View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Agriculture
      • UT - Soil Science and Land Resources
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Agriculture
      • UT - Soil Science and Land Resources
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Klasifikasi Fase Pertumbuhan Tanaman Padi pada Citra Sentinel-2 dengan Pendekatan k-Nearest Neighbors

      Thumbnail
      View/Open
      Cover (2.592Mb)
      Fullteks (9.437Mb)
      Lampiran (17.38Mb)
      Date
      2022
      Author
      Putra, Alief Yuda Ariska
      Munibah, Khursatul
      Tjahjono, Boedi
      Metadata
      Show full item record
      Abstract
      Padi merupakan komoditas utama dalam menyokong pangan masyarakat, hampir sebagian besar dari penduduk Indonesia menjadikan padi sebagai makanan pokok. Oleh karena itu, estimasi produksi beras tahunan perlu dilakukan pemerintah sebagai antisipasi terjadinya gagal panen. Salah satu upaya yang dapat dilakukan yaitu melalui pemantauan kondisi tanaman padi dengan memanfaatkan citra satelit. Penelitian ini bertujuan melakukan identifikasi kekontrasan tampilan citra hasil koreksi radiometrik dengan sen2cor, menganalisis klasifikasi fase pertumbuhan tanaman padi menggunakan metode klasifikasi k-Nearest Neighbors (kNN) dan menguji akurasi hasil klasifikasi fase pertumbuhan tanaman padi. Penelitian ini menggunakan metode klasifikasi k-nearest neighbors yang merupakan metode klasifikasi berdasarkan pada perhitungan jarak terdekat suatu objek data latih dengan objek lain di sekitarnya. Penelitian menggunakan data sekunder dari penelitian Wijayanti (2018) dan dilaksanakan pada Januari-Juli 2021. Hasil penelitian menunjukan bahwa nilai pasca koreksi atmosferik (BOA) memiliki standar deviasi yang lebih besar dibandingkan nilai sebelum koreksi atmosferik (TOA), sehingga secara visual citra koreksi BOA tampak lebih kontras. Pola spektral yang telah terkoreksi atomosferik (BOA) memiliki nilai pantulan yang lebih rendah dibandingkan pada citra sebelum koreksi atmosferik (TOA), khususnya pada band biru. Hasil klasifikasi k-nearest neighbors dari 3 kecamatan menunjukkan kontinuitas fase tumbuh dari dominansi fase bera basah di akuisisi 6 Desember 2017 ke dominansi fase bera kering di akuisisi 31 Maret 2018. Hasil uji akurasi klasifikasi k-Nearest Neighbors menunjukkan bahwa rata-rata akuisisi citra memiliki nilai akurasi yang baik yaitu di atas 85%. Kata Kunci: k-Nearest Neighbors, Citra Sentinel 2, Fase tumbuh padi, sen2cor.
       
      Rice is the main commodity in supporting people's food, almost most of the Indonesian population makes rice as a staple food. Therefore, it is necessary to estimate the annual rice production by the government in anticipation of crop failure. One of the efforts that can be done is through monitoring the condition of rice plants by utilizing satellite imagery. This study aims to identify the contrast of the image display resulting from radiometric correction with sen2cor, analyze the classification of rice growth phases using the k-Nearest Neighbors (kNN) classification method and test the accuracy of the classification results for the growing phases of rice plants. This study uses the k-nearest neighbors classification method, which is a classification method based on the calculation of the closest distance of a training data object to other objects in the vicinity. This study uses secondary data from Wijayanti's research (2018) and was carried out in January-July 2021. The results show that the post-atmospheric correction (BOA) value has a standard deviation that is larger than the pre-atmospheric correction (TOA) value, so that visually the BOA correction image appear more contrast. The atomospheric corrected spectral pattern (BOA) has a lower reflectance value than the image before atmospheric correction (TOA), especially in the blue band. The results of the k-nearest neighbors classification from 3 sub-districts show the continuity of the growing phase from the dominance of the wet fallow phase on the acquisition of December 6, 2017 to the dominance of the dry fallow phase on the acquisition of March 31, 2018. The results of the accuracy test for the classification of k-Nearest Neighbors show that the average image acquisition has a good accuracy value is above 85%. Keywords: k-Nearest Neighbors, Sentinel 2 imagery, paddy growth phase, sen2cor.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/112095
      Collections
      • UT - Soil Science and Land Resources [2823]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository