved as dot file 3 Extra Trees in forest :)
5 saved as dot file 4 Extra Trees in forest :)
6 saved as dot file 5 Extra Trees in forest :)
7 saved as dot file 6`` Extra Trees in forest :)
8 saved as dot file 7 Extra Trees in forest :)
9 saved as dot file 8 Extra Trees in forest :)
10 saved as dot file 9 
Process finished with exit code 0

I am happy to present this software to you!

Data Source: DataSource

###The coding language used:

  • Python >= 3.9.6
###Libraries Used:

  • Sklearn
  • Pandas
  • Numpy

Developer Information:

Name-Surname: Emirhan BULUT

Contact (Email) :

LinkedIn :

Official Website:

Project Kaggle Link: