Prediction of land-change using machine learning for the deforestation in paraguay

Max Muller; Shweta Vincent; Om Prakash Kumar

doi:10.11591/eei.v9i5.2532

Prediction of land-change using machine learning for the deforestation in paraguay

Max Muller
, Shweta Vincent^*
, Om Prakash Kumar

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

5 Citations (Scopus)

Abstract

Northwestern Paraguay is being deforested at a very rapid rate. This article studies the rate of deforestation that has happened in this area using satellite images of LandSAT5 and LandSAT7. The rate of the deforestation is detected from 1986 to 2011, graphically using which future prediction is made. The images of LandSAT8 are used to validate the prediction made until 2018. An extrapolation of the graph shows that the process of deforestation is already 3 years ahead of its forecast. An overall accuracy of 98% has been achieved using this technique. The root mean squre error (RMSE) is around 0.011.

Original language	English
Pages (from-to)	1774-1782
Number of pages	9
Journal	Bulletin of Electrical Engineering and Informatics
Volume	9
Issue number	5
DOIs	https://doi.org/10.11591/eei.v9i5.2532
Publication status	Published - 10-2020

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 15 Life on Land

All Science Journal Classification (ASJC) codes

Computer Science (miscellaneous)
Control and Systems Engineering
Information Systems
Instrumentation
Hardware and Architecture
Computer Networks and Communications
Control and Optimization
Electrical and Electronic Engineering

Access to Document

10.11591/eei.v9i5.2532

Cite this

@article{5a5e7189f4a941dc96bdf2fa416dc110,

title = "Prediction of land-change using machine learning for the deforestation in paraguay",

abstract = "Northwestern Paraguay is being deforested at a very rapid rate. This article studies the rate of deforestation that has happened in this area using satellite images of LandSAT5 and LandSAT7. The rate of the deforestation is detected from 1986 to 2011, graphically using which future prediction is made. The images of LandSAT8 are used to validate the prediction made until 2018. An extrapolation of the graph shows that the process of deforestation is already 3 years ahead of its forecast. An overall accuracy of 98\% has been achieved using this technique. The root mean squre error (RMSE) is around 0.011.",

author = "Max Muller and Shweta Vincent and Kumar, \{Om Prakash\}",

year = "2020",

month = oct,

doi = "10.11591/eei.v9i5.2532",

language = "English",

volume = "9",

pages = "1774--1782",

journal = "Bulletin of Electrical Engineering and Informatics",

issn = "2089-3191",

publisher = "Institute of Advanced Engineering and Science",

number = "5",

}

TY - JOUR

T1 - Prediction of land-change using machine learning for the deforestation in paraguay

AU - Muller, Max

AU - Vincent, Shweta

AU - Kumar, Om Prakash

PY - 2020/10

Y1 - 2020/10

N2 - Northwestern Paraguay is being deforested at a very rapid rate. This article studies the rate of deforestation that has happened in this area using satellite images of LandSAT5 and LandSAT7. The rate of the deforestation is detected from 1986 to 2011, graphically using which future prediction is made. The images of LandSAT8 are used to validate the prediction made until 2018. An extrapolation of the graph shows that the process of deforestation is already 3 years ahead of its forecast. An overall accuracy of 98% has been achieved using this technique. The root mean squre error (RMSE) is around 0.011.

AB - Northwestern Paraguay is being deforested at a very rapid rate. This article studies the rate of deforestation that has happened in this area using satellite images of LandSAT5 and LandSAT7. The rate of the deforestation is detected from 1986 to 2011, graphically using which future prediction is made. The images of LandSAT8 are used to validate the prediction made until 2018. An extrapolation of the graph shows that the process of deforestation is already 3 years ahead of its forecast. An overall accuracy of 98% has been achieved using this technique. The root mean squre error (RMSE) is around 0.011.

UR - https://www.scopus.com/pages/publications/85087142199

UR - https://www.scopus.com/pages/publications/85087142199#tab=citedBy

U2 - 10.11591/eei.v9i5.2532

DO - 10.11591/eei.v9i5.2532

M3 - Article

AN - SCOPUS:85087142199

SN - 2089-3191

VL - 9

SP - 1774

EP - 1782

JO - Bulletin of Electrical Engineering and Informatics

JF - Bulletin of Electrical Engineering and Informatics

IS - 5

ER -

Prediction of land-change using machine learning for the deforestation in paraguay

Abstract

UN SDGs

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this