Analisis Kesesuaian Prediksi Tutupan Lahan Terhadap RDTR Di Kota Mojokerto Menggunakan Artificial Neural Network

Fasya, Marsa Aulia (2026) Analisis Kesesuaian Prediksi Tutupan Lahan Terhadap RDTR Di Kota Mojokerto Menggunakan Artificial Neural Network. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5016221123-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (8MB) | Request a copy

Abstract

Perubahan tutupan lahan merupakan aspek penting dalam perencanaan tata ruang dan pengelolaan wilayah. Di Kota Mojokerto, pertumbuhan penduduk dan perkembangan kawasan terbangun mendorong terjadinya perubahan penggunaan lahan yang berpotensi menimbulkan ketidaksesuaian terhadap Rencana Detail Tata Ruang (RDTR). Penelitian ini bertujuan untuk menganalisis perubahan tutupan lahan tahun 2021–2025, memprediksi tutupan lahan tahun 2026 menggunakan Artificial Neural Network (ANN), serta menganalisis kesesuaiannya terhadap RDTR Kota Mojokerto. Data yang digunakan citra Sentinel-2A tahun 2021–2025 dan variabel pendorong yaitu kepadatan penduduk, jarak ke jalan utama, pusat kota, rumah sakit dan sekolah. Evaluasi model dilakukan menggunakan overall accuracy dan koefisien kappa. Hasil penelitian menunjukkan bahwa berdasarkan analisis perubahan tutupan lahan tahun 2021–2025, luas kelas permukiman cenderung mengalami peningkatan, sedangkan luas kelas pertanian, vegetasi, badan air, dan lahan terbuka berfluktuasi. Model ANN dengan skema 80:20 memberikan performa terbaik dengan nilai overall accuracy sebesar 0,831 dan koefisien kappa sebesar 0,716 pada testing data. Hasil prediksi tutupan lahan tahun 2026 terhadap RDTR menunjukkan tingkat kesesuaian sebesar 43,26% atau 883,328 ha dengan kesesuaian terbesar pada kelas permukiman dan tingkat ketidaksesuaian sebesar 56,74% atau 1.158,430 ha, yang didominasi oleh kelas pertanian pada kawasan yang direncanakan sebagai permukiman dalam RDTR. Kondisi ini mengindikasikan bahwa lahan tersebut belum mengalami perubahan fungsi sesuai arahan RDTR. Hasil penelitian ini diharapkan dapat menjadi bahan pertimbangan dalam perencanaan tata ruang dan pengelolaan wilayah di Kota Mojokerto guna mendukung pencapaian SDGs 11 melalui pemanfaatan ruang yang lebih terarah dan berkelanjutan.
====================================================================================================================================
Changes in land cover are a key aspect of spatial planning and regional management. In the city of Mojokerto, population growth and the expansion of built-up areas are driving changes in land use that have the potential to result in non-compliance with the Detailed Spatial Plan (RDTR). This study aims to analyse land cover changes for the period 2021–2025, predict land cover for 2026 using an Artificial Neural Network (ANN), and analyse its compliance with the Mojokerto City RDTR. The data used comprised Sentinel-2A imagery from 2021–2025 and the following driving variables: population density, distance to main roads, the city centre, hospitals and schools. Model evaluation was carried out using overall accuracy and the Kappa coefficient. The research results indicate that, based on the analysis of land cover changes from 2021 to 2025, the area classified as residential land tends to increase, whilst the areas classified as agricultural land, vegetation, water bodies and open land fluctuate. The ANN model with an 80:20 scheme delivered the best performance, with an overall accuracy of 0,831 and a Kappa coefficient of 0,716 on the test data. The results of the 2026 land cover prediction against the RDTR showed a level of agreement of 43,26%, or 883,328 ha, with the highest agreement in the settlement class, and a level of disagreement of 56,74%, or 1.158,430 ha, which is dominated by the agricultural class in areas designated as residential in the RDTR. This situation indicates that the land has not yet undergone a change of use in accordance with the RDTR guidelines. It is hoped that the findings of this study will serve as a basis for consideration in spatial planning and regional management in Mojokerto City, with a view to supporting the achievement of SDG 11 through more targeted and sustainable land use.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Tutupan Lahan, Artificial Neural Network, Prediksi Tutupan Lahan, Rencana Detail Tata Ruang, Artificial Neural Network, Land Cover Prediction, Detailed Spatial Plan, Land Cover
Subjects:	Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science)
Divisions:	Faculty of Civil, Planning, and Geo Engineering (CIVPLAN) > Geomatics Engineering > 29202-(S1) Undergraduate Thesis
Depositing User:	Marsa Aulia Fasya
Date Deposited:	22 Jul 2026 07:40
Last Modified:	22 Jul 2026 07:40
URI:	http://repository.its.ac.id/id/eprint/136276

Actions (login required)

View Item