article · Land
Rapid expansion and intensive cultivation of khat in Eastern Ethiopia has raised concerns regarding soil organic carbon depletion. Researchers collected and analysed 88 soil samples across the Haramaya District to quantify carbon stocks, combining this data with Sentinel-2 and RapidEye satellite imagery alongside topographic and environmental indicators. Using machine learning algorithms, they mapped carbon distributions across diverse land uses. Laboratory measurements indicated carbon stocks ranging between 24.99 and 65.94 megagrams of carbon per hectare. Random Forest models outperformed extreme gradient boosting, achieving moderate predictive accuracy using both RapidEye and Sentinel-2 inputs. Key predictive variables included the Topographic Wetness Index, land surface temperature, and soil clay content, alongside vegetation and water indices. Across both datasets, the lowest carbon stocks appeared in bare land, grasslands, and shrublands. This methodology offers baseline spatial data to guide sustainable land management and regional climate mitigation initiatives.
Soil organic carbon plays an essential role in agricultural productivity and regional climate regulation. As cash crops like khat expand across Eastern Ethiopia, accurate mapping helps environmental managers and policymakers track carbon depletion. Combining satellite imagery with machine learning provides a practical framework for identifying degraded areas and targeting sustainable soil management practices without relying entirely on extensive ground sampling.
This applied research provides a predictive framework that could assist agricultural extension agencies, environmental monitoring bodies, and land management programmes in Eastern Ethiopia. The approach demonstrates moderate predictive accuracy at an applied research stage. To move closer to practical deployment or commercial environmental monitoring services, the machine learning models would require further refinement to improve accuracy across varying sensors and diverse agricultural topographies.
AI-generated from the published abstract. Always read the original work before citing.
Soil organic carbon (SOC) stock is a key component of terrestrial ecosystems, playing a critical role in climate regulation and ecosystem productivity. Despite its economic importance, the impacts of the expansion of khat (Catha edulis) cultivation at the expense of other land uses and its intensive management practices on the depletion of soil carbon content are overlooked in Eastern Ethiopia. This study aimed to estimate and map SOC stocks using multispectral Sentinel-2 and RapidEye imagery, combined with environmental, soil, and topographic variables, across khat-dominated landscapes in the Haramaya District of Eastern Ethiopia. A total of 88 soil samples were collected and analyzed to quantify SOC stocks. Random Forest (RF) and extreme gradient boosting (XGBoost) algorithms were employed to predict SOC stocks. The dataset was stratified into training (70%) and an independent validation (30%) subset. Model development was performed using five-fold cross-validation on the training dataset, while final performance was assessed on the independent validation set using the coefficient of determination (R2), root mean square error (RMSE) and mean absolute error (MAE). Laboratory-measured SOC stocks ranged from 24.99 to 65.94 Mg C ha−1, with a mean value of 36.88 Mg C ha−1. The predicted spatial SOC stocks ranged from 30.4 to 50.4 Mg C ha−1 using RapidEye data and from 32.8 to 51.5 Mg C ha−1 using Sentinel-2, with Sentinel-2 producing slightly higher mean estimates. The lowest SOC stocks were consistently observed in bare, grass, and shrub land-use types across both datasets. RF demonstrated superior performance compared with XGBoost, achieving moderate predictive performance for both the RapidEye (R2 = 0.56, RMSE = 5.91 Mg C ha−1) and Sentinel-2 (R2 = 0.42, RMSE = 6.90 Mg C ha−1) datasets. This result indicates that RF provided greater robustness for SOC stock prediction under the heterogeneous environmental conditions of khat-dominated agricultural landscapes. Topographic and soil-related variables, particularly the Topographic Wetness Index (TWI), land surface temperature (LST), and clay content, were identified as the most influential predictors in both models. Although less consistent, remote sensing indices such as GNDVI, BSI, and NDWI also contributed to SOC prediction. While both sensors proved effective for SOC mapping, a measurable sensor-related effect was observed. The findings demonstrate the effectiveness of integrating multisource remote sensing, environmental, soil, and topographic variables with machine learning for SOC stock mapping in khat-dominated landscapes. This approach provides valuable spatial information to understand SOC variability and support sustainable land management and climate change mitigation strategies in Eastern Ethiopia.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/land15081492
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
