PREDIKSI REFORESTASI MENGGUNAKAN PENDEKATAN REGRESI LOGISTIK DI KABUPATEN SIAK, RIAU

KIRANA AISHA JASMINE, . (2026) PREDIKSI REFORESTASI MENGGUNAKAN PENDEKATAN REGRESI LOGISTIK DI KABUPATEN SIAK, RIAU. Sarjana thesis, UNIVERSITAS NEGERI JAKARTA.

	Text COVER.pdf Download (833kB)
	Text BAB 1.pdf Download (212kB)
	Text BAB 2.pdf Restricted to Registered users only Download (401kB) | Request a copy
	Text BAB 3.pdf Restricted to Registered users only Download (521kB) | 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 (197kB) | Request a copy
	Text DAFTAR PUSTAKA.pdf Download (314kB)
	Text LAMPIRAN.pdf Restricted to Registered users only Download (2MB) | Request a copy

Abstract

Kabupaten Siak, Provinsi Riau, memiliki ekosistem gambut luas yang rentan terhadap deforestasi dan karhutla, sebagaimana terlihat pada peristiwa besar tahun 2014–2015 yang melatarbelakangi kebijakan Siak Hijau (2016). Penelitian ini memprediksi potensi reforestasi di Kabupaten Siak pada tahun 2029 menggunakan regresi logistik terintegrasi Cellular Automata-Markov (plugin MOLUSCE, QGIS) berbasis data multitemporal 2014, 2019, dan 2024. Klasifikasi tutupan lahan menggunakan Random Forest pada citra Landsat 8 (Google Earth Engine) menghasilkan enam kelas tutupan lahan dengan Overall Accuracy 88,40–91,60% dan Kappa 0,8176–0,8593 (Almost Perfect Agreement). Variabel prediktor meliputi jarak dari jalan, sungai, permukiman, dan titik hotspot, dengan Pseudo R-squared 0,883 (2024) dan 0,831 (2029). Hasil menunjukkan neraca hutan net gain pada dua periode historis 17.082 Ha (2014–2019) dan 14.094 Ha (2019–2024), meski luas reforestasi menurun dari 41.476 Ha menjadi 25.435 Ha. Prediksi 2029 memproyeksikan pembalikan tren tersebut: perubahan ke non-hutan meningkat menjadi 15.317,18 Ha sementara reforestasi menurun tajam menjadi 8.108,46 Ha, menghasilkan net loss hutan 7.208,72 Ha (2,25%). Temuan ini mengindikasikan momentum pemulihan hutan 2014–2024 diproyeksikan tidak berkelanjutan pada 2024–2029, sehingga diperlukan intervensi kebijakan tambahan agar target Siak Hijau dan komitmen penurunan emisi 29% dalam kerangka SDGs 2030 tetap tercapai ***** Siak Regency, Riau Province, contains extensive peatland ecosystems vulnerable to deforestation and forest and land fires, as evidenced by the major 2014–2015 fire events that led to the Green Siak (Siak Hijau) policy in 2016. This study predicts reforestation potential in Siak Regency for 2029 using logistic regression integrated with Cellular Automata-Markov (the MOLUSCE plugin in QGIS), based on multitemporal data from 2014, 2019, and 2024. Land cover classification using Random Forest on Landsat 8 imagery (Google Earth Engine) produced six land cover classes with an Overall Accuracy of 88.40–91.60% and a Kappa Coefficient of 0.8176–0.8593, both falling under the Almost Perfect Agreement category. Predictor variables included distance to roads, rivers, settlements, and hotspot points, with the model yielding a Pseudo R-squared of 0.883 (2024 prediction) and 0.831 (2029 prediction). Results show a net forest gain across two historical periods 17,082 Ha (2014–2019) and 14,094 Ha (2019–2024), although reforestation area declined from 41,476 Ha to 25,435 Ha over the same span. The 2029 projection, however, indicates a reversal of this trend: conversion to non-forest increases to 15,317.18 Ha while reforestation drops sharply to 8,108.46 Ha, resulting in a net forest loss of 7,208.72 Ha (2.25%). These findings suggest that the forest recovery momentum observed during 2014–2024 is projected to be unsustainable through 2024–2029, underscoring the need for additional policy interventions to keep the Green Siak targets and the 29% greenhouse gas emission reduction commitment under the 2030 SDGs framework on track*****

Item Type:	Thesis (Sarjana)
Additional Information:	1). Rayuna Handawati, S.Si, M.Pd ; 2). Della Ayu Lestari, S.Si., M.Si
Subjects:	Geografi, Antropologi > Geografi Geografi, Antropologi > Geografi Fisik
Divisions:	FIS > S1 Geografi
Depositing User:	Kirana Aisha Jasmine .
Date Deposited:	13 Aug 2026 03:56
Last Modified:	13 Aug 2026 03:56
URI:	http://repository.unj.ac.id/id/eprint/68940

Actions (login required)

View Item