Land Cover Classification of an Area Susceptible to Landslides Using Random Forest and NDVI Time Series Data

Uehara, Tatiana Dias Tardelli; Soares, Anderson R.; Quevedo, Renata Pacheco; Körting, Thales Sehn; Fonseca, Leila María García; Adami, Marcos

doi:10.1109/igarss39084.2020.9324108

Cited by 4 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Summary statistics of the NDVI time series (first, second and third quartile and variance) were calculated to analyse vegetation dynamics, similar to Triscowati et al ( 2019) and Uehara et al (2020). However, the statistics were calculated at different year moments (phases) where NDVI behaves differently across the year.…”

Section: Variable Selection For Clusteringmentioning

confidence: 99%

Vegetation dynamic patterns of arid rangelands : a multifractal approach

Sanz Sancho

View full text Add to dashboard Cite

Rangelands are complex ecosystems with non-linear dynamics in space and time, however, their temporal dynamics have only recently started to be studied and they are not fully understood. Rangelands comprise 30-40% of the Earth´s landmass and their degradation caused by increasing misuse remains a global concern, affecting 73 % of all rangelands. Remote sensing and satellite monitoring methods are commonly used to study ecology and agriculture. Among different satellite indices, the Normalized Difference Vegetation Index (NDVI) is the most widely used vegetation index by rangeland ecologists. The NDVI reveals a good correlation with the biomass of different vegetation types in arid and semi-arid areas. NDVI anomalies (NDVIa and ZNDVI) are other indexes proven useful for identifying drought and water stress on vegetation; therefore, it is suited to study arid and semi-arid ecosystems List of tables xviii NDVI trend are included. For each phase, bold values show the strongest correlations among the different time lags tested.

show abstract

Section: Variable Selection For Clusteringmentioning

confidence: 99%