Instituto de Biodiversidade Agraria e Desenvolvemento Rural (IBADER)http://hdl.handle.net/10347/29732024-03-29T01:42:03Z2024-03-29T01:42:03ZNeural networks allow the automatic verification of the type of flour, analysing the starch granule morphology, to ensure the protected geographical indication ‘Galician Bread’Fernández Vidal, Xosé RamónFernández Canto, NereaRomero Rodríguez, María ÁngelesRamos Cabrer, Ana MaríaPereira Lorenzo, SantiagoLombardero Fernández, Matildehttp://hdl.handle.net/10347/329122024-03-21T09:21:44Z2024-01-01T00:00:00ZNeural networks allow the automatic verification of the type of flour, analysing the starch granule morphology, to ensure the protected geographical indication ‘Galician Bread’
Fernández Vidal, Xosé Ramón; Fernández Canto, Nerea; Romero Rodríguez, María Ángeles; Ramos Cabrer, Ana María; Pereira Lorenzo, Santiago; Lombardero Fernández, Matilde
Quality control of flour is essential to control the quality of bread produced from it. We propose a control method based on the morphological characteristics of the granules of starch. The automation of the identification, segmentation and determination of the average size of the granules of starch of each of the cereals that make up a flour, from microscopy images, is an essential procedure for producers who want to produce bread under the protected geographical indication (PGI) ‘Galician Bread’. This identification and counting procedure, if performed manually, is a tedious activity for a trained expert, and is very time consuming. Thus, automating this task would streamline the process, in addition to saving a great deal of time. This paper addresses this problem by using deep learning approaches (Mask R–CNN) to predict the type of the granule of starch and its size for the first time. The trained models are then evaluated with the same raw microscopy images of these granules observed under polarized light, as has been previouly used for manual identification and counting. A dataset comprising 1308 2564 × 1924-pixel images is analysed. The images contain 17000 labelled granules of starch for two types of wheat: commercial wheat flour from ‘Castilla’ (type 0) and the Galician autochthonous flour ‘Caaveiro’ (type 1). The number of samples is approximately the same for each class. Instance segmentation with Mask R–CNN (Model II) achieved valid results for unseen images, with a categorical global accuracy of about 88.6% and with a discrepancy with respect to the areas of the granules as estimated by a human expert of less than 4%. The performance achieved by Mask R–CNN produces a strong correlation between the results of an expert and the results of the network, confirming the practical validity of our proposal
2024-01-01T00:00:00ZHazards of swine slurry: Heavy metals, bacteriology, and overdosing—Physicochemical models to predict the nutrient valueFernández‐Labrada, MiguelLópez‐Mosquera, María ElviraGarcía Calvo, LucioBarrio, José CarlosLópez‐Fabal, Adolfohttp://hdl.handle.net/10347/311702024-02-23T11:17:19Z2023-07-01T00:00:00ZHazards of swine slurry: Heavy metals, bacteriology, and overdosing—Physicochemical models to predict the nutrient value
Fernández‐Labrada, Miguel; López‐Mosquera, María Elvira; García Calvo, Lucio; Barrio, José Carlos; López‐Fabal, Adolfo
In this work, 124 samples of slurry from 32 commercial farms of three animal categories (lactating sows, nursery piglets, and growing pigs) were studied. The samples were collected in summer and winter over two consecutive years and analyzed for physicochemical properties, macronutrient and micronutrient, heavy metals, and major microbiological indicators. The results were found to be influenced by farm type and to deviate especially markedly in nursery piglets, probably as a consequence of differences in pig age, diet, and management. The main potential hazards of the slurries can be expected to arise from their high contents in heavy metals (Cu and Zn), especially in the nursery piglet group, and from the high proportion of samples testing positive for Salmonella spp. (66%). Linear and nonlinear predictive equations were developed for each animal category and the three as a whole. Dry matter, which was highly correlated with N, CaO, and MgO contents, proved the best predictor of fertilizer value. Using an additional predictor failed to improve the results but nonlinear and farm-specific equations did. Rapid on-site measurements can improve the accuracy of fertilizer value estimates and help optimize the use of swine slurry as a result
2023-07-01T00:00:00ZImproving growing substrates by adding the seaweed Cystoseira baccataAntelo Rodríguez, MaiteIllera Vives, MartaFernández Labrada, MiguelSeoane Labandeira, SocorroLópez Mosquera, María Elvirahttp://hdl.handle.net/10347/299792023-01-24T03:02:42Z2022-01-01T00:00:00ZImproving growing substrates by adding the seaweed Cystoseira baccata
Antelo Rodríguez, Maite; Illera Vives, Marta; Fernández Labrada, Miguel; Seoane Labandeira, Socorro; López Mosquera, María Elvira
We examined the impact of adding the seaweed Cystoseira baccata (Ochrophyta, Sargassaceae) in various forms to two different growing substrates: pine bark and gorse compost. Specifically, we examined the influence of the seaweed on the physical and chemical properties of the substrates, and on their agronomic performance on a lettuce crop. The seaweed was used in a 20% (v/v) proportion and three different forms, namely: fresh (FS), washed fresh (WFS), and washed and dried (WDS). The mixed substrates exhibited no signs of instability. FS and DWS increased the total water retention capacity of pine bark by 20% and 27%, respectively. Adding the seaweed in any of its three forms to this type of substrate, which is poor in nutrients and has a low electrical conductivity (EC), significantly increased its P, K, Mg and Na contents, as well as its EC (from 0.08 dS m–1 in the control substrate to 0.69, 0.12 and 0.27 dS m–1 in those containing FS, WFS and WDS, respectively). On the other hand, only in fresh form (FS) altered the salinity and total K content of a substrate rich in nutrients and salts such gorse compost (from 0.89 to 1.42 dS m−1 in terms of EC and 0.59% to 0.98% in K). All mixtures performed well as substrates for a lettuce crop. Those containing DWS increased aerial mass in gorse compost, while any of the tested formats increased aerial mass in pine bark
2022-01-01T00:00:00ZHolocene environmental change on the Atlantic coast of NW Iberia as inferred from the Ponzos wetland sequenceGómez-Orellana Rodríguez, LuisRamil Rego, PabloFerreiro da Costa, JavierMuñoz Sobrino, Castorhttp://hdl.handle.net/10347/266282021-07-29T02:02:26Z2021-01-01T00:00:00ZHolocene environmental change on the Atlantic coast of NW Iberia as inferred from the Ponzos wetland sequence
Gómez-Orellana Rodríguez, Luis; Ramil Rego, Pablo; Ferreiro da Costa, Javier; Muñoz Sobrino, Castor
The intertidal environment of the Ponzos beach (NW Iberian Peninsula) hosts a sedimentary sequence (including large wood fragments) deposited during the first half of the Holocene in a hygrophilous continental wetland. Pollen and macrofossil data alongside radiocarbon dating allow reconstruction of the changes that occurred during the Early and Middle Holocene in the landscape of the NW Iberia coastal lowlands, as well as the local wetland plant communities, in response to the climate variations and the eustatic sea-level oscillations. The sequence represents the evolution of a coastal wetland from its initial phases as a hygrophilous wetland towards the subsequent installation of a freshwater lagoon. Pollen data show the dominant role of Atlantic (mainly deciduous) woody taxa, the scarcity of conifers and the lack of Mediterranean elements in the coastal landscapes around the Ponzos site. The presence and abundance of some taxa such as deciduous Quercus, Castanea, Fagus, Tilia and Ulmus during the Early Holocene provides further support for the occurrence of glacial refuges in the Cantabrian-Atlantic area during the Last Glaciation. The diverse vegetation that characterizes the modern landscapes in this territory established later, spreading from these glacial reservoirs of biodiversity. In this sense, the notable and early presence of Fagus at the beginning of the Holocene, a tree also previously recorded during several phases of the Last Glacial Cycle on the NW Iberia coasts, is noteworthy. In addition, during the Early and Middle Holocene are recorded other trees that are currently extirpated as natural taxa in the area, such as Pinus, Tilia and Carpinus
2021-01-01T00:00:00Z