Machine Learning Techniques Applied to the Assessment of GPS Accuracy under the Forest Canopy

Abstract

The geographic location of points using global positioning system (GPS) receivers is less accurate in forested environments than in open spaces because of signal loss and the multipath effect of tree trunks, branches, and leaves. This has been confirmed in studies that have concluded that a relationship exists between measurement accuracy and certain variables that characterize forest canopy, such as tree density, basal area, and biomass volume. However, the practical usefulness of many of these studies is limited because they are often limited to describing associations between the variables and mean errors in the measurement interval, when measurements should be made in real time and in intervals of seconds. In this work, machine learning techniques were applied to build mathematical models that would associate observation error and GPS signal and forest canopy variables. The results reveal that the excessive complexity of the signal prevents accurate measurement of observation error, especially in the