Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : MEDIA KONSERVASI

Study of Land Cover Change using Multi Layer Perceptron and Logistic Regression Methods in Gunung Ciremai National Park Agus Rudi Darmawan; Nining Puspaningsih; M. Buce Saleh
Media Konservasi Vol 22 No 3 (2017): Media Konservasi Vol. 22 No. 3 Desember 2017
Publisher : Department of Forest Resources Conservation and Ecotourism - IPB University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (644.283 KB) | DOI: 10.29244/medkon.22.3.252-261

Abstract

The development of land cover change is important to understand, so that the pattern of future land cover changes can be predicted and its negative impacts can be prevented or reduced. Various modeling approaches have been widely used to analyze land cover changes. The common modeling methods used for analyzing land cover changes are Multi-layer Perceptron (MLP) and Logistic Regression (Logit). This research is designed to assess the accuracy of modeling of land cover change with MLP and Logit methods in Gunung Ciremai National Park. The result indicated that the accuracy of both methods was very good with kappa values were 0,8991 and 0,8989 for MLP and Logit respectively. Therefore, the model can be applied to predict land cover change in Gunung Ciremai National Park in the future. Keywords: Gunung Ciremai National Park, land cover change, Logistic Regression, Multi-layer Perceptron
Canopy Density Estimation Model in Peat Swamp Forest Using LiDAR Data and Landsat 8 OLI Satellite Imagery Saleh, Muhammad Buce; Malta Daerangga; Prasetyo, Lilik Budi; Yudi Setiawan; Sahid Hudjimartsu; Wijayanto, Arif Kurnia
Media Konservasi Vol. 29 No. 2 (2024): Media Konservasi Vol 29 No 2 May 2024
Publisher : Department of Forest Resources Conservation and Ecotourism - IPB University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/medkon.29.2.249

Abstract

Canopy density is one of the important parameters in measuring the forest conditions. Canopy density can be estimated by using a remote sensing technology system. Light Detection and Ranging (LiDAR) is an active remote sensing system which uses a laser that is emitted by a sensor to the objects on the earth surface. For a wide area, image utilization which solely relies on LiDAR is still relatively expensive, so it is necessary to develop a method that combine LiDAR data with other medium resolution images such as Landsat 8 OLI imagery. Therefore, this research was conducted to obtain the canopy density estimation model from LiDAR and Landsat 8 OLI data. The results showed that the best estimation model at the study site, PT Global Alam Lestari's peat swamp forest was FRCI = - 0.0171 + 8.691 GRVI. The equation model had coefficient of determination (R²) of 50.2%, standard deviation value (s) of 0.101, aggregate deviation (SA) value of 0.459, and correlation coefficient (r) between the actual FRCI and the estimation FRCI (best model) of 0.503.
Examining the Use of the Watershed Algorithm for Segmenting Crown Closure on a Dry Land Forest Hardian, Dwika; I Nengah Surati Jaya; Muhammad Buce Saleh
Media Konservasi Vol. 29 No. 2 (2024): Media Konservasi Vol 29 No 2 May 2024
Publisher : Department of Forest Resources Conservation and Ecotourism - IPB University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/medkon.29.2.127

Abstract

This paper uses a watershed algorithm to detect canopy cover in dryland forests. The study at to determine the best parameters of the watershed segmentation algorithm to obtain information on crown closure from filtered and unfiltered high and very high-resolution images. The best performance of each parameter combination of tolerance value (T), mean value (M), and variance value (V), which is written as C:[T]-[M]-[V], is determined based on the level of accuracy. This study uses Pleiades-1B and SPOT-6 images as primary digital data. The results showed that the low-pass filtered Pleiades-1B image showed the best performance with a combination of parameters C6-MF:[10]-[0.7]-[0.3], had an overall accuracy (OA) of 91.0% and an accuracy Kappa (KA) by 83.2%. While the low-pass filtered Spot-6 image shows the combination of parameters C7-MF:[10]-[0.8]-[0.2], which has an accuracy of 90.6% OA and 65.4% KA. This study concludes that the filtered image with a low-pass filter always gives more accurate results than the original data (without filter), both for Pleiades-1B and SPOT-6 images. The very high spatial resolution provides better accuracy than the high spatial resolution