Monitoring and classification of karst rocky desertification with Landsat 8 OLI images using spectral indices, multi-endmember spectral mixture analysis and support vector machine

Authors : Çağan ALEVKAYALI, Onur YAYLA, Yıldırım ATAYETER

Pages : 277-289

Doi:10.26833/ijeg.1149738

View : 57 | Download : 109

Publication Date : 2023-10-15

Article Type : Research Paper

Abstract :Karst Rocky Desertification insert ignore into journalissuearticles values(KRD); is the reduction of vegetative productivity of this land with the release of bedrock as a result of the full or partial transportation of the fertile soil through natural processes and human activities in karst landscapes. The purpose of this study is to reveal the effectiveness of Remote Sensing methods in monitoring, mapping and evaluating KRD. Landsat 8 OLI images were used to carry out these procedures. In monitoring this process, Karst Bare Rock Index insert ignore into journalissuearticles values(KBRI);, Normalized Difference Rock Index insert ignore into journalissuearticles values(NDRI);, Carbonate Rock Index 2 insert ignore into journalissuearticles values(CRI2);, Normalized Difference Build-Up Index insert ignore into journalissuearticles values(NDBI);, Normalized Difference Vegetation Index insert ignore into journalissuearticles values(NDVI);, Dimidiate Pixel Model insert ignore into journalissuearticles values(DPM);, Multi Endmember Spectral Mixture Analysis insert ignore into journalissuearticles values(MESMA); and Support Vector Machine insert ignore into journalissuearticles values(SVM); were used from the spectral indices. In order to determine KRD with spectral indexes, a strong linear relationship was tested between some indices such as DPM insert ignore into journalissuearticles values(R2=0,79);, KBRI insert ignore into journalissuearticles values(R2=0,66);, and NDBI insert ignore into journalissuearticles values(R2=0,64); and field measurements. In order to evaluate the results obtained, KRD was divided into 4 basic classes such as none, mild, moderate, and severe. According to these classification levels, it was determined that the SVM method had the highest accuracy insert ignore into journalissuearticles values(Kappa=0.88);. According to the classification results, which have the highest accuracy in the study area, the rate of areas undergoing severe karst desertification is 40%, moderate desertification process is 17%, mild desertification is 14% and non-desertification is 29%. In the study, it was concluded that the KRD strengthens as one goes from south to north and from west to east in the research area. This study points out KRD is one of the effective ecosystem problems in the Mediterranean region, Türkiye.
Keywords : Remote Sensing, Karst Rocky Desertification, Spectral Indices, Spectral Mixture Analysis, Machine Learning