Machine Learning With GA Optimization to Model the Agricultural Soil-Landscape of Germany: An Approach Involving Soil Functional Types With Their Multivariate Parameter Distributions Along the Depth Profile

Societal demands on soil functionality in agricultural soil-landscapes are confronted with yield losses and environmental impact. Soil functional information at national scale is required to address these challenges. On behalf of the well-known theory that soils and their site-specific characteristics are the product of the interaction of the soil-forming factors, pedometricians seek to model the soil-landscape relationship using machine learning. Following the rationale that similarity in soils is reflected by similarity in landscape characteristics, we defined soil functional types (SFTs) which were projected into space by machine learning. Each SFT is described by a multivariate soil parameter distribution along its depth profile. SFTs were derived by employing multivariate similarity analysis on the dataset of the Agricultural Soil Inventory. Soil profiles were compared on behalf of differing sets of soil properties considering the top 100 and 200 cm, respectively. Various depth weighting coefficients were tested to attribute topsoil properties higher importance. Support vector machine (SVM) models were then trained employing optimization with a distributed multiple-population hybrid Genetic algorithm for parameter tuning. Model training, tuning, and evaluation were implemented in a nested k-fold cross-validation approach to avoid overfitting. With regards to the SFTs, organic soils were differentiated from mineral soils of various particle size distributions being partly influenced by waterlogging and groundwater. Further SFTs reflect soils with a depth limitation within the top 100 cm and high stone content. Altogether, with SVM predictive model accuracies between 0.7 and 0.9, the agricultural soil-landscape of Germany was represented with eight SFTs. Soil functionality with regards to the soil’s capacity to store plant-available water and soil organic carbon is well characterized. Four additional soil functions are described to a certain extent. An extension of the approach to fully cover soil functions such as nutrient cycling, agricultural biomass production, filtering of contaminants, and soil as a habitat for soil biota is possible with the inclusion of additional soil properties. Altogether, the developed data product represents the 3D multivariate soil parameter space. Its agglomerated simplicity into a limited number of spatially allocated process units provides the basis to run agricultural process models at national scale (Germany).

Manure Applications Combined With Chemical Fertilizer Improves Soil Functionality, Microbial Biomass and Rice Production in a Paddy Field

Synthetic fertilizer with organic fertilizer (OF) is an approach for the improvement of soil health and quality without compromising crop yield. Therefore, a two-year field experiment was conducted to explore optimal chemical fertilizer (CF) management strategies in the context of OF, such as cattle manure (CM) and poultry manure (PM) fertilization to Ultisol soil to improve soil microbial biomass production, enzyme activities and nutrient contents, as well as grain yield of rice. A total of six treatments in the following combinations were used: i.e., T1— CF0; T2—100% CF; T3—60% CM + 40% CF; T4—30% CM + 70%CF; T5—60% PM + 40% CF, and T6—30% PM + 70% CF. Results showed that the combined fertilization significantly increased soil enzymatic activities such as soil invertase, acid phosphatase, urease, catalase, ꞵ-glucosidase, and cellulase as compared to sole CF application. Similarly, the integrated manure and inorganic fertilizers led to significant increases in soil microbial biomass carbon (MBC), microbial biomass nitrogen (MBN), soil pH, soil organic carbon (SOC), total nitrogen (TN), available nitrogen (AN), available phosphorous (AP) and grain yield of rice. Average increases in soil MBC, MBN, SOC AN, and AP in the 0–20 cm soil depth were 62.2%, 54.5%, 29.2%, 17.4%, and 19.8%, respectively, across the years in treatment T3 compared with T2. Interestingly, the linear regression analysis displayed that soil enzymatic activities were highly positively correlated with MBC and MBN. Furthermore, the PCA exhibited that the improved soil enzyme activities and microbial biomass production played a key role in the higher grain yield of rice. Overall, the results of this study demonstrate that the combined use of CF and OF in paddy soil could be beneficial for the farmers in southern China by improving soil functionality and yield of rice on a sustainable basis.

Effects of Land-Use Change on Soil Functionality and Biodiversity: Toward Sustainable Planning of New Vineyards

Sustainable agriculture largely depends on soil biodiversity and requires efficient methods to assess the effectiveness of agronomic planning. Knowledge of the landscape and relative pedosite is enriched by data on the soil microarthropod community, which represent useful bio-indicators for early soil-quality detection in land-use change (LUC). In the hilly Maremma region of Grosseto, Italy, two areas, a >10ys meadow converted into a vineyard and an old biodynamic vineyard (no-LUC), were selected for evaluating the LUC effect. For maintaining soil vitality and ecosystem services by meadow, the vineyard was planted and cultivated using criteria of the patented “Corino method”. The aim was to evaluate the LUC impact, within one year, by assessing parameters characterizing soil properties and soil microarthropod communities after the vineyard was planted. The adopted preservative method in the new vineyards did not show a detrimental impact on the biodiversity of soil microarthropods, and in particular, additional mulching contributed to a quick recovery from soil stress due to working the plantation. In the short term, the adopted agricultural context confirmed that the targeted objectives preserved the soil quality and functionality.

Biochar remediation of soil: linking biochar production with function in heavy metal contaminated soils

The focus of this study is on the soil physicochemical, biological, and microbiological processes altered by biochar application to heavy metal (HM) contaminated soils. The aim is to highlight agronomical and environmental issues by which the restorative capacity of biochar might be developed. Literature shows biochar can induce soil remediation, however, it is unclear how soil processes are linked mechanistically to biochar production and if these processes can be manipulated to enhance soil remediation. The literature often fails to contribute to an improved understanding of the mechanisms by which biochar alters soil function. It is clear that factors such as biochar feedstock, pyrolysis conditions, application rate, and soil type are determinants in biochar soil functionality. These factors are developed to enhance our insight into production routes and the benefits of biochar in HM soil remediation. Despite a large number of studies of biochar in soils, there is little understanding of long-term effects, this is particularly true with respect to the use and need for reapplication in soil remediation.