Penentuan Wilayah Resiko Bencana Kekeringan di Jawa Tengah Menggunakan Machine Learning dan Indeks Vegetasi pada Citra Landsat 8 OLI

  • Septian Silvianugroho Universitas Kristen Satya Wacana
  • Sri Yulianto Joko Prasetyo Fakultas Teknologi Informasi Universitas Kristen Satya Wacana
  • Kristoko Dwi Hartomo Fakultas Teknologi Informasi Universitas Kristen Satya Wacana
Keywords: Bencana Kekeringan, Machine learning, Decision tree,  Principal Component Analisys(PCA), Random Forest, Indeks Vegetasi

Abstract

Bencana kekeringan di Indonesia terjadi hampir setiap tahun, khususnya untuk provinsi Jawa Tengah yang mana tercatat dalam sejarah dari tahun 1815 sampai tahun 2015 telah terjadi 382 kejadian. Untuk itu diperlukan adanya prediksi penentuan wilayah kekeringan di seluruh kecamatan di Jawa Tengah. Pada penelitian ini prediksi kekeringan menggunakan  Machine Learning untuk menganalisa hasil ekstraksi dari citra Landsat-8 OLI yang berupa indeks vegetasi yaitu NDVI, SAVI, VCI, VHI dan TCI dengan menggunakan beberapa algoritma, diantaranya adalah Decision Tree, Principal Component Analisys(PCA) dan Random Forest. Hasil yang diperoleh ada total 17 kecamatan yang diprediksi terkena bencana kekeringan yang sangat parah, dengan nilai accuracy 0,7507463, logloss 0,6232992 dan Mean Sequare Error (MSE) sebesar 0,1795135.

Downloads

Download data is not yet available.

References

D. Geofisika, D. A. N. Meteorologi, F. Matematika, D. A. N. Ilmu, and P. Alam, “Analisis temporal vegetation health index (vhi) untuk kekeringan lahan persawahan (studi kasus kabupaten indramayu, jawa barat) linda yuliyanti,” 2014.

E. Surmaini, “Pemantauan dan peringatan dini kekeringan pertanian di Indonesia,” J. Sumberd. lahan, vol. 10, no. 1, pp. 37–50, 2016.

D. B. P. dan K. BNPB, “Kajian risiko bencana jawa tengah 2016 - 2020,” 2016.

H. Z. M. Shafri, “Machine Learning in Hyperspectral and Multispectral Remote Sensing Data Analysis,” pp. 3–9, 2017.

J. Rhee, J. Im, and S. Park, “Drought forecasting based on machine learning of remote sensing and long-range forecast data,” Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. - ISPRS Arch., vol. 41, no. July, pp. 157–158, 2016.

M. Kanevski, A. Pozdnoukhov, and V. Timonin, “Machine learning algorithms for geo spatial data. Applications and software tools,” Proc. iEMSs 4th Bienn. Meet. - Int. Congr. Environ. Model. Softw. Integr. Sci. Inf. Technol. Environ. Assess. Decis. Making, iEMSs 2008, vol. 1, pp. 320–327, 2008.

A. E. Maxwell, T. A. Warner, and F. Fang, “Implementation of machine-learning classification in remote sensing: An applied review,” Int. J. Remote Sens., vol. 39, no. 9, pp. 2784–2817, 2018.

H. Park, K. Kim, and D. K. Lee, “Prediction of severe drought area based on random forest: Using satellite image and topography data,” Water (Switzerland), vol. 11, no. 4, pp. 1–15, 2019.

K. Sriram and K. Suresh, “Machine Learning Perspective for Predicting Agricultural Droughts Using Naive Bayes Algorithm,” vol. 24, pp. 178–184, 2016.

A. Belayneh and J. Adamowski, “Drought forecasting using new machine learning methods / Prognozowanie suszy z wykorzystaniem automatycznych samouczących się metod,” J. Water L. Dev., vol. 18, no. 9, pp. 3–12, 2013.

E. . Andana, “Pengembangan Data Citra Satelit Landsat-8 Untuk Pemetaan Area Tanaman Hortikultura Dengan Berbagai Metode Algoritma Indeks Vegetasi (Studi Kasus: Kabupaten Malang Dan Sekitarnya),” Nas. Manaj. Teknol., vol. 9, no. Sistem Informasi Geografis, pp. 1–10, 2015.

J. Xue and B. Su, “Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications,” J. Sensors, vol. 2017, pp. 1–17, 2017.

H. dan R. H. J. Hendry Frananda, “Komparasi Indeks Vegetasi untuk Estimasi Stok Karbon Hutan Mangrove Kawasan Segoro Anak Pada Kawasan Taman Nasional Alas Purwo Banyuwangi , Jawa Timur ( Comparison of Vegetation Indices for Mangrove Carbon Stock Estimation,” Maj. Ilm. Globe, vol. 17, no. 2, pp. 113–123, 2015.

A. Klisch and C. Atzberger, “Operational drought monitoring in Kenya using MODIS NDVI time series,” Remote Sens., vol. 8, no. 4, 2016.

N. Yan, B. Wu, V. K. Boken, S. Chang, and L. Yang, “A drought monitoring operational system for China using satellite data: design and evaluation,” Geomatics, Nat. Hazards Risk, vol. 7, no. 1, pp. 264–277, 2016.

R. I. Sholihah et al., “Identification of Agricultural Drought Extent Based on Vegetation Health Indices of Landsat Data: Case of Subang and Karawang, Indonesia,” Procedia Environ. Sci., vol. 33, pp. 14–20, 2016.

B. Gupta, A. Rawat, A. Jain, A. Arora, and N. Dhami, “Analysis of Various Decision Tree Algorithms for Classification in Data Mining,” Int. J. Comput. Appl., vol. 163, no. 8, pp. 15–19, 2017.

J. Lever, M. Krzywinski, and N. Altman, “Principal component analysis,” Nat. Methods, vol. 14, p. 641, Jun. 2017.

Y. Riko, A. I. Meha, and S. Y. J. Prasetyo, “Perubahan Konversi Lahan Menggunakan NDVI, EVI, SAVI dan PCA pada Citra Landsat 8 (Studi Kasus : Kota Salatiga),” vol. 8, 2018.

et al., “Application of Principal Component Analysis (PCA) to Medical Data,” Indian J. Sci. Technol., vol. 10, no. 20, pp. 1–9, 2017.

N. Horning, “Random Forests: An algorithm for image classification and generation of continuous fields data sets,” Int. Conf. Geoinformatics Spat. Infrastruct. Dev. Earth Allied Sci. 2010, pp. 1–6, 2010.

V. Vani and V. R. Mandla, “Comparative study of NDVI and SAVI vegetation indices in Anantapur district semi-arid areas,” Int. J. Civ. Eng. Technol., vol. 8, no. 4, 2017.

L. F. Amalo, R. Hidayat, and S. Sulma, “Analysis of Agricultural Drought in East Java Using Vegetation Health Index,” AGRIVITA J. Agric. Sci., vol. 40, no. 1, pp. 63–73, 2018.

D. Dutta, A. Kundu, N. R. Patel, S. K. Saha, and A. R. Siddiqui, “Assessment of agricultural drought in Rajasthan (India) using remote sensing derived Vegetation Condition Index (VCI) and Standardized Precipitation Index (SPI),” Egypt. J. Remote Sens. Sp. Sci., vol. 18, no. 1, pp. 53–63, 2015.
Published
2019-12-11
How to Cite
Silvianugroho, S., Prasetyo, S., & Hartomo, K. (2019). Penentuan Wilayah Resiko Bencana Kekeringan di Jawa Tengah Menggunakan Machine Learning dan Indeks Vegetasi pada Citra Landsat 8 OLI. Indonesian Journal of Computing and Modeling, 2(2), 17-24. Retrieved from https://ejournal.uksw.edu/icm/article/view/2952
Section
Articles