Leonardo Ramirez-Lopez

TL;DR: In this article, the authors developed and analyzed a global soil visible-near infrared (vis-NIR) spectral library, which is currently the largest and most diverse database of its kind, and showed that the information encoded in the spectra can describe soil composition and be associated to land cover and its global geographic distribution, which acts as a surrogate for global climate variability.

TL;DR: In this article, the authors describe the state of the art of soil spectroscopy as well as its potential to facilitate soil monitoring, and highlight that the widespread use of spectroscopes to monitor the status of the soil should be encouraged by the creation of a standard for the collection of laboratory soil spectra, to promote the sharing of spectral libraries, and to scan existing soil archives.

TL;DR: It is shown that memory-based learning (MBL) is a very promising approach to deal with complex soil visible and near infrared (vis–NIR) datasets and that soil vis-NIR distance matrices can be used to further improve the prediction performance of spectral models.

TL;DR: In this article, the authors investigated the potential use of VNIRDRS to classify soils in a region with variable soils, geology, and topography in southeastern Brazil, using principal component (PC) analysis and multinomial logistic regression to classify 291 soils at the levels of order (highest), suborder (second highest), and suborder plus textural classification (STC).

TL;DR: In this paper, a new hyper-scale terrain analysis approach, referred to as Contextual Statistical Mapping (ConStat), is presented, which is based on statistical neighborhood measures derived for growing sparse circular neighborhoods.