| Sumario: | Despite its well documented role in improving agricultural productivity, agricultural mechanization adoption remains very low in Ethiopia. Within the context of agricultural mechanization, tractors represent the dominant source of mechanical farm power used to perform farm operations. This study develops a national-scale spatial assessment of tractor suitability by integrating expert-based multi-criteria analysis, Analytic Hierarchy Process (AHP) weighting, and machine-learning models trained on observed tractor use from LSMS survey data. Using harmonized 1 km resolution datasets on soils, topography, accessibility, rainfall, and farm size, we map both technical suitability and predicted adoption intensity. Results show strong spatial heterogeneity, with slope, farm size, and accessibility emerging as dominant constraints. The framework highlights where mechanization investments are most viable and where complementary policy interventions might be required.
|
|---|