Application of unsupervised learning of finite mixture models in ASTER VNIR data-driven land use classification

Zhao, Bo; Yang, Fan; Zhang, Rongzhen; Shen, Jingjing; Pilz, Jürgen; Zhang, Dehui

doi:10.1080/14498596.2019.1570478

Cited by 9 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The EM is a well-known algorithm that is available in many computerized calculation tools and, as shown, its use is relatively straightforward. This algorithm is for general use in optimization and is included in packages suitable for determining the parameters of normal mixtures, as is the case of the mixtools package of R (R, 2021(R, , Benaglia et al, 2008, that has been used in this work. If this is possible, as in the example presented above, we can reproduce the empirical data distribution function through a theoretical model, which, once obtained, can be extended to the entire population.…”

Section: Discussionmentioning

confidence: 99%

“…In this way, the probability of an observed value comes from the mixture of the probabilities that it comes from each of the distributions that make up the mixture. The first works date back to 1894 when Pearson worked with the mixture of two normal distributions with the same variance and has been developed by multiple researchers (a detailed review can be seen in McLachlan-Peel, 2000;McLachlan et al, 2019, or Huang et al, 2017 and some examples of recent applications of mixtures in different fields can be seen, for instance, in Zhao et al, 2021or Li et al, 2021. To the best of our knowledge, this approach has never been previously applied to the case of errors in DEM.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Finite mixtures of normal distributions in the study of the error in altimetry

Avi¹,

López²

2021

Adv. Cartogr. GIScience Int. Cartogr. Assoc.

View full text Add to dashboard Cite

Abstract. The modelling of the altimetric error is proposed by means of the mixture of normal distributions. This alternative allows to avoid the problems of lack of normality of the altimetric error and that have been indicated numerous times. The conceptual bases of the mixture of distributions are presented and its application is demonstrated with an applied example. In the example, the altimetric errors existing between a DEM with 5 × 5 m resolution and another DEM with 2 × 2 m resolution are modelled, which is considered as a reference. The application demonstrates the feasibility and power of analysis of the proposal made.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Finite mixtures of normal distributions in the study of the error in altimetry

Avi¹,

López²

2021

Adv. Cartogr. GIScience Int. Cartogr. Assoc.

View full text Add to dashboard Cite

show abstract

“…Therefore, this experiment calculated the NDWI to extract Pedicularis [47]. Numerous studies have verified that the three indices are efficient for land use/land cover and target extraction [44,45,[48][49][50][51].…”

Section: Planetscope Imagerymentioning

confidence: 98%

Spatiotemporal Pattern of Invasive Pedicularis in the Bayinbuluke Land, China, during 2019–2021: An Analysis Based on PlanetScope and Sentinel-2 Data

Wang,

Tang,

Zhang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The accurate identification and monitoring of invasive plants are of great significance to sustainable ecological development. The invasive Pedicularis poses a severe threat to native biodiversity, ecological security, socioeconomic development, and human health in the Bayinbuluke Grassland, China. It is imperative and useful to obtain a precise distribution map of Pedicularis for controlling its spread. This study used the positive and unlabeled learning (PUL) method to extract Pedicularis from the Bayinbuluke Grassland based on multi-period Sentinel-2 and PlanetScope remote sensing images. A change rate model for a single land cover type and a dynamic transfer matrix were constructed under GIS to reflect the spatiotemporal distribution of Pedicularis. The results reveal that (1) the PUL method accurately identifies Pedicularis in satellite images, achieving F1-scores above 0.70 and up to 0.94 across all three datasets: PlanetScope data (seven features), Sentinel-2 data (seven features), and Sentinel-2 data (thirteen features). (2) When comparing the three datasets, the number of features is more important than the spatial resolution in terms of use in the PUL method of Pedicularis extraction. Nevertheless, when compared with PlanetScope data, Sentinel-2 data demonstrated a higher level of accuracy in predicting the distribution of Pedicularis. (3) During the 2019–2021 growing season, the distribution area of Pedicularis decreased, and the distribution was mainly concentrated in the northeast and southeast of Bayinbuluke Swan Lake. The acquired spatiotemporal pattern of invasive Pedicularis could potentially be used to aid in controlling Pedicularis spread or elimination, and the methods proposed in this study could be adopted by the government as a low-cost strategy to identify priority areas in which to concentrate efforts to control and continue monitoring Pedicularis invasion.

show abstract

“…De esta manera, la probabilidad de un valor observado procede de la mezcla de las probabilidades de que proceda de cada una de las distribuciones que componen la mixtura. Los primeros trabajos se remontan a 1894, cuando Pearson trabajó con la mezcla de dos distribuciones normales con la misma varianza y ha sido desarrollada por múltiples investigadores (una revisión detallada puede verse en McLachlan-Peel, 2000;McLachlan et al, 2019, o Huang et al, 2017 y algunos ejemplos de aplicaciones recientes de mixturas en diferentes campos pueden verse en Pan et al, 2020;Sallay et al, 2020;Zhao et al, 2021o Li et al, 2021.…”

Section: Introductionunclassified

Caracterización del error en MDE por mixtura de distribuciones

Avi

2021

rcarto

View full text Add to dashboard Cite

La exactitud posicional de los modelos digitales de elevaciones (MDE) suele evaluarse por medio del análisis del error vertical que se observa en muestras de puntos. Las técnicas estadísticas tradicionales suponen que los errores altimétricos siguen distribuciones normales, pero se sabe que esto no es cierto en numerosas ocasiones. En este trabajo se propone, de manera pionera en el campo de los MDE, la utilización de técnicas basadas en la determinación de mixturas (o mezclas) de distribuciones normales para aproximar mejor la distribución de error observada. Se propone un método para aplicar el proceso y se aplica al caso de errores en unos datos reales procedentes de MDE de 2x2 m de paso de malla (referencia) y de 5x5 m (producto).

show abstract

Application of unsupervised learning of finite mixture models in ASTER VNIR data-driven land use classification

Cited by 9 publications

References 31 publications

Finite mixtures of normal distributions in the study of the error in altimetry

Finite mixtures of normal distributions in the study of the error in altimetry

Spatiotemporal Pattern of Invasive Pedicularis in the Bayinbuluke Land, China, during 2019–2021: An Analysis Based on PlanetScope and Sentinel-2 Data

Caracterización del error en MDE por mixtura de distribuciones

Contact Info

Product

Resources

About