La estimación de la biomasa aérea usando sistemas de aprendizaje automático es útil para conocer de forma rápida y sistemática la productividad en bosques y plantaciones. En este estudio la biomasa aérea (AGB) se estimó para las plantaciones forestales de Eucalyptus grandis y Pinus spp. ubicadas en el sector centro-oriental del departamento del Cauca (Colombia). Las variables de mayor incidencia en AGB para E. grandis fueron las bandas SWIR y las texturas de la polarización VV; mientras que para P. spp fueron CorrelaciónVV, GNDVI y B2. Los modelos obtenidos combinando datos ópticos y SAR muestran mejores resultados con un coeficiente de determinación R2 = 0.27 y un error cuadrado promedio EMC = 42.75 t.ha-1 en E. grandis, y R2 = 0.36 y EMC = 141.71 t.ha-1 en Pinus spp. El estudio demostró el potencial de combinar datos Sentinel para estimar la AGB en plantaciones comerciales y el uso de Randon forest para la construcción de los modelos, pero aún se requiere el estudio del acoplamiento espacial de los datos de campo y su incidencia en las estimaciones de los modelos, así como la pertinencia de adelantar estudios a nivel de especies para evaluar su incertidumbre.
This paper describes the implementation of a prototype REST service for triangulation of point sets collected by mobile GPS receivers. The first objective of this paper is to test functionalities of an application, which exploits mobile devices' capabilities to get data associated with their spatial location. A triangulation of a set of points provides a mechanism through which it is possible to produce an accurate representation of spatial data. Such triangulation may be used for representing surfaces by Triangulated Irregular Networks (TINs), and for decomposing complex two-dimensional spatial objects into simpler geometries. The second objective of this paper is to promote the use of oriented matroids for finding alternative solutions to spatial data processing and analysis tasks. This study focused on the particular case of the calculation of triangulations based on oriented matroids. The prototype described in this paper used a wrapper to integrate and expose several tools previously implemented in C++.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.