Evaluation of spectral built-up indices for impervious surface extraction using Sentinel-2A MSI imageries: A case of Addis Ababa city, Ethiopia

Kebede, Tsion Ayalew; Hailu, Binyam Tesfaw; Suryabhagavan, K. V.

doi:10.1016/j.envc.2022.100568

Cited by 29 publications

(8 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The split is performed using optimal maximum margin, with points on the margins called 'support vectors' pertaining to structural risk minimization. Kernel representations offer a solution to locating complex hyperplanes between classes [66,67]. The commonly used types of SVM kernels for classification include: linear, polynomial, radial basis function (RBF), and sigmoid [68].…”

Section: Classification Methods Selectionmentioning

confidence: 99%

Refinement of Individual Tree Detection Results Obtained from Airborne Laser Scanning Data for a Mixed Natural Forest

et al. 2022

View full text Add to dashboard Cite

Numerous semi- and fully-automatic algorithms have been developed for individual tree detection from airborne laser-scanning data, but different rates of falsely detected treetops also accompany their results. In this paper, we proposed an approach that includes a machine learning-based refinement step to reduce the number of falsely detected treetops. The approach involves the local maxima filtering and segmentation of the canopy height model to extract different segment-level features used for the classification of treetop candidates. The study was conducted in a mixed temperate forest, predominantly deciduous, with a complex topography and an area size of 0.6 km × 4 km. The classification model’s training was performed by five machine learning approaches: Random Forest (RF), Extreme Gradient Boosting, Artificial Neural Network, the Support Vector Machine, and Logistic Regression. The final classification model with optimal hyperparameters was adopted based on the best-performing classifier (RF). The overall accuracy (OA) and kappa coefficient (κ) obtained from the ten-fold cross validation for the training data were 90.4% and 0.808, respectively. The prediction of the test data resulted in an OA = 89.0% and a κ = 0.757. This indicates that the proposed method could be an adequate solution for the reduction of falsely detected treetops before tree crown segmentation, especially in deciduous forests.

show abstract

Section: Classification Methods Selectionmentioning

confidence: 99%

Refinement of Individual Tree Detection Results Obtained from Airborne Laser Scanning Data for a Mixed Natural Forest

et al. 2022

View full text Add to dashboard Cite

show abstract

“…RS urban applications are now indispensable from planning to city management, and old maps and field surveys for city surveys are out of date and have been replaced by RS images rapidly (Netzband et al 2007). Many urban land use mapping studies have been made with RS images and methods, from the global scale to the regional mapping of a single city (Duan et al 2015;Trianni et al 2015;Liu et al 2018;Wang et al 2017;Magidi and Ahmed, 2019;Misra et al 2020, Zhang et al 2021Kebede et al,2022).…”

Section: Introductionmentioning

confidence: 99%

Determination of Urban Areas Using Google Earth Engine and Spectral Indices; Esenyurt Case Study

KAYA

Dervisoglu

2023

International Journal of Environment and Geoinformatics

View full text Add to dashboard Cite

Identifying impervious surfaces for monitoring urban expansion is important for the sustainable management of land resources and the protection of the environment. Remote sensing provides an important data source for urban land use/land cover mapping, and these data can be analyzed with various techniques for different purposes. If the aim is to extract information easily and rapidly, using spectral indices is the most appropriate solution, and there are many indices created for this purpose. The study carried out on the Google Earth Engine (GEE) platform, Esenyurt, the most populous district of Istanbul, was investigated using Sentinel 2 MSI image, with eight urban spectral indices and three vegetation indices. In addition, classification was made, and the results were evaluated. As a result of the urban index applications, it has been seen that the roofs are more or less mixed with the bare soil areas, and Normalized Difference Tillage Index (NDTI)gives the best results. Accuracy assessment is performed for index results and classification using the same points, and due to the urban area density in the application area, it is determined as 0.95% and 0.95% for NDTI and Normalized Difference Vegetation Index (NDVI), and 97% for classification, respectively. In GEE, a high (-0.79) negative correlation is observed between May mean values and 2007-2022 population data when the NDVI time series was applied to the entire area within the district borders using Landsat 5 and Landsat 8 images between 1990-2022. The rapidly increasing population in the district leads to rapid urbanization, and green areas are disappearing at the same rate.

show abstract

“…In recent decades, China has experienced rapid urbanization and industrialization, which has led to signi cant changes in land use/cover (Qiao et al 2016). As one of the most important indicators for studying urbanization, impervious surface area (ISA) directly re ected ecological and environmental issues from local to global (Ayalew et al 2022). The research on the spatiotemporal dynamic distribution of ISA contributed to understanding the impact of human activities on the natural world (Seto et al 2012).…”

Section: Introductionmentioning

confidence: 99%

Impervious surface Mapping and its spatial–temporal evolution analysis in the Yellow River Delta over the last three decades using Google Earth Engine

Liu

Zhang

et al. 2023

Earth Sci Inform

View full text Add to dashboard Cite

The unique geographical location of the land-sea transition makes the ecological environment of the Yellow River Delta very fragile and vulnerable to human activities. As one of the characteristics of anthropogenic activities, monitoring the spatiotemporal changes of impervious surface is of great signi cance to the protection of the ecological environment in the Yellow River Delta (YRD). Based on the Landsat historical images and computing resources provided by Google Earth Engine (GEE), an impervious surface area (ISA) mapping method was developed through combining spectral, texture features and random forest algorithm, and subsequently was applied to generate the spatiotemporal distribution data of ISA of the YRD for 1992YRD for , 1998YRD for , 2004YRD for , 2010YRD for , 2016YRD for and 2021. The experimental results demonstrated that the proposed method achieved satisfactory accuracy, with an average overall accuracy of 92.23% and an average Kappa coe cient of 0.9090. Through further time-series analysis of ISA, it found that the area of ISA in the YRD increased from the initial 394.87 km 2 to 1081.74 km 2 during study periods, and the annual growth rate broke through new highs, ranging from the initial 1.01 km 2 /year to 67.87 km 2 /year. According to the research results, urban development activities in the region should be strictly restricted in order to protect the ecological environment of the Yellow River Delta.

show abstract

Evaluation of spectral built-up indices for impervious surface extraction using Sentinel-2A MSI imageries: A case of Addis Ababa city, Ethiopia

Cited by 29 publications

References 53 publications

Refinement of Individual Tree Detection Results Obtained from Airborne Laser Scanning Data for a Mixed Natural Forest

Refinement of Individual Tree Detection Results Obtained from Airborne Laser Scanning Data for a Mixed Natural Forest

Determination of Urban Areas Using Google Earth Engine and Spectral Indices; Esenyurt Case Study

Impervious surface Mapping and its spatial–temporal evolution analysis in the Yellow River Delta over the last three decades using Google Earth Engine

Contact Info

Product

Resources

About