Maize yield dynamics generally involve temporal changes, because increasing soil organic matter through manure application influences maize yields over the longer term, while inorganic nutrient application controls shorter term yields. These temporal soil properties and yield changes have been measured with long-term experiments. In sub-Saharan Africa (SSA), long-term experiments (more than 20 years) are rare due mainly to lack of funds. Farmers in the semi-arid northern Ethiopian Rift Valley (NERV) apply manure to maize fields in the long term. The relationships between the manure application levels, nutrient supply, soil nutrient levels, maize grain yields, and above-ground plant nutrient uptake levels were investigated by field measurement, interviews with farmers, laboratory analyses, and 2-years' yield trials. The farmers applied on average 6.0 Mg ha(-1) yr(-1) of manure over 16.8 years on average. Significant linear or curve-linear correlations were found (1) between the annual nutrient supply and soil nutrient levels and (2) between the soil nutrient levels and maize productivities with minor exceptions. The regression equations determined from the yield trials proved 3.0 and 4.0 Mg ha(-1) of maize yields can be expected when soil available N contents were 3.9 and 5.1 mg kg(-1) in an ordinary rainfall year in NERV. For the farmers who apply 6.0 Mg ha(-1) yr(-1) manure, they are recommended to use 30 kg ha(-1) yr(-1) additional Urea to attain 3.0 Mg ha(-1) maize yields. These types of assessment methods do not require much cost, and yet it can provide long-term scientific information in SSA.