TY - JOUR

T1 - Soil organic carbon stock retrieval from Sentinel-2A using a hybrid approach

AU - Сулейманов, Азамат Русланович

AU - Абакумов, Евгений Васильевич

AU - Низамутдинов, Тимур Ильгизович

AU - Поляков, Вячеслав Игоревич

AU - Шевченко, Евгений Викторович

AU - Макарова, Мария Владимировна

PY - 2024/1/1

Y1 - 2024/1/1

N2 - Digital soil maps find application in numerous fields, making their accuracy a crucial factor. Mapping soil properties in homogeneous landscapes where the soil surface is concealed, as in forests, presents a complex challenge. In this study, we evaluated the spatial distribution of soil organic carbon stocks (SOCstock) under forest vegetation using three methods: regression kriging (RK), random forest (RF), and RF combined with ordinary kriging of residuals (RFOK) in combination with Sentinel-2A satellite data. We also compared their accuracies and identified key influencing factors. We determined that SOCstock ranged from 0.6 to 10.9 kg/m2 with an average value of 4.9 kg/m2. Among the modelling approaches, we found that the RFOK exhibited the highest accuracy (RMSE = 1.58 kg/m2, NSE = 0.33), while the RK demonstrated a lack of spatial correlation of residuals, rendering this method inapplicable. An analysis of variable importance revealed that the SWIR B12 band of the Sentinel-2A satellite contributed the most to RFOK predictions. We concluded that the RFOK hybrid approach outperformed the others, potentially serving as a foundation for digital soil mapping under similar environmental conditions. Therefore, it is essential to consider spatial correlations when mapping soil properties in ecosystems that are inaccessible for capturing the spectral response of the soil surface.

AB - Digital soil maps find application in numerous fields, making their accuracy a crucial factor. Mapping soil properties in homogeneous landscapes where the soil surface is concealed, as in forests, presents a complex challenge. In this study, we evaluated the spatial distribution of soil organic carbon stocks (SOCstock) under forest vegetation using three methods: regression kriging (RK), random forest (RF), and RF combined with ordinary kriging of residuals (RFOK) in combination with Sentinel-2A satellite data. We also compared their accuracies and identified key influencing factors. We determined that SOCstock ranged from 0.6 to 10.9 kg/m2 with an average value of 4.9 kg/m2. Among the modelling approaches, we found that the RFOK exhibited the highest accuracy (RMSE = 1.58 kg/m2, NSE = 0.33), while the RK demonstrated a lack of spatial correlation of residuals, rendering this method inapplicable. An analysis of variable importance revealed that the SWIR B12 band of the Sentinel-2A satellite contributed the most to RFOK predictions. We concluded that the RFOK hybrid approach outperformed the others, potentially serving as a foundation for digital soil mapping under similar environmental conditions. Therefore, it is essential to consider spatial correlations when mapping soil properties in ecosystems that are inaccessible for capturing the spectral response of the soil surface.

KW - Digital soil mapping

KW - Kriging

KW - Random forest

KW - Remote sensing

KW - Spatial assessment

UR - https://www.mendeley.com/catalogue/2790f5ee-f634-33b3-a48c-8cb2e94bbb25/

U2 - 10.1007/s10661-023-12172-y

DO - 10.1007/s10661-023-12172-y

M3 - Article

VL - 196

JO - Environmental Monitoring and Assessment

JF - Environmental Monitoring and Assessment

SN - 0167-6369

IS - 1

M1 - 23

ER -