Improving Classification Accuracy of Multi-Temporal Landsat Images by Assessing the Use of Different Algorithms, Textural and Ancillary Information for a Mediterranean Semiarid Area from 2000 to 2015

Abstract

Abstract:The aim of this study was to evaluate three different strategies to improve classification accuracy in a highly fragmented semiarid area using, (i) different classification algorithms with parameter optimization in some cases; (ii) different feature sets including spectral, textural and terrain features; and (iii) different seasonal combinations of images. A three-way ANOVA was used to discern which of these approaches and their interactions significantly increases accuracy. Tukey-Kramer contrast using a heteroscedasticity-consistent estimation of the kappa covariances matrix was used to check for significant differences in accuracy. The experiment was carried out with Landsat TM, ETM and OLI images corresponding to the period 2000-2015. A combination of four images using random forest and the three feature sets was the best way to improve accuracy. Maximum likelihood, random forest and support vector machines do not significantly increase accuracy when textural information was added, but do so when terrain features were taken into account. On the other hand, sequential maximum a posteriori increased accuracy when textural features were used, but reduced accuracy substantially when terrain features were included. Random forest using the three feature subsets and sequential maximum a posteriori with spectral and textural features had the largest kappa values, around 0.9.

Isolation Forests to Evaluate Class Separability and the Representativeness of Training and Validation Areas in Land Cover Classification

“…Winter images were excluded as cloud free data for those months were unavailable. However, Gomariz Castillo et al (2017) concluded, in a multi-temporal study, that winter images are the least informative for this region [24]. The images were downloaded through the Semi-automatic Classification Plugin (SCP) of the GIS software QGIS [25] , which also allows the preprocessing of images.…”

Effect of watershed subdivision and estimation of climatic variables on hydrological simulation with the swat model in semi-arid mediterranean basins

“…Longitud del eje del cauce principal; Tc: Tiempo de concentración de Kirpich. Fuente: elaboración propia En lo referente a la obtención de los parámetros característicos de las URHs, el mapa de usos del suelo utilizado para su reasignación con las categorías de SWAT ha sido el generado para 2010 en GOMARIZ-CASTILLO et al (2017b). La ventaja de esta clasificación es su resolución espacial (30 m), la elevada concordancia entre los datos de validación y el mapa clasificado (se clasificaron de forma correcta el 89,86 % de los píxeles, con un índice Kappa de 0,88) y el periodo de tiempo (2010, final del periodo de simulación y próximo a la fecha de MDT05).…”

Clasificación de imágenes Landsat-8 en la Demarcación Hidrográfica del Segura

“…Diversas estrategias se han propuesto para añadir nueva información relevante a la reflectividad de las diferentes bandas de una imagen de satélite. El uso de información textural destaca la variación espacial del brillo de una imagen, favoreciendo así la separabilidad de las clases (Berberoglu et al, 2007, Gomariz et al, 2017. Wang y Tenhunen (2004), Ezzine et al (2014) o Gomariz et al (2017) muestran cómo, debido a la estacionalidad de usos y coberturas, el uso de una imagen por estación aumenta la exactitud de la clasificación de usos del suelo.…”