Quantification of species composition in grass-clover swards using RGB and multispectral UAV imagery and machine learning.

Introduction: Growing grass-legume mixtures for forage production improves both yield productivity and nutritional quality, while also benefiting the environment by promoting species biodiversity and enhancing soil fertility (through nitrogen fixation). Consequently, assessing legume proportions in grass-legume mixed swards is essential for breeding and cultivation. This study introduces an approach for automated classification and mapping of species in mixed grass-clover swards using object-based image analysis (OBIA). Methods: The OBIA procedure was established for both RGB and ten band multispectral (MS) images capturedby an unmanned aerial vehicle (UAV). The workflow integrated structural (canopy heights) and spectral variables (bands, vegetation indices) along with a machine learning algorithm (Random Forest) to perform image segmentation and classification. Spatial k-fold cross-validation was employed to assess accuracy. Results and discussion: Results demonstrated good performance, achieving an overall accuracy of approximately 70%, for both RGB and MS-based imagery, with grass and clover classes yielding similar F1 scores, exceeding 0.7 values. The effectiveness of the OBIA procedure and classification was examined by analyzing correlations between predicted clover fractions and dry matter yield (DMY) proportions. This quantification revealed a positive and strong relationship, with R2 values exceeding 0.8 for RGB and MS-based classification outcomes. This indicates the potential of estimating (relative) clover coverage, which could assist breeders but also farmers in a precision agriculture context.

Renewable P sources: P use efficiency of digestate, processed animal manure, compost, biochar and struvite.

In the attempt to close nutrient cycles, organic fertilizers and soil improvers are getting interest as renewable P sources for crops. However, both the P availability of these compounds for crops and the underlying mechanisms are not fully understood. In this study composts (n = 8), biochars (n = 5), animal manure and processed animal manure (n = 13), digestates and processed digestates (n = 15) and blends of digestates with compost/animal manure/mineral fertilizers (n = 15) were analyzed for chemical composition, organic matter stability and P use efficiency (PUE). Biodegradability (=holocellulose/lignin ratio) proved to be a good indicator for organic matter stability and can successfully replace time-consuming incubation experiments in standard analyses of organic fertilizers. The PUE of digestates, struvites, animal manure products and blends of digestate with compost/animal manure/mineral fertilizers was determined by the NH4+-N, Mg and Fe content of the organic fertilizers. The PUE can be predicted by PUE = 61.34 + 8.59*NH4+-N/P + 42.25*Mg/P - 8.09*Fe/P (R2 = 0.71). As increasing amounts of NH4+-N and Mg stimulate the formation of soluble struvite crystals, increasing PUE is explained by an increasing amount of P as struvite. The PUE of biochars and composts was determined by the Ca/P and Al content of the organic fertilizers. Here, PUE can be predicted by PUE = 88.87-1.07*Ca/P + 6.08*Al/P (R2 = 0.93). As increasing amounts of Ca stimulate the formation of highly stable apatite crystals, increasing PUE is explained by an increasing amount of P in the form of apatite.

Longitudinal screening of antibiotic residues, antibiotic resistance genes and zoonotic bacteria in soils fertilized with pig manure.

Fertilization with animal manure is one of the main routes responsible for the introduction of antibiotic residues, antibiotic resistance genes, and zoonotic bacteria into the environment. The aim of this study was to assess the effect of the use of pig (swine) manure as a fertilizer on the presence and fate of six antibiotic residues, nine antibiotic resistance genes, and bacteria (zoonotic bacteria Salmonella spp. and Campylobacter spp. and E. coli as indicator for Gram-negative bacterial species of the microbiota of livestock) on five fields. To the best of our knowledge, the present study is the first to assess a multitude of antibiotic residues and resistance to several classes of antibiotics in pig manure and in fertilized soil over time in a region with an intensive pig industry (Flanders, Belgium). The fields were sampled at five consecutive time points, starting before fertilization up to harvest. Low concentrations of antibiotic residues could be observed in the soils until harvest. The antibiotic resistance genes studied were already present at background levels in the soil environment prior to fertilization, but after fertilization with pig manure, an increase in relative abundance was observed for most of them, followed by a decline back to background levels by harvest-time on all of the fields studied. No apparent differences regarding the presence of antibiotic resistance genes in soils were observed between those fertilized with manure that either contained antibiotic residues or not. With regard to dissemination of resistance, the results presented in this study confirm that fertilization with animal manure directly adds resistance genes to the soil. In addition, it shows that this direct mechanism may be more important than possible selective pressure in soil-dwelling bacteria exerted by antibiotic residues present in the manure. These results also indicate that zoonotic bacteria detected in the manure could be detected in the soil environment directly after fertilization, but not after 1 month. In conclusion, although some antibiotic residues may be present in both manure and soil at concentrations to exert selective pressure, it seems that antibiotic resistance is mostly introduced directly to soil through fertilization with animal manure.

Biochar amendment before or after composting affects compost quality and N losses, but not P plant uptake.

We investigated the use of biochar (10% on a dry weight basis) to improve the composting process and/or the compost quality by adding it to either the feedstock mixture or the mature compost. The addition of biochar to the feedstocks was essayed in a full scale trial using a mixture of green waste and the organic fraction of municipal solid waste. Addition of biochar to mature compost was performed in a medium scale experiment. The use of biochar, even in small amounts, changed the composting process and the properties of the end products. However these effects depended on the time of application. We observed a faster decomposition in the bio-oxidative phase and lower greenhouse gas emissions when biochar was added at the beginning of the composting process, and a reduction in readily available P when biochar was applied during compost storage. Biochar as a means to increase the C content of the compost was only effective during compost storage. The P fertilizer replacement value of the compost with and without biochar was tested in a plant trial with annual ryegrass. While there was a clear effect on readily available P concentrations in the compost, adding biochar to the feedstock or the compost did not affect the P fertilizer replacement value.