Cevdet ŞEKER & Noel MANIRAKIZA - EFFECTIVENESS OF COMPOST AND BIOCHAR IN IMPROVING WATER RETENTION CHARACTERISTICS AND AGGREGATION OF A SANDY CLAY LOAM SOIL UNDER WIND EROSION, Carpathian Journal of Earth and Environmental Sciences, February 2020, Vol. 15, No. 1, p. 5 - 18; DOI:10.26471/cjees/2020/015/103

Evaluation of the land use/ land cover (LULC) case over large regions is very important in a variety of domains, including natural resources such as soil, water, etc., and climate change risks and LULC change has emerged as a high anxiety for the environment. Therefore, we tested and compared the performance of three classification algorithms: Support Vector Machines (SVM), Random Trees (RT), and Maximum Likelihood (MaxL) to derive and extract LULC information for the district of Sarayönü/ Konya across five distinct classes: water, plantation, grassland, built-up, and bare land. Two remote sensing indices, the normalized difference vegetation index (NDVI) and the normalized difference water index (NDWI), were used as supplementary inputs for the classification of LULC. To evaluate the performance of the algorithms, a confusion matrix was employed. The average overall accuracy of support vector machines, random trees, and maximum likelihood algorithms was found 85.60%, 79.20%, and 74.80%, respectively, and 82.00%, 74.00%, and 68.50% for the Kappa coefficient. These results indicate that the support vector machines algorithm outperforms other algorithms in terms of accuracy. As a result of the research, it was determined that classification algorithms integrated with remote sensing in LULC change monitoring/determination could produce accurate classification maps that can be used as base data. This is due to the ability of machine learning algorithms to learn complex patterns, adapt to diverse data, and continuously improve, making them achieve higher accuracy compared to traditional classifiers. Therefore, their use was recommended for decision-makers.

The Sustainable Development Goals of the United Nations call for applying soil management practices that contribute land degradation neutrality. Our objectives were to investigate the effect of (i) soil management—conventional tillage (CT under crop) and no-tillage (NT under grass)—and (ii) an amendment (polyacrylamide (PAM)) application on the structure stability indices of soils from a semi-arid region. Two sets of experiments were conducted using the high-energy moisture characteristic (HEMC) method for the assessment of (i) land-use type (CT vs. NT) in soils (30 samples) varying in texture, and (ii) the effect of six PAM concentrations (0, 10, 25, 50, 100, and 200 mg L⁻¹) on three typical soils (sandy clay loam, clay loam, and clay) under CT management; then, the contributions of PAM concentration (CT) and NT were compared. Water retention curves of samples were obtained at a matric potential from 0 to −5.0 J kg⁻¹ and characterized by a modified van Genuchten model that yields (i) model parameters α and n, and (ii) a soil structure stability index (SI). The treatments affected the shape of the water retention curves. Change of land use from CT to NT and PAM application to CT soil increased the SI and ɑ, and decreased n compared to CT-managed soils. The magnitude of the NT and PAM effect was inversely related to soil clay content. CT-managed soils treated with a low PAM rate (10–25 mg L⁻¹) gave SI comparable to that obtained for the NT-managed soils, while CT-managed soils treated with a high PAM rate (50–200 mg L⁻¹) yielded 1.3–2.0 and 2–4 times higher SI than that for NT and CT-managed soils, respectively. Our findings suggest that both the change of land use to NT or the addition of small amounts of PAM are viable alternatives for stabilizing CT-managed weakly alkaline semi-arid soils, whose soil structure stability is a priori limited.

The direct estimation of soil hydraulic conductivity (Ks) requires expensive laboratory measurement to present adequately soil properties in an area of interest. Moreover, the estimation process is labor and time-intensive due to the difficulties of collecting the soil samples from the field. Hence, innovative methods, such as machine learning techniques, can be an alternative to estimate Ks. This might facilitate agricultural water and nutrient management which has an impact on food and water security. In this spirit, the study presents neural-network-based models (artificial neural network (ANN), deep learning (DL)), tree-based (decision tree (DT), and random forest (RF)) to estimate Ks using eight combinations of soil data under calcareous alluvial soils in a semi-arid region. The combinations consisted of soil data such as clay, silt, sand, porosity, effective porosity, field capacity, permanent wilting point, bulk density, and organic carbon contents. The results compared with the well-established model showed that all the models had satisfactory results for the estimation of Ks, where ANN7 with soil inputs of sand, silt, clay, permanent wilting point, field capacity, and bulk density values showed the best performance with mean absolute error (MAE) of 2.401 mm h⁻¹, root means square error (RMSE) of 3.096 mm h⁻¹, coefficient of determination (R²) of 0.940, and correlation coefficient (CC) of 0.970. Therefore, the ANN could be suggested among the neural-network-based models. Otherwise, RF could also be used for the estimation of Ks among the tree-based models.

Calcareous and sandy soils generally have soil fertility problems, and these problems have been revealed to be improved by applying compost and biochar produced from the distinct biomass. However, comparing the effects of compost and biochar originating from the same biomass on soil fertility are still not clearly explained. The comparing impacts of compost and biochar both made from the same biomass on soil fertility status in a wind erosion afflicted calcareous and alkaline sandy clay loam (SCL) soil, were explored using a pot experiment. Compost and biochar were produced from a pioneering Oleaster (Oleaster Angustifolia L.) tree through the windrow composting method and pyrolysis process at 450 °C, respectively. The SCL soil used was treated with compost and biochar at rates of 0%, 1%, 2%, and 4% by weight and thereafter incubated for 2 months. The trial layout was in line with a completely randomized plot design with four replicates. Pursuant to the experimental results, the addition of compost and biochar considerably enriched soil fertility by enhancing soil biochemical properties of SCL soil. SCL soil treated with compost yielded the highest available phosphorous (AP), organic carbon (OC), total nitrogen (TN), NH₄ ⁺-N, NO₃-N, active carbon (AC), potential mineralizable nitrogen (PMN), soil microbial respiration (SMR), electrical conductivity (EC), CaCO_3, extractable cations (Mg, K, Ca, and Na), cation exchange capacity (CEC), and available micronutrients (Mn, Fe, and Zn), which were significantly higher (P < .001) than the SCL soil amended with biochar, suggesting the recalcitrance of biochar on microbial activities. Furthermore, available micronutrients (Mn, Fe, and Zn) were significantly decreased in SCL soil amended with biochar compared with compost amended SCL soil, indicating the sorption potential of biochar. It was concluded that applying Oleaster tree compost is more effective than biochar in improving soil fertility. However, the effects of biochar on carbon sequestration and the findings of this study need to be proven under field demonstration for more conclusive results prior to recommending farmers to apply either compost or biochar in soil management practices.