Prediction of Rice Growth Phases with Multitemporal Landsat-8 Data Using Rotation Forest Multiclass Method

Raditya Novidianto, Kartika Fithriasari*, Heri Kuswanto

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In 2018 the Area Sample Framework Survey (ASF) was formed, which was carried out by BPS Statistics to calculate rice harvested area and improve food crop data. The combination of satellite data and official data is an innovation that needs to be done to overcome a limitation, especially in the Sampling ASF carried out by BPS Statistics, so that the success of combining official data and big data will make suggestions for adding samples to the non-sample ASF Survey for data estimation harvest area is more accurate. Rotation Forest is a method that is often used and excels in classification with continuous data predictors. Multitemporal remote sensing using Landsat-8 satellite imagery was launched in 2013 with a recording period every 16 days. The basic features produced on the Landsat-8 satellite include bands 1 to 7, EVI, NDVI, NDWI, and NDBI indexes that can be used for prediction using the ensemble rotfor method. OVO method is better than the OVA in the case of multiclass rotfor rice growth phase detection using Landsat-8 satellite imagery. The best model formed is the RotFor MultiClass OVO model with a sensitivity value of 0.88, specificity 0.96, accuracy 0.87, MCC 0.83 and Cohen Kappa Index 0.83.

Original languageEnglish
Title of host publication3rd International Conference on Science, Mathematics, Environment, and Education
Subtitle of host publicationFlexibility in Research and Innovation on Science, Mathematics, Environment, and Education for Sustainable Development
EditorsNurma Yunita Indriyanti, Meida Wulan Sari
PublisherAmerican Institute of Physics Inc.
ISBN (Electronic)9780735443099
DOIs
Publication statusPublished - 27 Jan 2023
Event3rd International Conference on Science, Mathematics, Environment, and Education: Flexibility in Research and Innovation on Science, Mathematics, Environment, and Education for Sustainable Development, ICoSMEE 2021 - Surakarta, Indonesia
Duration: 27 Jul 202128 Jul 2021

Publication series

NameAIP Conference Proceedings
Volume2540
ISSN (Print)0094-243X
ISSN (Electronic)1551-7616

Conference

Conference3rd International Conference on Science, Mathematics, Environment, and Education: Flexibility in Research and Innovation on Science, Mathematics, Environment, and Education for Sustainable Development, ICoSMEE 2021
Country/TerritoryIndonesia
CitySurakarta
Period27/07/2128/07/21

Keywords

  • Area Sampling Framework
  • Binarization
  • Classification
  • Landsat-8
  • Rotation Forest

Fingerprint

Dive into the research topics of 'Prediction of Rice Growth Phases with Multitemporal Landsat-8 Data Using Rotation Forest Multiclass Method'. Together they form a unique fingerprint.

Cite this