Vegetation anomaly index from remote sensing for landslide activities mapping
Remote sensing has long been used for landslide mapping and monitoring. Landslide activity is one of the important parameters for landslide inventory and it can be strongly related to vegetation anomalies. A high-density airborne Light Detection and Ranging (LiDAR), aerial photo and satellite imager...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/81712/1/NurliyanaIzzatiIshakMFABU2018.pdf http://eprints.utm.my/id/eprint/81712/ http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:126855 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Remote sensing has long been used for landslide mapping and monitoring. Landslide activity is one of the important parameters for landslide inventory and it can be strongly related to vegetation anomalies. A high-density airborne Light Detection and Ranging (LiDAR), aerial photo and satellite imagery were captured over the landslide prone area along Sungai Mesilau, Kundasang, Sabah. This study aims to evaluate landslide inventory, generate vegetation properties and vegetation anomalies using high density airborne LiDAR and other remotely sensed data. There are four research objectives. The first objective is to delineate and characterize landslide inventory based on different landslide type, depth and activity. Second objective is to generate vegetation properties and vegetation anomalies using high density airborne LiDAR and other remotely sensed data. The third objective is to generate landslide activity probability map and the fourth objective is to analyze the capability of vegetation anomalies in characterizing landslide activity for different landslide type and depth. Landslide identification has been conducted using orthophoto and three terrain-derived raster layers. Series of landslide validations were conducted to ensure the certainty level of the delineated landslide. These validation processes were conducted by visiting the landslide areas and based on expert-knowledge. Remote sensing data have been used in characterizing vegetation into several classes of height, density, types and structures in the study area. There were 13 vegetation anomalies derived from remotely sensed data. To produce a probability map for landslide activity, different combinations of landslide type, activity and depth have been used as the input data together with the vegetation anomalies raster layer. The use of statistical model was based-on data-driven approach which focusing on the bivariate model (hazard index). The capabilities of landslide probability maps are later evaluated using Receiver Operating Characteristic (ROC) curve together with success and prediction rate values. There were 14 scenarios have been modeled in this study by focusing on two landslide depths, three main landslide types, and three landslide activities. All scenarios show that more than 65% of the landslides are captured within 70% of the probability model which indicates high model efficiency. The predictive model rate curve also shows that more than 45% of the independent landslides can be predicted within 30% of the probability model. Indices of vegetation for 13 vegetation anomalies layers were tabulated by conducting statistical analysis on the weightage for each of the model. This study introduces new method that utilizes vegetation anomalies extracted using remote sensing data as a bio-indicator for landslide activity analysis and mapping. In conclusion, this integrated disaster study provides a better understanding into the utilization of advanced remote sensing data for extracting and characterizing vegetation anomalies induced by hillslope geomorphology processes. |
|---|