Open Access

Harison K. Kipkulei, Sonoko D. Bellingrath-Kimura, Marcos Lana, Gohar Ghazaryan, Mark Boitt, Stefan Sieber

• Population growth and increasing demand for agricultural production continue to drive global cropland expansions. These expansions lead to the overexploitation of fragile ecosystems, propagating land degradation, and the loss of natural diversity. This study aimed to identify the factors driving land use/land cover changes (LULCCs) and subsequent cropland expansion in Trans Nzoia County in Kenya. Landsat images were used to characterize the temporal LULCCs in 30 years and to derive cropland expansions using change detection. Logistic regression (LR), boosted regression trees (BRTs), and evidence belief functions (EBFs) were used to model the potential drivers of cropland expansion. The candidate variables included proximity and biophysical, climatic, and socioeconomic factors. The results showed that croplands replaced other natural land covers, expanding by 38% between 1990 and 2020. The expansion in croplands has been at the expense of forestland, wetland, and grassland losses, whichPopulation growth and increasing demand for agricultural production continue to drive global cropland expansions. These expansions lead to the overexploitation of fragile ecosystems, propagating land degradation, and the loss of natural diversity. This study aimed to identify the factors driving land use/land cover changes (LULCCs) and subsequent cropland expansion in Trans Nzoia County in Kenya. Landsat images were used to characterize the temporal LULCCs in 30 years and to derive cropland expansions using change detection. Logistic regression (LR), boosted regression trees (BRTs), and evidence belief functions (EBFs) were used to model the potential drivers of cropland expansion. The candidate variables included proximity and biophysical, climatic, and socioeconomic factors. The results showed that croplands replaced other natural land covers, expanding by 38% between 1990 and 2020. The expansion in croplands has been at the expense of forestland, wetland, and grassland losses, which declined in coverage by 33%, 71%, and 50%, respectively. All the models predicted elevation, proximity to rivers, and soil pH as the critical drivers of cropland expansion. Cropland expansions dominated areas bordering the Mt. Elgon forest and Cherangany hills ecosystems. The results further revealed that the logistic regression model achieved the highest accuracy, with an area under the curve (AUC) of 0.96. In contrast, EBF and the BRT models depicted AUC values of 0.86 and 0.77, respectively. The findings exemplify the relationships between different potential drivers of cropland expansion and contribute to developing appropriate strategies that balance food production and environmental conservation.…