Predicting gully densities at sub‐continental scales: a case study for the Horn of Africa

Abstract

Despite its environmental and scientific significance, predicting gully erosion remains problematic. This is especially so in strongly contrasting and degraded regions such as the Horn of Africa. Machine learning algorithms such as random forests (RF) offer great potential to deal with the complex, often non‐linear, nature of factors controlling gully erosion. Nonetheless, their applicability at regional to continental scales remains largely untested. Moreover, such algorithms require large amounts of observations for model training and testing. Collecting such data remains an important bottleneck. Here we help to address these gaps by developing and testing a methodology to simulate gully densities across Ethiopia, Eritrea and Djibouti (total area: 1.2 million km2). We propose a methodology to quickly assess the gully head density (GHD) for representative 1 km2 study sites by visually scoring the presence of gullies in Google Earth and then converting these scores to realistic estimates of GHD. Based on this approach, we compiled GHD observations for 1,700 sites. We used these data to train sets of RF regression models that simulate GHD at a 1 km2 resolution, based on topographic/geomorphic, land cover, soil and rainfall conditions. Our approach also accounts for uncertainties in GHD observations. Independent validations showed generally acceptable simulations of regional GHD patterns. We further show that: (i) model performance strongly depends on the amount of training data used, (ii) large prediction errors mainly occur in areas where also the predicted uncertainty is large and (iii) collecting additional training data for these areas results in more drastic model performance improvements. Analyses of the feature importance of predictor variables further showed that patterns of GHD across the Horn of Africa strongly depend on NDVI and annual rainfall, but also on normalized steepness index (ksn) and distance to rivers. Overall, our work opens promising perspectives to assess gully densities at continental scales. © 2020 John Wiley & Sons, Ltd.

Measuring, modelling and managing gully erosion at large scales: A state of the art

“…Minasny and McBratney, 2006) or by using a (semi-) random sampling procedure of smaller sites to be mapped (e.g. Vanmaercke et al, 2020).…”

“…Their successful application results in a gully erosion susceptibility map (GESM), from which proxies of gully density can be derived. However, some approaches try to directly predict the gully density within a catchment (Zhao et al, 2016) or pixel (Kheir et al, 2007;Vanmaercke et al, 2020).…”

“…They can also be used to spatially assess uncertainties on model outputs, thus guiding interpretation and targeting further data collection (e.g. Kuhnert et al, 2010;Vanmaercke et al, 2020).…”

“…Various studies successfully used NDVI as a predictor for gully densities (e.g. Zhao et al, 2016;Vanmaercke et al, 2020). Nonetheless, also other indices may be useful for gully erosion modelling, e.g.…”

“…However, the role of soil properties in explaining patterns of gully erosion remains relatively poorly understood (e.g. Torri and Poesen, 2014;Vanmaercke et al, 2016Vanmaercke et al, , 2020. One reason for this is that soil properties affect both the hydrological functioning of soils but also their erosion resistance during concentrated flow shear stresses (e.g.…”