**4. Conclusions**

The approach based on the combination of orbital remote sensing data, with random forest (RF) and OK models to predict properties of soils in the Brazilian semiarid region, was considered satisfactory for sand, clay and CEC contents, and unsatisfactory for Na content.

The use of remote sensing data to map soil properties in flat relief areas, where common topographic covariates may not result in adequate maps by digital soil technics, is an advance. However, more research is needed to improve the quality of the covariates used as an input data.

The zoning procedures through multivariate analysis allowed to identify areas with higher salinization risks and where the management of irrigation is more complex. In the same way, the approach allowed to recognize zone of soils with lower sodium content and clay activity, which are preferred to grow annual crops.

## **Author details**

Helena Saraiva Koenow Pinheiro<sup>1</sup> \*, Pedro Armentano Mudado Xavier<sup>1</sup> , Lúcia Helena Cunha dos Anjos<sup>1</sup> , Cesar da Silva Chagas<sup>2</sup> and Waldir de Carvalho Júnior<sup>2</sup>

1 Soil's Department, Agronomy Institute, Federal Rural University of Rio de Janeiro (UFRRJ), Seropédica, RJ, Brazil

2 Embrapa Solos, Rio de Janeiro, RJ, Brazil

\*Address all correspondence to: lenask@gmail.com

© 2019 The Author(s). Licensee IntechOpen. This chapter is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/ by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

*Pedometric Tools Applied to Zoning Management of Areas in Brazilian Semiarid Region DOI: http://dx.doi.org/10.5772/intechopen.88526*
