Improving Accuracy of Impervious Surface Extraction Based on a Threshold Hierarchical Method (THM)

Impervious surface area (ISA) is an important representation of urban area. It is very popular to extract ISA by using linear spectral mixture analysis (LSMA). However, there are still some defects in this method: underestimated in areas with a large amount of ISA. Hence, we designed a threshold hierarchical method (THM) to test this underestimation and understand which scale is the best to mixture. The capacity of the THM and the optimal threshold in the impervious surface extraction are the focus in this work. In THM model, the medium-resolution image (Landsat 8 OLI) and the high-resolution image (Gaofen-2, GF-2) were used, the LSMA and the object-oriented method (OOM) were applied for the area with a larger amount of impervious surfaces, which was extracted from the Landsat 8 OLI image after finishing the LSMA procedure by a threshold of the ISA abundance data, the GF-2 image was employed to extract the ISA by OOM. The results show that the THM had the capacity to achieve higher ISA extraction accuracy and ameliorate the ISA underestimate problem.

Kajian Transformasi Indeks Vegetasi Citra Satelit Sentinel-2A untuk Estimasi Produksi Daun Kayu Putih Menggunakan Linear Spectral Mixture Analysis

A forest plantation area of Melaleuca cajuputi at BDH Karangmojo, BKPH Yogyakarta are 2,325.20 ha. One of the efforts to keep its sustainability is to plan the target and realization of cajuputi leaf production considerwith forest condition. Advances in remote sensing technology can be an alternative in estimating the cajuputi leaf production on large areas with an efficient time and high accuracy and able to analyze the quality of cajuputi. This study aims to examine Sentinel-2A capabilities through a relationship model of some vegetation indices integrated with vegetative factors on the production to obtain estimates of leaf production, map and test the estimation model accuracy. The method used is to classify objects in pixels with Linear Spectral Mixture Analysis and build relationship between age, number of plants and vegetation index with cajuputi leaf production. The results showed that the unmixing method has 99,66% accuracy in classifying pixels into the fraction of cajuputi. MERIS Terrestrial Chlorophyll Index of unmixing cajuputi fraction simultaneously with age and number of plants has the highest correlation with value of r = 0,668 to the production and modeled in mapping the estimated cajuputi leaf production at the research location with Standard Error of Estimate is 0,183.

Performance Evaluation and Comparison of Modified Spectral Mixture Analysis Method for Different Images of Landsat Series Satellites

Urban impervious surface is considered one of main factors affecting urban heat island and urban waterlogging. It is commonly extracted utilizing the original linear spectral mixture analysis (LSMA) model. However, due to the deficiencies of this method, many improvements and modifications have been proposed. In this paper, a modified dynamic endmember linear spectral mixture analysis (DELSMA) model was introduced and tested in Zhengzhou, China, using different images of Landsat series satellites. The accuracy and performance of DELSMA model was evaluated in terms of R M S E , r and R 2 . Results show that (1) the DELSMA model performed equally well for Landsat-5 Thematic Mapper (TM) and Landsat-7 Enhanced Thematic Mapper (ETM+) images, and obtained better accuracy by using Landsat-8 Operational Land Imager (OLI) than Landsat TM/ETM+; (2) the DELSMA model achieved a better performance than the original LSMA model consistently, using images of Landsat from different sensors. Based exclusively on the overall accuracy reports, the DELSMA model proved to be a more efficient method for extracting impervious surface. Our study will provide a reliable method of impervious surface estimation for the urban planner and management in monitoring urban expansion, revealing urban heat island, and estimating urban surface runoff, using time-series Landsat imagery.

Discriminating Urban Forest Types from Sentinel-2A Image Data through Linear Spectral Mixture Analysis: A Case Study of Xuzhou, East China

Urban forests are an important component of the urban ecosystem. Urban forest types are a key piece of information required for monitoring the condition of an urban ecosystem. In this study, we propose an urban forest type discrimination method based on linear spectral mixture analysis (LSMA) and a support vector machine (SVM) in the case study of Xuzhou, east China. From 10-m Sentinel-2A imagery data, three different vegetation endmembers, namely broadleaved forest, coniferous forest, and low vegetation, and their abundances were extracted through LSMA. Using a combination of image spectra, topography, texture, and vegetation abundances, four SVM classification models were performed and compared to investigate the impact of these features on classification accuracy. With a particular interest in the role that vegetation abundances play in classification, we also compared SVM and other classifiers, i.e., random forest (RF), artificial neural network (ANN), and quick unbiased efficient statistical tree (QUEST). Results indicate that (1) the LSMA method can derive accurate vegetation abundances from Sentinel-2A image data, and the root-mean-square error (RMSE) was 0.019; (2) the classification accuracies of the four SVM models were improved after adding topographic features, textural features, and vegetation abundances one after the other; (3) the SVM produced higher classification accuracies than the other three classifiers when identical classification features were used; and (4) vegetation endmember abundances improved classification accuracy regardless of which classifier was used. It is concluded that Sentinel-2A image data has a strong capability to discriminate urban forest types in spectrally heterogeneous urban areas, and that vegetation abundances derived from LSMA can enhance such discrimination.