Work

Accuracy estimates of land use and land cover classification are associated with the sensitivity of the MAXVER classifier and the holdout subsampling technique on allotments in Pelotas-RS

Year: 2024

Type: article

Abstract: Urban growth in the Pelotas-RS community has intensified in recent years. The number of new subdivisions and housing developments available in the city’s real estate market is a testament to this trend. With this growth, potential problems related to flooding and possible inundation become a cause for concern given the topographical characteristics of the city. One way to monitor this urban expansion is through remote sensing analysis, which provides a wide range of statistical information, including precision and accuracy indices obtained from land use and land cover classification methods. The KAPPA test, for instance, has proven to be very efficient in analyzing areas of impervious surfaces, loss of vegetation cover, etc. These values are important for carrying out urban drainage calculations to determine the dimensioning of rainwater systems. In this case, the study focused on Pelotas. The classification procedure achieved an accuracy of over 90%, which is considered excellent for this type of interpretative analysis.

Source: Ciência e Natura

DOI: 10.5902/2179460x87230

Authors: Everton Rodrigues Zirbes, Daniela Buske, Diuliana Leandro, Andrea Souza Castro

Institution: Universidade Federal de Pelotas

Language: English

Topic: Remote-Sensing Image Classification

Subfield: Media Technology

Field: Engineering

Domain: Physical Sciences

SDGs: Sustainable cities and communities, Life on land

Open Access status: diamond

Funders: Universidade Federal de Pelotas, Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Conselho Nacional de Desenvolvimento Científico e Tecnológico