Soil organic carbon (SOC) is an important indicator of soil quality and directly determines soil fertility. Hence, understanding its spatial distribution and controlling factors is necessary for efficient and sustainable soil nutrient management. In this study, machine learning algorithms including artificial neural network (ANN), support vector machine (SVM), cubist regression, random forests (RF), and multiple linear regression (MLR) were chosen for advancing the prediction of SOC. A total of sixty (n = 60) soil samples were collected within the research area at 30 cm soil depth and measured for SOC content using the Walkley–Black method. From these samples, 80% were used for model training and 21 auxiliary data were included as predictors. The predictors include effective cation exchange capacity (ECEC), base saturation (BS), calcium to magnesium ratio (Ca_Mg), potassium to magnesium ratio (K_Mg), potassium to calcium ratio (K_Ca), elevation, plan curvature, total catchment area, channel network base level, topographic wetness index, clay index, iron index, normalized difference build-up index (NDBI), ratio vegetation index (RVI), soil adjusted vegetation index (SAVI), normalized difference vegetation index (NDVI), normalized difference moisture index (NDMI) and land surface temperature (LST). Mean absolute error (MAE), root-mean-square error (RMSE) and R2 were used to determine the model performance. The result showed the mean SOC to be 1.62% with a coefficient of variation (CV) of 47%. The best performing model was RF (R2 = 0.68) followed by the cubist model (R2 = 0.51), SVM (R2 = 0.36), ANN (R2 = 0.36) and MLR (R2 = 0.17). The soil nutrient indicators, topographic wetness index and total catchment area were considered an indicator for spatial prediction of SOC in flat homogenous topography. Future studies should include other auxiliary predictors (e.g., soil physical and chemical properties, and lithological data) as well as cover a broader range of soil types to improve model performance.

No abstract

The comparative assessment of wetland and coastal plain soils for agricultural productivity were studied. The investigation was carried out in two areas: Atimbo and Obufa Esuk in Calabar, Cross River State. The dominant particle size in both coastal and wetland soil was sandy texture. The mean bulk density values of 1.35 g/cm 3 and 1.30 g/cm 3 were obtained for Atimbo and Obufa Esuk coastal plain soil while 1.33 g/cm 3 and 1.30 g/cm 3 were obtained for Atimbo and Obufa Esuk wetland soil respectively. Total porosity in wetland soils was lower than coastal plain soil whereas moisture content in wetland soil was higher than coastal plain soil. Except Ap horizon in Atimbo coastal plain soil, the pH observed for the studied soils were all below pH of 5.0 unit which signifies high acidic condition. The mean organic carbon content in coastal plain soil was lower than wetland soil. Available phosphorus in the studied soils were high with Atimbo and Obufa Esuk coastal plain soil having a mean value of 32.10 and 32.42 mg/kg respectively, whereas those in Atimbo and Obufa Esuk wetland soils were 32.73 and 33.88 mg/kg respectively. The exchangeable calcium content obtained for both coastal and wetland soils were all below the critical limit of 5.0 cmolkg-1. Although exchangeable magnesium content was low in both soils but wetland soils was only slightly below the critical value of 1.5cmol/kg when compared to coastal plain soil. Both wetland and coastal plain soils were below (>0.2 cmolkg-1) critical level of K in soils of the zone. Also, exchangeable Na in both soil were low and below 0.3 cmol/kg limit and are adequate for cultivation of arable and tree crops. ECEC in both soils were low whereas percent base saturation was high. The mean C:N ratio in Atimbo and Obufa Esuk coastal plain soil were 11.45 and 15.48 respectively. Comparatively, the C:N ratio in Atimbo and Obufa Esuk wetland soils was slightly higher having a mean value of 16.39 and 18.14 respectively. This also reflect low rate of decomposition because of anaerobic condition of the soil. The Mg:K ratio were low in both soils. The Ca:Mg ratio values were high in wetland soil when compared with a normal range of 3:1-5:1 for productive soils and was low for coastal plain soil. Per cent silt content, moisture content, and exchangeable sodium of soil sample analyzed from wetland and coastal plain soil in Atimbo were significantly different (p<0.05). The result of the studied soils indicated that coastal plain soil is already losing its fertility status as typified by low values of organic carbon, total nitrogen, Exchangeable cations and high acidity couple with low moisture content; hence there is need to harnessed wetland soil for crop productivity. Wetland soils could be exploited for the cultivation of rice, oil palm, coconut, plantain, pineapple and sugar cane with judicious application of lime, and N and K fertilizers since these crops can perform well under acidic condition.

No abstract

No abstract