Pembuatan Model Kota 3D LOD1 Dan Algoritma Random Forest Untuk Prediksi NJOP Sebagai Dasar Pengenaan PBB-P2 (Studi Kasus: Area Kelurahan Embong Kaliasin, Surabaya)

Armazeta, Aura Jovita Gandari (2025) Pembuatan Model Kota 3D LOD1 Dan Algoritma Random Forest Untuk Prediksi NJOP Sebagai Dasar Pengenaan PBB-P2 (Studi Kasus: Area Kelurahan Embong Kaliasin, Surabaya). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5016211056-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (15MB) | Request a copy

Abstract

Dalam rangka peningkatan data dasar, pemetaan kadaster di Indonesia mulai bertransformasi ke bentuk 3D dengan memanfaatkan teknologi LiDAR. Teknologi ini memiliki akurasi tinggi dalam representasi digital permukaan bumi, sehingga cocok digunakan untuk aplikasi model kota 3D dengan tingkat detail LOD 1. Penelitian ini menggunakan data DSM dan DTM LiDAR untuk pengolahan NDSM, pada data Ortofoto akan dilakukan digitasi tiap bangunan untuk pembuatan model kota 3D, serta data NJOP Bumi dan Bangunan untuk melakukan prediksi harga NJOP dengan menggunakan machine learning algoritma random forest. Dari 608 bangunan model 3D yang dibuat, dihasilkan tingkat detail dengan hasil RMSE uji validasi tinggi sebesar 0,437 meter. Pada evaluasi metrik prediksi NJOP, didapatkan hasil terbaik dengan model 70:30 dengan R2 sebesar 0,983; MAPE 7,05%; MAE Rp741.572/m2; dan RMSE sebesar Rp1.257.935/m2. Model prediksi NJOP mempertimbangkan beberapa faktor pengaruh untuk kelas bumi dan bangunan. Pada NJOP Bumi, fitur yang memiliki pengaruh paling besar ialah luas bumi dengan nilai 0,65 dan lebar jalan senilai 0,6. Pada NJOP Bangunan, fitur yang paling dominan ialah luas bangunan dengan nilai kepentingan sebesar 0,45 yang diikuti oleh tinggi bangunan senilai 0,3. Hasil pengolahan prediksi NJOP dilakukan perhitungan ke nilai PBB-P2, hasil perhitungan menunjukkan terdapat peningkatkan nilai PBB-P2 sebesar 70% dengan rata-rata peningkatan nilai PBB-P2 sebesar Rp3.365.273, selanjutnya terdapat 27% objek mengalami penurunan nilai pajak, dan 3% data memiliki nilai tetap seperti nilai awal. Hasil penelitian berupa visualisasi model kota 3D LOD1 dengan pola distribusi spasial kelas tarif PBB-P2 di area Kelurahan Embong Kaliasin dibuat pada platform ArcGIS Online di alamat link https://its.id/m/PBBP2EmbongKaliasin.
==============================================================================================================================================
In order to improve basic data, cadastral mapping in Indonesia has begun to transform into a 3D format by utilizing LiDAR technology. This technology has high accuracy in digital representation of the earth's surface, making it suitable for use in 3D city models with a level of detail (LOD) of 1. This study uses LiDAR DSM and DTM data for NDSM processing. Orthophoto data will be digitized for each building to create a 3D city model, and NJOP land and building data will be used to predict NJOP prices using a random forest machine learning algorithm. Out of the 608 3D building models created, a high validation test RMSE of 0.437 meters was achieved. In the NJOP prediction metric evaluation, the best results were obtained with the 70:30 model, achieving an R² of 0.983; MAPE of 7.05%; MAE of Rp741,572/m²; and RMSE of Rp1,257,935/m². The NJOP prediction model considers several influencing factors for land and building classes. For NJOP Land, the most influential feature is land area with a value of 0.65, followed by road width with a value of 0.6. For NJOP Buildings, the most dominant feature is building area with an importance value of 0.45, followed by building height with a value of 0.3. The NJOP prediction results were processed to calculate the PBB-P2 value. The calculation results showed a 70% increase in the PBB-P2 value, with an average increase of Rp3,365,273. Additionally, 27% of objects experienced a decrease in tax value, and 3% of data maintained the same value as the initial value. The research results are in the form of a 3D LOD1 city model visualization with the spatial distribution pattern of the PBB-P2 tariff class in the Embong Kaliasin sub-district area, created on the ArcGIS Online platform at the link https://its.id/m/PBBP2EmbongKaliasin.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	LiDAR, Model Kota 3D, NJOP, PBB-P2, Random Forest, LiDAR, 3D City Model, NJOP, PBB-P2, Random Forest.
Subjects:	G Geography. Anthropology. Recreation > G Geography (General) > G70.212 ArcGIS. Geographic information systems. G Geography. Anthropology. Recreation > G Geography (General) > G70.217 Geospatial data G Geography. Anthropology. Recreation > G Geography (General) > G70.5.I4 Remote sensing G Geography. Anthropology. Recreation > GA Mathematical geography. Cartography > GA102.4.R44 Cartography--Remote sensing G Geography. Anthropology. Recreation > GA Mathematical geography. Cartography > GA109.5 Multipurpose cadastres. G Geography. Anthropology. Recreation > GA Mathematical geography. Cartography > GA139 Digital Elevation Model (computer program) H Social Sciences > HG Finance > HG4028.V3 Valuation. Economic value H Social Sciences > HJ Public Finance T Technology > T Technology (General) > T174 Technological forecasting T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. T Technology > T Technology (General) > T58.5 Information technology. IT--Auditing T Technology > T Technology (General) > T58.62 Decision support systems
Divisions:	Faculty of Civil, Planning, and Geo Engineering (CIVPLAN) > Geomatics Engineering > 29202-(S1) Undergraduate Thesis
Depositing User:	Aura Jovita Gandari Armazeta
Date Deposited:	21 Jul 2025 01:27
Last Modified:	21 Jul 2025 01:27
URI:	http://repository.its.ac.id/id/eprint/120116

Actions (login required)

View Item