Unveiling Undercover Cropland Inside Forests Using Landscape Variables: A Supplement to Remote Sensing Image Classification

Abstract

The worldwide demand for food has been increasing due to the rapidly growing global population, and agricultural lands have increased in extent to produce more food crops. The pattern of cropland varies among different regions depending on the traditional knowledge of farmers and availability of uncultivated land. Satellite images can be used to map cropland in open areas but have limitations for detecting undergrowth inside forests. Classification results are often biased and need to be supplemented with field observations. Undercover cropland inside forests in the Bale Mountains of Ethiopia was assessed using field observed percentage cover of land use/land cover classes, and topographic and location parameters. The most influential factors were identified using Boosted Regression Trees and used to map undercover cropland area. Elevation, slope, easterly aspect, distance to settlements, and distance to national park were found to be the most influential factors determining undercover cropland area. When there is very high demand for growing food crops, constrained under restricted rights for clearing forest, cultivation could take place within forests as an undercover. Further research on the impact of undercover cropland on ecosystem services and challenges in sustainable management is thus essential.

Fig 1. Study site and land use/land cover classes a) Location of the study site and distribution of sample plots b) Major land use/land cover types derived using Random Forest classification of RapidEye images.

Field estimated percent cropland per plot is overlaid on the land use/land cover map.

Fig 2. General workflow of a) Field data sampling b) Image classification c) Validation of classification results.

Fig 3. Boosted Regression Trees fitted model showing the relative importance of influential factors of undercover cropland area calculated from field estimated percent cover.

Fig 4. Undercover cropland area predicted from most influential topographic factors identified using Boosted Regression Trees.

Fig 5. Undercover cropland area calculated from field estimated percent cover for selected sample plots with an area of 36 hectares.

Photos labeled a to d show close range view of the undercover cropland taken at the location on the map labeled with the same letters.