Background Hangadi watershed is endowed with the only virgin forest in Odo shakisso harbouring high biodiversity, but it has been suffered from anthropogenic activities. This study was conducted to investigate composition and community diversity of woody species in restoration for posterity. Satellite images of 1988, 2008, and 2018 were used to classify and analyse trends of deforestation. For both woody species and topsoil (0–30 cm), 20 m × 20 m, 100 plots laid at every 300 m along line transects, 1 km apart from each other. In each sample plot, woody species ≥ 3 m were counted, Shannon–wiener diversity index, cluster analysis and ordination were computed. Results Agroforestry is found to be the dominant land use/land cover class followed by forest and cultivated land. A total of 61 woody species belonging to 34 families; 8.2% of the species were endemic to Ethiopia. The highest number of species was recorded from families Euphorbiaceae and Rubiaceae (5 species, 8.2%), Rutaceae, Celastraceae, and Oleaceae (3 species, 5.08%) followed by Flacourtiaceae, Meliaceae, Araliaceaae, Myrsinaceae, Moraceae, Boraginaceae, Asteraceae, Spontaceae, Lauraceae and Sapindaceae (2 species each). Four woody plant communities were identified using free statistical software R version 3.1.1. The canonical correspondence analysis result showed that EC, pH, OM, altitude, C:N, CEC, sand, silt, AvP, and TN significantly affected species distribution in the watershed. Conclusion Local people involved in cutting mature woody species for timber production, making farm implements and, cultivated land expansion. Protection of woody species diversity of forest and coffee systems with low biodiversity value conservation concepts are recommended to be executed jointly by local people and stakeholders.

Machine learning and geostatistics are efficient techniques for investigating the geographic distribution of soil properties. This study’s objectives were to assess soil fertility status, map the spatial variability of selected soil parameters and compare random forest with ordinary kriging. Soil samples were collected to analyze parameters: pH, cation exchange capacity (CEC) and organic carbon (OC) using systematic sampling. Some environmental covariates were used in the machine learning process: a digital elevation model (DEM) collected from USGS distributing shuttle radar topography mission data and a LULC map generated from a 30-year time series (1988–2018) of Landsat 8. Georeferenced samples were sent to Batu Soil Research Laboratory. pH, CEC and OC were mapped and status was determined using random forest and ordinary kriging. Random forest was more accurate with low mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE) and coefficient of determination (high R2). In random forest, pH varied between 5.03 and 5.76 and ordinary kriging pH ranged from 4.96 to 5.76. pH was greater in cultivated land. CEC and OC were higher in the forest. The higher pH in cultivated land was due to grass coverage and minimal tillage. The addition of organic matter and CEC to a forest may result in higher OC. Environmental covariates (topographic, bands, NDVI and LULC) were used to predict the gradients of pH, OC and CEC. For pH, OC and CEC, DEM was the most important predictor. CEC was high in low landscape, but low in high landscape positions. Low OC requires composting, fallow and organic fertilizers. Future research should include the remaining predictors: physiochemical and lithological data to improve the performance of random forest.