Spatio-Temporal Deforestation Measurement Using Automatic Clustering
Journal Title: EMITTER International Journal of Engineering Technology - Year 2016, Vol 4, Issue 1
Abstract
Deforestation is one of the crucial issues in Indonesia. In 2012, deforestation rate in Indonesia reached 0.84 million hectares, exceeding Brazil. According to the 2009 Guinness World Records, Indonesia's deforestation rate was 1.8 million hectares per year between 2000 and 2005. An interesting view is the fact that Indonesia government denied the deforestation rate in those years and said that the rate was only 1.08 million hectares per year in 2000 and 2005. The different problem is on the technique how to deal with the deforestation rate. In this paper, we proposed a new approach for automatically identifying the deforestation area and measuring the deforestation rate. This approach involves differential image processing for detecting Spatio-temporal nature changes of deforestation. It consists series of important features extracted from multiband satellite images which are considered as the dataset of the research. These data are proceeded through the following stages: (1) Automatic clustering for multiband satellite images, (2) Reinforcement Programming to optimize K-Means clustering, (3) Automatic interpretation for deforestation areas, and (4) Deforestation measurement adjusting with elevation of the satellite. For experimental study, we applied our proposed approach to analyze and measure the deforestation in Mendawai, South Borneo. We utilized Landsat 7 to obtain the multiband images for that area from the year 2001 to 2013. Our proposed approach is able to identify the deforestation area and measure the rate. The experiment with our proposed approach made a temporal measurement for the area and showed the increasing deforestation size of the area 1.80 hectares during those years.
Authors and Affiliations
Irene Erlyn Wina Rachmawan, Ali Ridho Barakbah, Tri Harsono
Keywords
Related Articles
- EP ID EP269403
- DOI 10.24003/emitter.v4i1.120
- Views 100
- Downloads 0
Mobile Application to Identify Indonesian Flowers on Android Platform
Although many people love flowers, they do not know their name. Especially, many people do not recognize local flowers. To find the flower image, we can use search engine such as Google, but it does not give much help to...
Performance Analysis of Scheduling Schemes for Femto to Macro Interference Coordination in LTE-Femtocell Deployment Scenario
Deploying femtocells that have low power level in LTE with small coverage area is an alternative solution for mobile operators to improve indoors network coverage area as well as system capacity. However deploying femtoc...
Determination of Nearest Emergency Service Office using Haversine Formula Based on Android Platform
Emergency Reporting Application is an Android-based application that serves to help the community in reporting the emergency condition. This application allows users to choose and contact the emergency services office, w...
Development of Healthcare Kiosk for Checking Heart Health
The main problem encountered nowadays in the health field, especially in health care is the growing number of population and the decreasing health facilities. In this regard, healthcare kiosk is used as an alternative to...
Application of Artificial Neural Networks in Modeling Direction Wheelchairs Using Neurosky Mindset Mobile (EEG) Device
The implementation of Artificial Neural Network in prediction the direction of electric wheelchair from brain signal input for physical mobility impairment.. The control of the wheelchair as an effort in improving disabl...