Classification of soil quality using K-Nearest Neighbors methods

I. D. Ratih*, S. M. Retnaningsih, V. M. Dewi

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

Abstract

The damage or deterioration of the material due to reaction with the environment is called corrosion. The corrosive of soil can cause natural disasters such as landslides. Soil corrosivity is a serious problem in industrial and infrastructure activities. Soil corrosivity is also a problem at PT. IPMOMI, because of the large number of metal pipes that are planted underground which functions to drain fluid in the form of seawater as the main material for steam production. PT. IPMOMI wants to install metal pipes underground, Therefore PT. IPMOMI requires information about the status of soil corrosivity at that location. To overcome soil corrosivity, PT. IMOMI will install cathodic protection on the soil with high corrosivity. One of the efforts to deal with this problem is by mapping the subsurface corrosion zone. Before mapping the corrosion zone, it is necessary to know the level of soil corrosivity whether it is very high, high, medium, low, or very low. So that to determine the level of soil corrosivity whether very high, high, medium, low, or very low, a classification method is needed. In this study, the classification method used is the nonparamteric classification method, namely K Nearest Neigbors. The results of classification accuracy were 83.3% and variable chargebility had a higher contribution than the depth level in the classification model.

Original languageEnglish
Article number012011
JournalIOP Conference Series: Earth and Environmental Science
Volume739
Issue number1
DOIs
Publication statusPublished - 26 Apr 2021
Event1st Universitas Lampung International Conference on Science, Technology and Environment, ULICOSTE 2020 - Bandar Lampung, Virtual, Indonesia
Duration: 18 Nov 202019 Nov 2020

Fingerprint

Dive into the research topics of 'Classification of soil quality using K-Nearest Neighbors methods'. Together they form a unique fingerprint.

Cite this