PREDIKSI URBAN HEAT ISLAND (UHI) PADA TAHUN 2035 DI KOTA BEKASI

Qaanitah Hasmaulia, . (2026) PREDIKSI URBAN HEAT ISLAND (UHI) PADA TAHUN 2035 DI KOTA BEKASI. Sarjana thesis, UNIVERSITAS NEGERI JAKARTA.

	Text COVER.pdf Download (4MB)
	Text BAB 1.pdf Download (440kB)
	Text BAB 2.pdf Restricted to Registered users only Download (617kB) | Request a copy
	Text BAB 3.pdf Restricted to Registered users only Download (749kB) | Request a copy
	Text BAB 4.pdf Restricted to Registered users only Download (3MB) | Request a copy
	Text BAB 5.pdf Restricted to Registered users only Download (517kB) | Request a copy
	Text DAFTAR PUSTAKA.pdf Download (406kB)
	Text LAMPIRAN.pdf Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Fenomena Urban Heat Island (UHI) di Kota Bekasi terus meningkat seiring pesatnya alih fungsi lahan vegetasi menjadi kawasan terbangun akibat tekanan urbanisasi di kawasan metropolitan Jabodetabek. Penelitian ini bertujuan memprediksi sebaran intensitas UHI di Kota Bekasi pada tahun 2035 menggunakan pendekatan regresi linier berganda berbasis data penginderaan jauh. Metode yang digunakan adalah deskriptif kuantitatif dengan memanfaatkan citra Landsat 8 dan Landsat 9 tahun 2015, 2020, dan 2025 yang diolah melalui Google Earth Engine (GEE) untuk mengekstraksi Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), dan Land Surface Temperature (LST). Klasifikasi tutupan lahan dilakukan dengan algoritma Random Forest yang menghasilkan overall accuracy 82,50-85,60% dan koefisien Kappa 0,79-0,82. Prediksi tutupan lahan tahun 2035 dimodelkan menggunakan Cellular Automata-Markov ANN pada Tools Molusce di QGIS, kemudian nilai prediksi NDVI dan NDBI digunakan sebagai variabel bebas dalam persamaan regresi. Hasil penelitian menunjukkan bahwa NDBI berhubungan positif dengan suhu permukaan, sedangkan NDVI berhubungan negatif. Proyeksi tahun 2035 menunjukkan 87,81% wilayah Kota Bekasi atau 19.379,97 hektar berada pada kelas rendah dengan suhu 39,95-40,51°C. Kondisi ini mengindikasikan potensi terbentuknya UHI dengan suhu yang tinggi apabila tidak ada intervensi kebijakan penambahan ruang terbuka hijau dan pengendalian kepadatan bangunan secara sistemik di Kota Bekasi. ***** The Urban Heat Island (UHI) phenomenon in Bekasi City continues to increase along with the rapid conversion of vegetated land into built-up areas due to urbanization pressures in the Greater Jakarta metropolitan area. This study aims to predict the distribution of UHI intensity in Bekasi City in 2035 using a multiple linear regression approach based on remote sensing data. The method used is quantitative descriptive by utilizing Landsat 8 and Landsat 9 imagery in 2015, 2020, and 2025 processed through Google Earth Engine (GEE) to extract the Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), and Land Surface Temperature (LST). Land cover classification was performed using the Random Forest algorithm which produced an overall accuracy of 82.50%-85.60% and a Kappa coefficient of 0.79-0.82. Land cover prediction in 2035 was modeled using Cellular Automata-Markov ANN in the Molusce Tools in QGIS, then the predicted values of NDVI and NDBI were used as independent variables in the regression equation. The results showed that NDBI was positively related to surface temperature, while NDVI was negatively related. The 2035 projection shows that 87.81% of Bekasi City's area or 19,346.67 ha is in the low UHI class with temperatures of 39.95-40.51°C. This condition indicates the potential for the formation of UHI with high temperatures if there is no policy intervention to increase green open space and control building density systematically in Bekasi City

Item Type:	Thesis (Sarjana)
Additional Information:	1). Ilham Badaruddin Mataburu, S.Si, M.Si; 1). Hikari Dwi Saputro, S.Pd., M.Pd.
Subjects:	Geografi, Antropologi > Geografi Geografi, Antropologi > Matematika Geografi, Kartografi Geografi, Antropologi > Geografi Fisik
Divisions:	FIS > S1 Geografi
Depositing User:	Users 34299 not found.
Date Deposited:	04 Aug 2026 01:45
Last Modified:	04 Aug 2026 01:45
URI:	http://repository.unj.ac.id/id/eprint/68324

Actions (login required)

View Item