| dc.contributor.advisor | Suroso, Arif Imam | |
| dc.contributor.advisor | Hermadi, Irman | |
| dc.contributor.advisor | Prasetyo, Lilik Budi | |
| dc.contributor.author | Iskandar, Ade Rahmat | |
| dc.date.accessioned | 2026-08-04T11:47:09Z | |
| dc.date.available | 2026-08-04T11:47:09Z | |
| dc.date.issued | 2026 | |
| dc.identifier.uri | http://repository.ipb.ac.id/handle/123456789/177059 | |
| dc.description.abstract | Penelitian dalam bidang hutan kota ekowisata berbasis pendekatan machine learning dan remote sensing masih sedikit dilakukan oleh para peneliti. Hutan kota ekowisata memberikan banyak manfaat positif bagi masyarakat urban, perkotaan dan negara. Salah satu manfaatnya adalah dapat meningkatkan pendidikan dan kesadaran lingkungan, meningkatkan kualitas hidup urban, dan meningkatkan keberlanjutan dan konservasi habitat. Beberapa hutan kota ekowisata di Indonesia di antaranya adalah hutan kota Srengseng dan Tebet Eco Park di Jakarta, hutan Babakan Siliwangi di Bandung, hutan Kaombona di Palu, Sulawesi Tengah, hutan kota Kemuning di Pekanbaru, Riau, dan hutan kota Tinjomoyo di Semarang.
Pengalokasian hutan kota untuk tiap provinsi atau wilayah kota di Indonesia masih terbatas. Data tahun 2017 menunjukkan ruang terbuka hijau (RTH) DKI Jakarta hanya sebesar 9,98% dari total luas wilayah; kebutuhan ideal RTH kota sebesar 30% (20% RTH publik dan 10% RTH privat). Tujuan penyelenggaraan hutan kota adalah untuk kelestarian, keserasian, dan keseimbangan ekosistem perkotaan yang meliputi unsur lingkungan.
Topik Model Hutan Kota Ekowisata Berbasis Pendekatan Machine Learning dan Remote Sensing merupakan hasil analisis tersistematis (analysis bibliometric) berdasarkan kajian ilmiah menggunakan tools Publish or Perish dan VOSviewer. Paper penelitian diperoleh dari basis data Scopus dan ScienceDirect. Kata kunci yang digunakan dalam paper collection penelitian ini adalah (ecotourism urban forest, urban forest management, urban forest machine learning, remote sensing for urban forest, analytical hierarchy process for ecotourism urban forest). Hasil telaah dari systematic literature review (SLR) dan state of the art penelitian ini bermuara pada kajian Model Hutan Kota Ekowisata berbasis pendekatan Machine Learning dan Remote Sensing dengan analytical hierarchy process sebagai kerangka konseptual yang digunakan dalam penelitian ini.
Analytical hierarchy process (AHP) digunakan sebagai kerangka konseptual untuk mengintegrasikan pendekatan mixed-method dalam membangun model hutan ekowisata berbasis pendekatan machine learning dan remote sensing atau penginderaan jauh. Pendekatan kuantitatif dilakukan menggunakan data spasial urban forest dari hutan kota Srengseng dan Tebet Eco Park Jakarta menggunakan tools google earth pro, google earth engine, dan Pyhton dengan mengadopsi teknologi remote sensing melalui satelit Landsat 8/OLI untuk mengeksplorasi data indeks vegetasi atau normalized difference vegetation index (NDVI), data kerapatan tutupan tajuk hutan atau Forest canopy density (FCD), dan data suhu permukaan tanah atau land surface temperature (LST), selain itu pendekatan kualitatif dilakukan dengan teknik observasi, deep interview untuk mendapatkan informasi sahih mengenai ecotourism urban forest qualitative data dari pakar hutan ekowisata, dan kuesioner tersistematis dari masyarakat atau wisatawan urban).
Pada penelitian ini, Google Earth Pro digunakan untuk membuat poligon presisi hutan Kota Srengseng dan Tebet Eco Park, Jakarta. Tahap berikutnya menggunakan tools Google Earth Engine untuk membuat kode program berbasis JavaScript untuk mendapatkan data spasial NDVI, FCD, dan LST hutan kota yang diteliti. Hasil dari kode program tersebut adalah diperolehnya data spasial berupa data set NDVI, FCD, dan LST hutan kota Srengseng dan Tebet Eco Park dari tahun 2019 sampai tahun 2024.
Data spasial tersebut diolah menggunakan algoritma machine learning random forest regressor untuk memprediksi indeks vegetasi, kerapatan tutupan tajuk hutan dan suhu permukaan tanah menggunakan data spasial satelit Landsat 8/OLI di Hutan Kota Srengseng dan Tebet Eco Park. Luaran dari penelitian ini adalah dirancangnya Model Pengelolaan Hutan Kota Ekowisata Berbasis Pendekatan Machine Learning dan Remote Sensing.
Kebaruan penelitian ini terletak pada penerjemahan hasil machine learning berbasis remote sensing menjadi model prioritas pengelolaan yang operasional melalui integrasi indikator ekologis dan sosio-kultural. Pendekatan ini menjadikan hasil analisis tidak hanya informatif, tetapi juga langsung dapat digunakan sebagai alat pendukung keputusan dalam pengelolaan hutan kota ekowisata | |
| dc.description.abstract | Research in the field of urban ecotourism forests based on machine learning and remote sensing approaches is still limited. Urban ecotourism forests offer numerous positive benefits for urban communities, cities, and the nation. Among these benefits are increased environmental education and awareness, improved urban quality of life, and increased desire for and conservation of habitats. Some urban ecotourism forests in Indonesia include the Srengseng and Tebet Eco Park urban forests in Jakarta, the Babakan Siliwangi forest in Bandung, the Kaombona forest in Palu, Central Sulawesi, the Kemuning urban forest in Pekanbaru, Riau, and the Tinjomoyo urban forest in Semarang.
The allocation of urban forests for each province or city in Indonesia remains limited. 2017 data shows that Jakarta's green open space (RTH) only covers 9.98% of the total area, while the ideal urban green space requirement is 30% (20% public green space and 10% private green space). The purpose of urban forest management is to preserve, harmonize, and balance the urban ecosystem, encompassing all environmental elements.
The topic "Urban Forest Ecotourism Model Based on Machine Learning and Remote Sensing Approaches" is the result of a systematic bibliometric analysis based on scientific studies using the Publish or Perish and Vos Viewer tools. Research papers were obtained from the Scopus and ScienceDirect databases. The keywords used in this collection of research papers are (urban forest ecotourism, urban forest management, urban forest machine learning, remote sensing for urban forests, analytical hierarchy process for urban forest ecotourism). The results of this systematic literature review (SLR) and advanced research culminate in the study of an Urban Forest Ecotourism Model based on Machine Learning and Remote Sensing approaches, using the analytical hierarchy process as the conceptual framework used in this study.
The Analytical Hierarchy Process (AHP) is used as a conceptual framework to integrate a mixed-method approach in developing an ecotourism forest model based on machine learning and remote sensing approaches. A quantitative approach was conducted using urban forest spasial data from the Srengseng and Tebet Eco Park urban forests in Jakarta. Using Google Earth Pro, Google Earth Engine, and Python, remote sensing technology was used via the Landsat 8/OLI satellite to explore vegetation index data (Normalized Difference Vegetation Index (NDVI), Forest canopy density (FCD), and land surface temperature (LST). A qualitative approach was also conducted using observation techniques, in-depth interviews to obtain valid information about ecotourism (qualitative data from ecotourism forest experts, and systematic questionnaires from the community and urban tourists).
In this study, Google Earth Pro was used to create precision polygons for the Srengseng and Tebet Eco Park urban forests in Jakarta. The next step involved using Google Earth Engine to create a JavaScript-based program code to obtain spasial data on the NDVI, FCD, and LST of the urban forest being studied. The resulting code generated spasial data in the form of NDVI, FCD, and LST datasets for the Srengseng and Tebet Eco Park urban forests from 2019 to 2024.
This spasial data will be processed using a random forest regressor machine learning algorithm to predict vegetation index, forest canopy density, and land surface temperature using Landsat 8/OLI satellite spasial data in the Srengseng and Tebet Eco Park urban forests. The output of this research is the creation of an Ecotourism Urban Forest Model based on Machine Learning and Remote Sensing approaches, utilizing the Analytical Hierarchy Process (AHP) as a conceptual framework to provide recommendations for ecotourism urban forest management for ecotourism urban forest stakeholders. The ecotourism urban forest model based on machine learning and remote sensing is based on seven indicators studied, namely (NDVI, FCD, LST, facilities, accessibility, landscape beauty, and educational value) in the Srengseng and Tebet Eco Park ecotourism urban forests.
The novelty of this study lies in translating remote sensing-based machine learning outputs into a practical management prioritization framework through the integration of ecological and socio-cultural indicators. This approach enables the analytical results to serve not only as a source of information but also as an effective decision-support tool for urban forest ecotourism management | |
| dc.description.sponsorship | YPTelkom | |
| dc.language.iso | id | |
| dc.publisher | IPB University | id |
| dc.title | Model Pengelolaan Hutan Kota Ekowisata Berbasis Pendekatan Machine Learning dan Remote Sensing | id |
| dc.title.alternative | Ecotourism Urban Forest Management Model Based on Machine Learning and Remote Sensing Approaches | |
| dc.type | Disertasi | |
| dc.subject.keyword | AHP model | id |
| dc.subject.keyword | urban forest ecotourism | id |
| dc.subtype | Dissertations | |