Dataset for Digital Soil Mapping of Key Soil Properties for Tea Productivity in Tarime District, Tanzania

Title
Dataset for Digital Soil Mapping of Key Soil Properties for Tea Productivity in Ganyange Ward, Tarime District, Tanzania

Description
This dataset supports the study on the application of Random Forest (RF) machine learning in digital soil mapping (DSM) of key soil properties relevant to tea cultivation in Ganyange Ward, Tarime District, Tanzania. The dataset comprises laboratory-analyzed soil properties and environmental covariates used to model spatial variability of soils under a SCORPAN framework.

A total of 64 topsoil samples (0–30 cm depth), including 16 profile-derived surface samples and 48 auger samples, were collected using a conditioned Latin Hypercube Sampling (cLHS) design to capture environmental variability. Laboratory analyses include soil pH, electrical conductivity (EC), soil organic carbon (SOC), total nitrogen (N), available phosphorus (P), exchangeable cations (K, Ca, Mg, Na), cation exchange capacity (CEC), and particle size fractions (sand, silt, clay).

Environmental covariates include Sentinel-2A spectral bands and derived indices (NDVI, SAVI, OSAVI, BSI, CMR, CI, FII, GSI, SER), as well as terrain attributes derived from SRTM DEM (elevation, slope, aspect, topographic wetness index). These variables were used as predictors in RF models for spatial prediction of soil properties.

The dataset is intended to support reproducibility of DSM workflows, machine learning applications in soil science, and GIS-based land suitability analysis for tea cultivation in tropical environments.

Geographical coverage
Ganyange Ward, Tarime District, Mara Region, Tanzania

Coordinate system
WGS84 / UTM Zone 36S (EPSG:32736)

Keywords
Digital Soil Mapping; Random Forest; Soil Properties; Tea Cultivation; Environmental Covariates; GIS; Tanzania