tunnels, bridges, pipelines, and roads [site engineer]

Nov 6, 2019 - Sep 6, 2024

supervising on tunnels, bridges, pipelines, and roads works

Comparative study of Supervised Classification Methods for Mapping Land Cover Using Sentinel 2 Data: A Case study in Al-Hawija District /Iraq

Aug 11, 2024

Journal THE 4TH INTERNATIONAL CONFERENCE ON SUSTAINABLE ENGINEERING TECHNIQUES (ICSET)

publisher AIP Conf. Proc. 3105, 010001 (2024)

DOI 10.1063/12.0025730

Volume 3105

This study aims to classify the land cover of high-resolution satellite images using a supervised classification method and evaluate the performance of four supervised classification techniques, namely Support Vector Machine (SVM), Artificial neural network (ANN), Maximum likelihood (ML), and Mahalanobis distance (MLD). Sentinel-2 satellite data was used in the present study with 10m spatial resolution. The classification results revealed that the Support Vector Machine and Artificial neural network gave excellent results. Overall accuracy values for SVM, ML, ANN, and MLD methods were 90%, 81.8%, 87% and 78.7%, and the kappa coefficient values are 0.875, 0.758, 0.833, and 0.717, with respectively. Selecting an appropriate classification algorithm is equally important to get better classification results. Advanced classifiers gave higher accuracy with minimal errors; hence, for critical planning and monitoring tasks, these classifiers should be preferred

Read Publication

Comparison of the accuracies of different spectral indices for mapping the vegetation covers in Al-Hawija district, Iraq

Jul 1, 2023

Journal The Fourth International Conference on Civil and Environmental Engineering Technologies

publisher AIP Publishing. 978-0-7354-4595-6/$30.00

DOI 10.1063/5.0142004

This study aims to evaluate the performance of seven vegetation indices, namely (Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GDVI), Soil Adjusted Vegetation Index (SAVI), Difference Vegetation Index (DVI), Infrared Percentage Vegetation Index (IPVI), Enhanced Vegetation Index (EVI) and Optimized Soil adjusted Vegetation Index (OSAVI)). Four bands of Sentinel-2 satellite were used in the present study with 10m spatial resolution. The overall accuracy of NDVI, GDVI, SAVI, DVI, IPVI, EVI, and OSAVI is 72.5%, 92.5%, 85%, 85%, 87.5%, 65%, and 97.5%, respectively. The results showed that the OSAVI and GNDVI are the most suitable indices for this study. It is very useful in mapping vegetation cover, which is beneficial for municipal planning and management.

Read Publication