Ramadaningtyas, Niken (2021) Analisis Ketelitian Klasifikasi Penutupan Lahan Menggunakan Metode Digitize on Screen dan Deep Learning Series Convolutional Neural Network (CNN) Berdasarkan Citra Landsat-8 OLI (Studi Kasus: Provinsi Kalimantan Timur). Undergraduate thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
03311840000062_Undergraduate_Thesis.pdf Download (4MB) | Preview |
Preview |
Text
03311840000062_Undergraduate_Thesis.pdf - Accepted Version Download (4MB) | Preview |
Abstract
Penutupan lahan bersifat dinamis dikarenakan kebutuhan manusia atau kejadian alam yang dapat terjadi secara terencana maupun tidak terencana. Dit. IPSDH-KLHK menggunakan data citra satelit penginderaan jauh untuk menghasilkan data penutupan lahan dengan metode interpretasi visual (penafsiran manual). Identifikasi objek dilakukan dengan cara digitize on screen. Seiring berkembangnya zaman dan teknologi saat ini telah muncul beberapa penelitian mengenai klasifikasi penutupan lahan dan uji akurasi nya menggunakan teknologi terbaru, salah satunya menggunakan deep learning. Dalam penelitian ini dilakukan uji akurasi hasil klasifikasi digitize on screen dan klasifikasi penutupan lahan dengan deep learning beserta uji akurasinya. Uji akurasi klasifikasi penutupan lahan hasil digitize on screen dilakukan dengan metode centroid. Validasi dilakukan dengan menggunakan citra satelit resolusi tinggi yaitu google earth pro sesuai temporal akuisisi citra Landsat 8 yang digunakan, yaitu Juli 2019-Juni 2020 dengan menyebar 360 sampel secara acak. Hasil menunjukan Provinsi Kalimantan Timur memiliki 21 kelas penutupan lahan dengan nilai overall accuracy 87,22% kategori sangat baik dan masuk toleransi. Klasifikasi penutupan lahan menggunakan deep learning dilakukan dengan menggunakan citra Landsat-8 OLI yang telah dilakukan segmentasi. Pengambilan sampel dilakukan dengan segment picker untuk 20 kelas penutupan lahan tanpa kelas Pertanian Lahan Kering Campur. Hasil klasifikasi menunjukan saling tumpang tindih karena suatu kelas penutupan lahan juga terklasifikasi menjadi kelas lainnya serta tidak semua area citra terklasifikasi. Uji akurasi dilakukan dengan jumlah dan penyebaran titik sampel yang sama dengan sampel uji metode digitize on screen. Nilai akurasi hasil klasifikasi penutupan lahan metode deep learning adalah 15,09% untuk 21 kelas penutupan pada seluruh sampel yang tergolong akurasi kecil dan tidak masuk toleransi sedangkan pada kelas hutan dan non-hutan memiliki nilai akurasi 42,27% . Nilai akurasi metode deep learning menggunakan sampel pada area terklasifikasi menghasilkan akurasi 70,21% untuk 21 kelas penutupan lahan dan 81,38% pada kelas hutan dan non-hutan. Hal ini disebabkan banyak nya kelas penutupan lahan dengan kunci interpretasi yang hampir mirip. Kunci interpretasi 21 kelas penutupan lahan lebih cocok digunakan untuk metode digitize on screen.
Kata Kunci: CNN, Deep Learning, Digitize on Screen, Penutupan Lahan, Uji Akurasi
===================================================================================================
Land cover is dynamic due to human needs or natural events that can occur in a planned or unplanned manner. Dit. IPSDH-KLHK uses remote sensing satellite imagery data to generate land cover data using a visual interpretation method (manual interpretation). Object identification is done by digitizing on screen. Along with the development of the times and current technology, several studies have emerged regarding the classification of land cover and its accuracy test using the latest technology, one of which uses deep learning. In this study, the accuracy of the digitize on screen classification results and land cover classification using deep learning was carried out along with the accuracy test. The accuracy test for land cover classification as a result of digitizing on screen was carried out using the centroid method. Validation was carried out using high resolution satellite imagery, namely google earth pro according to the temporal acquisition of Landsat 8 imagery used, namely July 2019-June 2020 by spreading 360 samples randomly. The results show that East Kalimantan Province has 21 land cover classes with an overall accuracy value of 87.22% in the very good category and in the tolerance category. Land cover classification using deep learning is carried out using segmented Landsat-8 OLI images. Sampling was carried out with a segment picker for 20 land cover classes without the Mixed Dry Land Agriculture class. The classification results show overlapping because one land cover class is also classified into other classes and not all image areas are classified. The accuracy test was carried out with the same number and distribution of sample points as the test sample using the digitize on screen method. The accuracy value of the land cover classification using the deep learning method is 15.09% for 21 cover classes in all samples which is classified as small accuracy and does not enter into tolerance, while the forest and non-forest classes have an accuracy value of 42.27%. The accuracy value of the deep learning method using samples in classified areas resulted in an accuracy of 70.21% for 21 land cover classes and 81.38% for forest and non-forest classes. This is due to the many land cover classes with almost similar interpretation keys. The interpretation key of 21 land cover classes is more suitable for the digitize on screen method.
Keywords: CNN, Deep Learning, Digitize on Screen, Land Cover, Accuracy Test
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Uncontrolled Keywords: | CNN, Deep Learning, Digitize on Screen, Penutupan Lahan, Uji Akurasi CNN, Deep Learning, Digitize on Screen, Land Cover, Accuracy Test |
| Subjects: | G Geography. Anthropology. Recreation > GA Mathematical geography. Cartography > GA102.4.R44 Cartography--Remote sensing |
| Divisions: | Faculty of Civil, Planning, and Geo Engineering (CIVPLAN) > Geomatics Engineering > 29202-(S1) Undergraduate Thesis |
| Depositing User: | Niken Ramadaningtyas |
| Date Deposited: | 07 Feb 2022 07:10 |
| Last Modified: | 21 Oct 2024 04:59 |
| URI: | http://repository.its.ac.id/id/eprint/92906 |
Actions (login required)
 |
View Item |