Land Use Analysis Using Machine-Learning Based on Cloud Computing Platform

Syukur Toha Prasetyo; Fahmi Arief Rahman; Sinar Suryawati; Slamet Supriyadi; Eko Setiawan

doi:10.18343/jipi.30.4.765

Authors

Syukur Toha Prasetyo Study Program of Agrotechnology, Faculty of Agriculture, University of Trunojoyo Madura, Bangkalan 69162
Fahmi Arief Rahman Study Program of Agrotechnology, Faculty of Agriculture, University of Trunojoyo Madura, Bangkalan 69162
Sinar Suryawati Study Program of Agrotechnology, Faculty of Agriculture, University of Trunojoyo Madura, Bangkalan 69162
Slamet Supriyadi Study Program of Agrotechnology, Faculty of Agriculture, University of Trunojoyo Madura, Bangkalan 69162
Eko Setiawan Study Program of Agrotechnology, Faculty of Agriculture, University of Trunojoyo Madura, Bangkalan 69162

DOI:

https://doi.org/10.18343/jipi.30.4.765

Abstract

Land use analysis can provide a foundation for successful and efficient regional planning and environmental monitoring. The application of machine-learning on a cloud computing platform (Google Earth Engine, GEE) in land use analysis enables efficient and rapid processing of spatial data on a wide scale. It overcomes the constraints inherent in conventional approaches. The purpose of this study was to identify land use and estimate its level of accuracy using GEE and a Random Forest machine-learning method. The data utilized were the administrative boundaries of Bangkalan Regency (1:25,000) and Landsat 8 SR L2 C2 T1 satellite images from 2022. Satellite image analysis using the Random Forest algorithm on the GEE platform with the JavaScript API, including masking, cloud masking, class and sampling, training, and testing sample data. Land use study using the Random Forest algorithm yielded the following results in order of area: vegetation 65,040.39 ha (49.98%), agricultural land 31,817.16 ha (24.45%), settlements 20,578.05 ha (15.81%), open land 6,683.94 ha (5.14%), and water bodies 6,021.09 ha (4.63%). The accuracy test in GEE revealed an overall accuracy (OA) of 91.39% and a kappa score of 88.39%, or 0.88. At the same time, validation in the field gave an OA of 88.68% and a Kappa of 85.53%. The findings of this study can be applied to land use evaluation and fundamental decision-making.

Keywords: land use, random forest, geographic information system, remote sensing

Downloads

Download data is not yet available.

References

Arif N, Wahyuni FS. 2016. Penggunaan metode machine learning untuk pengenalan pola tutupan lahan pada citra satelit. In: Seminar Nasional Teknologi Informasi dan Multimed. STMIK AMIKOM Yogyakarta, 6–7 Februari 2016.

Arifin S. 2017. Kajian perubahan penggunaan tanah pasca pembangunan jembatan Suramadu di Kecamatan Bangkalan, Kabupaten Bangkalan, Provinsi Jawa Timur. Yogyakarta (ID). Sekolah Tinggi Pertahanan Nasional.

Asra R, Mappiasse MF, Nurnawati AA. 2020. Penerapan model CA–Markov untuk prediksi perubahan penggunaan lahan di Sub–DAS Bila tahun 2036. Agrovital: Jurnal llmu Pertanian. 5(1): 1–10. https://doi.org/10.35329/agrovital.v5i1.630

[BPS] Badan Pusat Statistika. 2023. Kabupaten Bangkalan Dalam Angka 2023. Jakarta (ID): Badan Pusat Statistik.

Febriani N, Yunidar S, Hidayat RA, Amor G, Indrayani P. 2022. Klasifikasi citra satelit dengan metode Random Forest untuk observasi dinamika lansekap ekosistem Kabupaten Sujunjung. El–jughrafiyah. 2(2): 75–81. https://doi.org/10.24014/jej.v2i2.18730

Firmawan MA, Widiatmaka, Nirmala K. 2021. Identifikasi dinamika spasial penggunaan dan tutupan lahan di Kabupaten Indramayu. Jurnal Ilmu Tanah dan Lingkungan. 23(2): 78–84. https://doi.org/10.29244/jitl.23.2.78-84

Hossaimah H, Subari S. 2017. Percepatan alih fungsi (konversi) lahan pertanian ke non pertanian di Kecamatan Galis, Kabupaten Pamekasan. Agrisaintifika Jurnal Ilmu–Ilmu Pertanian. 1(2): 97–108. https://doi.org/10.32585/ags.v1i2.45

Landis JR, Koch GG. 1977. The measurement of observer agreement for categorical data. Biometrics. 33(1): 159–174. https://doi.org/10.2307/2529310

Lestari SC, Arsyad M. 2018. Studi penggunaan lahan berbasis data citra satelit dengan metode sistem informasi geografis (GIS). Jurnal Sains dan Pendidikan Fisika. 14(1): 81–88.

Marlina D. 2022. Klasifikasi tutupan lahan pada citra Sentinel–2 Kabupaten Kuningan dengan NDVI dan Algoritme Random Forest. STRING (Satuan Tulisan Riset dan Inovasi Teknologi). 7(1): 41–49. https://doi.org/10.30998/string.v7i1.12948

Novianti TC. 2021. Klasifikasi landsat 8 OLI untuk tutupan lahan di Kota Palembang menggunakan Google Earth Engine. Jurnal Swarnabhumi. 6(1): 75–85.

Nuraida D, Rosyida SZA, Widyawati NA, Sari WK, Fanani IMR. 2022. Analisis vegetasi tumbuhan herba di Kawasan Hutan Krawak. Jurnal Biologi dan Pembelajarannya. 9(2): 96–104. https://doi.org/10.29407/jbp.v9i2.18417

Rahman FA, Adiputra A. 2022. Analisis konversi lahan pertanian menjadi pemukiman di Kabupaten Bangkalan Tahun 2009–2019. In: Prosiding Seminar Nasional Pendidikan Geografi FKIP UHAMKA. Institut Pendidikan FKIP Uhamka, Jakarta Timur, 9th April 2022.

Rahmawati H. 2021. Relevansi pergeseran alih guna lahan pertanian menjadi pemukiman di Desa Simogirang, Kecamatan Prambon, Sidoarjo. Jurnal Ekonomi Bisnis dan Akuntansi. 1(3): 74–86. https://doi.org/10.55606/jebaku.v1i3.171

Rizaldi A, Darmawan A. Kaskoyo H. Setiawan A. 2023. Pemanfaatan Google Earth Engine untuk pemantauan lahan agroforestri dalam skema perhutanan sosial. Majalah Geografi Indonesia. 37(1): 12–21 https://doi.org/10.22146/mgi.73923

Suryono H, Marsuhandi AH, Pramana S. 2022. Klasifikasi tutupan lahan berdasarkan Random Forest Algorithm menggunakan cloud computing platform. Jurnal Aplikasi Statistika dan Komputasi Statatistik. 14(3): 1–12. https://doi.org/10.34123/jurnalasks.v14i1.383

Susanti Y, Syafrudin, Helmi M. 2020. Analysis of land use change in Upper Serayu Watersheds using remote sensing and Geographic Information Systems. Bioedukasi: Jurnal Pendidikan Biologi. 13(1): 23–30.

Tosiani A, Mohammad AR, Sularso MGN, Lugiana M, Novita N, Lestrai NS. 2020. Standar Operasional Prosedur (SOP): Penghitungan Akurasi dan Uncertainty Perubahan Penutupan Lahan. Bogor (ID): IPB Pr.

Zulfajri, Danoedoro P, Murti SH. 2021. Klasifikasi tutupan lahan Data Landsat–8 OLI menggunakan metode Random Forest. Jurnal Penginderaan Jauh Indonesia. 3(1): 1–7. https://doi.org/10.12962/jpji.v3i1.266