This study was conducted with the objective of comparing the performance of differentrnimage classification techniques in discriminating Yushania alpina K. Shmann Lin.rn(highland bamboo) from other land cover classes, with the use of medium resolutionrnimages in three Woredas of the Bale highland. A subset of four Landsat 7 ETM+rnimages acquired on the 28th of November and 5th of February 2000, (path 167 / rows 55-rn56 and path 168 / rows 55-56), covering the study area were used for the classification.rnThe image processing software employed was ENVI 4.3. After performing thernnecessary pre-classification processes, Decision Tree and Maximum Likelihoodrnclassification techniques were applied on the images and the results thereof werernexamined using confusion matrix. Landsat 7 ETM+ image derived data sets such asrntasseled cap and as well the spectral values of the different bands of the images werernused as the decision rules in the Decision Tree Classifier. Analysis of the accuracyrnassessment had revealed that it had an overall accuracy of 66.79% and a Kappa statisticrnof agreement of about 0.56. The technique also showed userâ€™s accuracy of 23.05% forrnbamboo class. The other classification technique evaluated was maximum likelihood,rnfor which region of interest, based on the field data was delineated as a training guide inrnthe classification process. The Maximum likelihood classification showed an overallrnaccuracy of 87.75% and a Kappa value of about 0.84. Userâ€™s accuracy for bamboornforest by this technique was 40.56%.rnThe potential highland bamboo growing areas of Ethiopia was mapped in order tornprovide an indication of the suitable areas for the growth and future expansion of Y.rnalpine, to guide the establishment of observation plots from which detailed ecologicalrnrequirements of the species can further be investigated and to direct future mapping ofrnthe resource. The existing temperature, rainfall and altitudinal information were used tornidentify the location of these areas and it covered an estimated 7,632,788ha representingrnabout 6.74% of the total country. Classification results showed that the existingrnHighland bamboo land units found in the study area cover a total of 63,407.32ha. Therndominant corresponding soil types of these areas are Orthic Luvisols, Chromic Luvisolsrnand with not less correlation with Eutric Cambisols, Eutric Fluvisols and EutricrnNitosols.rnKeywords: Yushania alpina, Landsat 7 ETM+, remote sensing, Bale highland, bamboo