Tatiana Dias Tardelli Uehara

Tatiana Dias Tardelli Uehara

Auto-generated profile, based on publicly available information

Tatiana Dias Tardelli Uehara

National Institute for Space Research, Earth Observation and Geoinformatics Division, Sao Jose dos Campos, Brazil

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 November 2021 in Geocarto International
Verified
Journal Article
Closed access
Renata Pacheco QuevedoRenata Pacheco Quevedo
Renata Pacheco Quevedo
DMDaniel Andrade Maciel
Daniel Andrade Maciel
TUTatiana Dias Tardelli Uehara
Tatiana Dias Tardelli Uehara
Matej VojtekMatej Vojtek
Matej Vojtek
CRCamilo Rennó
Camilo Rennó
QPQuoc Bao Pham
Quoc Bao Pham
Most previous studies of landslide susceptibility mapping (LSM) have not contemplated spatial heterogeneity and the commonly used models for LSM are aspatial, which could reduce model performance. Therefore, aiming to evaluate the applicability of spatial algorithms to predict landslide susceptibility, the performance of geographical random forest (GRF) was evaluated, in comparison to random forest (RF) and extreme gradient boosting (XGBoost). Based on the results, GRF presented the better performance (AUC = 0.876), followed by RF (AUC = 0.748) and XGBoost (AUC = 0.745). GRF also provided the most suitable susceptibility map. While RF and XGBoost presented almost 50% of the study area as susceptible, the GRF presented more concentrated susceptibility areas spatially, with a reasonable area for moderate (15.55%), high (8.73%) and very-high (2.59%) susceptibility classes. Finally, it can be inferred that spatial assessment may improve model performance, and that spatial models have a great potential for LSM.

14 November 2020 in Revista Brasileira de Cartografia
Verified
Journal Article
Open access
PDF file
TUTatiana Dias Tardelli Uehara
Tatiana Dias Tardelli Uehara
SCSabrina Paes Leme Passos Corrêa
Sabrina Paes Leme Passos Corrêa
Renata Pacheco QuevedoRenata Pacheco Quevedo
Renata Pacheco Quevedo
TKThales Körting
Thales Körting
Luciano Vieira DutraLuciano Vieira Dutra
Luciano Vieira Dutra
CRCamilo Rennó
Camilo Rennó
Landslide inventory is an essential tool to support disaster risk mitigation. The inventory is usually obtained via conventional methods, as visual interpretation of remote sensing images, or semi-automatic methods, through pattern recognition. In this study, four classification algorithms are compared to detect landslides scars: Artificial Neural Network (ANN), Maximum Likelihood (ML), Random Forest (RF) and Support Vector Machine (SVM). From Sentinel-2A imagery and SRTM’s Digital Elevation Model (DEM), vegetation indices and slope features were extracted and selected for two areas at the Rolante River Catchment, in Brazil. The classification products showed that the ML and the RF presented superior results with OA values above 92% for both study areas. These best accuracy’s results were identified in classifications using all attributes as input, so without previous feature selection.

1 July 2022 in Journal of Applied Remote Sensing
Verified
Journal Article
Open access
PDF file
TUTatiana Dias Tardelli Uehara
Tatiana Dias Tardelli Uehara
TKThales Körting
Thales Körting
ASAnderson Soares
Anderson Soares
Renata Pacheco QuevedoRenata Pacheco Quevedo
Renata Pacheco Quevedo
Landslides are a natural gravity-driven phenomenon, which consists of the movement of a mass of soil or rock from the top of the hill toward the bottom. The occurrence of landslides is registered all over the world, frequently in mountainous areas, where there has been extreme precipitation events, earthquakes, or snow melting.1 Landslides happen with recurrence in Brazil and have been the reason for many socioeconomic losses and casualties, for instance, the consequences of the so-called Mega disaster in 2011 at Nova Friburgo in Rio de Janeiro state, Brazil.2