Articles de revista
http://hdl.handle.net/2117/1745
2024-03-29T01:22:11ZCombining computer vision and deep learning to classify varieties of Prunus dulcis for the nursery plant industry
http://hdl.handle.net/2117/383846
Combining computer vision and deep learning to classify varieties of Prunus dulcis for the nursery plant industry
Borraz Martínez, Sergio; Simó Cruanyes, Joan; Gras Moreu, Anna Maria; Boqué, Ricard; Tarrés Ruiz, Francisco
Varietal control to avoid unwanted varietal mixtures is an important objective for the nursery plant industry. In this study, we have developed and analyzed the capabilities of a computer vision system based on deep learning for the control of plant varieties in the nursery plant industry and for evaluating its capabilities. For this purpose, three datasets of nursery plant images were compared. The datasets came from two varieties of almond trees (Prunus dulcis) named Soleta and Pentacebas. Each dataset contained images with three different scales: whole plant, leaf, and venation. The Gradient-weighted Class Activation Mapping (Grad-CAM) technique was used to unveil the most important features to discriminate between both varieties. The three datasets provided classification accuracies above 97% in the test set, being the leaf dataset, with a 98.8% accuracy, the one providing the best results. Concerning the most important features of the plants, the Grad-CAM showed that they are located in the center of the leaf, that is, the venation. In conclusion, we have shown that computer vision is a promising technique for the control of plant varietal mixtures.
2023-02-22T10:11:06ZBorraz Martínez, SergioSimó Cruanyes, JoanGras Moreu, Anna MariaBoqué, RicardTarrés Ruiz, FranciscoVarietal control to avoid unwanted varietal mixtures is an important objective for the nursery plant industry. In this study, we have developed and analyzed the capabilities of a computer vision system based on deep learning for the control of plant varieties in the nursery plant industry and for evaluating its capabilities. For this purpose, three datasets of nursery plant images were compared. The datasets came from two varieties of almond trees (Prunus dulcis) named Soleta and Pentacebas. Each dataset contained images with three different scales: whole plant, leaf, and venation. The Gradient-weighted Class Activation Mapping (Grad-CAM) technique was used to unveil the most important features to discriminate between both varieties. The three datasets provided classification accuracies above 97% in the test set, being the leaf dataset, with a 98.8% accuracy, the one providing the best results. Concerning the most important features of the plants, the Grad-CAM showed that they are located in the center of the leaf, that is, the venation. In conclusion, we have shown that computer vision is a promising technique for the control of plant varietal mixtures.La conservación de la biodiversidad cultivada
http://hdl.handle.net/2117/367802
La conservación de la biodiversidad cultivada
Casañas Artigas, Francesc; Simó Cruanyes, Joan; Casals Missio, Joan
Los programas de revalorización de una variedad tradicional tienen por objeto la recuperación y mejora de plantas cultivadas loca-
les que han perdido, a través de la erosión genética, propiedades sensoriales y nutritivas de interés. Además de tener en cuenta su
viabilidad comercial, se busca la conservación de la variedad no solo en los bancos de semillas (ex situ), sino también su cultivo per-
manente por los agricultores (in situ). Abajo se resumen los principales pasos que pueden seguirse para conseguirlo
2022-05-27T12:12:45ZCasañas Artigas, FrancescSimó Cruanyes, JoanCasals Missio, JoanLos programas de revalorización de una variedad tradicional tienen por objeto la recuperación y mejora de plantas cultivadas loca-
les que han perdido, a través de la erosión genética, propiedades sensoriales y nutritivas de interés. Además de tener en cuenta su
viabilidad comercial, se busca la conservación de la variedad no solo en los bancos de semillas (ex situ), sino también su cultivo per-
manente por los agricultores (in situ). Abajo se resumen los principales pasos que pueden seguirse para conseguirloImpacts of use and abuse of nature in Catalonia with proposals for sustainable management
http://hdl.handle.net/2117/353319
Impacts of use and abuse of nature in Catalonia with proposals for sustainable management
Peñuelas Reixach, Josep; Arús, Pere; Carceller, Xavier; Casademunt, And J; Casals Missio, Joan; Casals Torrens, Pau; Casañas Artigas, Francesc; Catalan Aguila, Jordi; Martinez Cordero, Pedro Antonio; Estrada Miyares, Marta; Folch I Guillen, Ramón; Geli de Ciurana, Anna Maria; Lleonart Aliberas, Jordi; Lloret Romañach, Josep; Mallarach, Josep Mº; Martín Vide, Juan Pedro; Munné Torras, Antoni; Nel·lo Colom, Oriol; Palazon, S Torres; Pino, José; Prat Fornells, Narcís; Roca Pascual, Núria; Romanyà, J; Simó Cruanyes, Joan; Vallejo Calzada, Ramon V.; Vilaplana Fernández, Joan Manuel
This paper provides an overview of the last 40 years of use, and in many cases abuse, of the natural resources in Catalonia, a country that is representative of European countries in general, and especially those in the Mediterranean region. It analyses the use of natural resources made by mining, agriculture, livestock, logging, fishing, nature tourism, and energy production and consumption. This use results in an ecological footprint, i.e., the productive land and sea surface required to generate the consumed resources and absorb the resulting waste, which is about seven times the amount available, a very high number but very similar to other European countries. This overexploitation of natural resources has a huge impact on land and its different forms of cover, air, and water. For the last 25 years, forests and urban areas have each gained almost 3% more of the territory at the expense of agricultural land; those municipalities bordering the sea have increased their number of inhabitants and activity, and although they only occupy 6.7% of the total surface area, they account for 43.3% of the population; air quality has stabilized since the turn of the century, and there has been some improvement in the state of aquatic ecosystems, but still only 36% are in good condition, while the remainder have suffered morphological changes and different forms of nonpoint source pollution; meanwhile the biodiversity of flora and fauna remains still under threat. Environmental policies do not go far enough so there is a need for revision of the legislation related to environmental impact and the protection of natural areas, flora, and fauna. The promotion of environmental research must be accompanied by environmental education to foster a society which is more knowledgeable, has more control and influence over the decisions that deeply affect it. Indeed, nature conservation goes hand in hand with other social and economic challenges that require a more sustainable vision. Today’s problems with nature derive from the current economic model, which is environmentally unsustainable in that it does not take into account environmental impacts. Lastly, we propose a series of reasonable and feasible priority measures and actions related to each use made of the country’s natural resources, to the impacts they have had, and to their management, in the hope that these can contribute to improving the conservation and management of the environment and biodiversity and move towards sustainability.</jats:p>
2021-10-07T12:45:29ZPeñuelas Reixach, JosepArús, PereCarceller, XavierCasademunt, And JCasals Missio, JoanCasals Torrens, PauCasañas Artigas, FrancescCatalan Aguila, JordiMartinez Cordero, Pedro AntonioEstrada Miyares, MartaFolch I Guillen, RamónGeli de Ciurana, Anna MariaLleonart Aliberas, JordiLloret Romañach, JosepMallarach, Josep MºMartín Vide, Juan PedroMunné Torras, AntoniNel·lo Colom, OriolPalazon, S TorresPino, JoséPrat Fornells, NarcísRoca Pascual, NúriaRomanyà, JSimó Cruanyes, JoanVallejo Calzada, Ramon V.Vilaplana Fernández, Joan ManuelThis paper provides an overview of the last 40 years of use, and in many cases abuse, of the natural resources in Catalonia, a country that is representative of European countries in general, and especially those in the Mediterranean region. It analyses the use of natural resources made by mining, agriculture, livestock, logging, fishing, nature tourism, and energy production and consumption. This use results in an ecological footprint, i.e., the productive land and sea surface required to generate the consumed resources and absorb the resulting waste, which is about seven times the amount available, a very high number but very similar to other European countries. This overexploitation of natural resources has a huge impact on land and its different forms of cover, air, and water. For the last 25 years, forests and urban areas have each gained almost 3% more of the territory at the expense of agricultural land; those municipalities bordering the sea have increased their number of inhabitants and activity, and although they only occupy 6.7% of the total surface area, they account for 43.3% of the population; air quality has stabilized since the turn of the century, and there has been some improvement in the state of aquatic ecosystems, but still only 36% are in good condition, while the remainder have suffered morphological changes and different forms of nonpoint source pollution; meanwhile the biodiversity of flora and fauna remains still under threat. Environmental policies do not go far enough so there is a need for revision of the legislation related to environmental impact and the protection of natural areas, flora, and fauna. The promotion of environmental research must be accompanied by environmental education to foster a society which is more knowledgeable, has more control and influence over the decisions that deeply affect it. Indeed, nature conservation goes hand in hand with other social and economic challenges that require a more sustainable vision. Today’s problems with nature derive from the current economic model, which is environmentally unsustainable in that it does not take into account environmental impacts. Lastly, we propose a series of reasonable and feasible priority measures and actions related to each use made of the country’s natural resources, to the impacts they have had, and to their management, in the hope that these can contribute to improving the conservation and management of the environment and biodiversity and move towards sustainability.</jats:p>Varietal quality control in the nursery plant industry using computer vision and deep learning techniques
http://hdl.handle.net/2117/344965
Varietal quality control in the nursery plant industry using computer vision and deep learning techniques
Borraz Martínez, Sergio; Tarrés Ruiz, Francisco; Boqué, Ricard; Mestre, Mariàngela; Simó Cruanyes, Joan; Gras Moreu, Anna Maria
Computer vision coupled to deep learning is a promising technique withmultiple applications in the industry. In this work, the potential of thistechnique has been assessed in the classification of two varieties of almondtrees (Prunus dulcis), Soleta and Pentacebas. For that, a convolutional neuralnetwork named VGG16 was used. The most appropriate configuration formodel training was studied, which included the comparison between twodifferent filling modes (reflect and nearest) in the data augmentation step, theevaluation of the batch size and the analysis of the image sizes. The robustnessof the model was also checked, and information was obtained about how themodel extracts the information from the images
2021-05-03T11:29:57ZBorraz Martínez, SergioTarrés Ruiz, FranciscoBoqué, RicardMestre, MariàngelaSimó Cruanyes, JoanGras Moreu, Anna MariaComputer vision coupled to deep learning is a promising technique withmultiple applications in the industry. In this work, the potential of thistechnique has been assessed in the classification of two varieties of almondtrees (Prunus dulcis), Soleta and Pentacebas. For that, a convolutional neuralnetwork named VGG16 was used. The most appropriate configuration formodel training was studied, which included the comparison between twodifferent filling modes (reflect and nearest) in the data augmentation step, theevaluation of the batch size and the analysis of the image sizes. The robustnessof the model was also checked, and information was obtained about how themodel extracts the information from the imagesEstimating sensory properties with near-infrared spectroscopy: A tool for quality control and breeding of ‘Calçots’ (Allium cepa L.)
http://hdl.handle.net/2117/338162
Estimating sensory properties with near-infrared spectroscopy: A tool for quality control and breeding of ‘Calçots’ (Allium cepa L.)
Sans Molins, Sílvia; Ferré, Joan; Boqué, Ricard; Sabaté Reboll, José; Casals Missio, Joan; Simó Cruanyes, Joan
Using trained panelists to evaluate sensory attributes is unfeasible when many samples must be evaluated, such as in quality control or breeding programs. Near-infrared spectroscopy (NIRS) is a rapid inexpensive method often used in food quality evaluation. We assessed the
feasibility of using NIRS to estimate sweetness, fiber perception, and off-flavors, the most important sensory attributes in cooked ‘calçots’ (the immature floral stems of second-year onion resprouts). The best results were achieved through models using interval partial least squares (iPLS) variable selection on spectra from pureed cooked ‘calçots’, which yielded values of the ratio of performance to deviation (RPD) greater than 1.4 in all cases. Therefore, it would be feasible to use NIRS to estimate sensory properties in ‘calçots’. This approach would be useful in initial screening to discard samples that differ substantially from the ideotype; thus, sensory analysis by trained panels could be reserved for finer discriminations.
2021-02-09T13:58:00ZSans Molins, SílviaFerré, JoanBoqué, RicardSabaté Reboll, JoséCasals Missio, JoanSimó Cruanyes, JoanUsing trained panelists to evaluate sensory attributes is unfeasible when many samples must be evaluated, such as in quality control or breeding programs. Near-infrared spectroscopy (NIRS) is a rapid inexpensive method often used in food quality evaluation. We assessed the
feasibility of using NIRS to estimate sweetness, fiber perception, and off-flavors, the most important sensory attributes in cooked ‘calçots’ (the immature floral stems of second-year onion resprouts). The best results were achieved through models using interval partial least squares (iPLS) variable selection on spectra from pureed cooked ‘calçots’, which yielded values of the ratio of performance to deviation (RPD) greater than 1.4 in all cases. Therefore, it would be feasible to use NIRS to estimate sensory properties in ‘calçots’. This approach would be useful in initial screening to discard samples that differ substantially from the ideotype; thus, sensory analysis by trained panels could be reserved for finer discriminations.Horticultura i ciutat
http://hdl.handle.net/2117/328702
Horticultura i ciutat
Gras Moreu, Anna Maria; Maldonado Rius, Luis; Casals Missio, Joan; Simó Cruanyes, Joan
El 1912 es crea l’Escola Superior d’Agricultura de Barcelona (ESAB),amb la pretensió d’aportar coneixement
al món agrícola i fer avançar l’agricultura i la ramaderia del camp català, d’acord amb les necessitats de
la societat de començament de segle.
2020-09-14T07:45:27ZGras Moreu, Anna MariaMaldonado Rius, LuisCasals Missio, JoanSimó Cruanyes, JoanEl 1912 es crea l’Escola Superior d’Agricultura de Barcelona (ESAB),amb la pretensió d’aportar coneixement
al món agrícola i fer avançar l’agricultura i la ramaderia del camp català, d’acord amb les necessitats de
la societat de començament de segle.Nutritional values of raw and cooked 'calçots' (Allium cepa L. resprouts), an expanding crop
http://hdl.handle.net/2117/186146
Nutritional values of raw and cooked 'calçots' (Allium cepa L. resprouts), an expanding crop
Sans Molins, Sílvia; Bobo García, Gloria; Zudaire, Lorena; Aragües Lafarga, Ramón; Sabaté Reboll, José; Casals Missio, Joan; Simó Cruanyes, Joan
‘Calçot’ is the Catalan name for the immature floral stems of second-year onion resprouts of the Blanca Tardana de Lleida (BTL) landrace. Highly appreciated for their sensory attributes, these resprouts are typically consumed after roasting on an open fire. Now new preparations are appearing, helping to expand the market for ‘calçots’. This study aimed (i) to compare the nutritional and sensory characteristics of BTL ‘calçots’ versus other onion varieties; (ii) to analyze the effects of cooking and / or in vitro gastrointestinal digestion on the nutritional properties of ‘calçots’; and (iii) to determine the influence of the environment on the antioxidant properties of ‘calçots’.
2020-05-04T10:43:32ZSans Molins, SílviaBobo García, GloriaZudaire, LorenaAragües Lafarga, RamónSabaté Reboll, JoséCasals Missio, JoanSimó Cruanyes, Joan‘Calçot’ is the Catalan name for the immature floral stems of second-year onion resprouts of the Blanca Tardana de Lleida (BTL) landrace. Highly appreciated for their sensory attributes, these resprouts are typically consumed after roasting on an open fire. Now new preparations are appearing, helping to expand the market for ‘calçots’. This study aimed (i) to compare the nutritional and sensory characteristics of BTL ‘calçots’ versus other onion varieties; (ii) to analyze the effects of cooking and / or in vitro gastrointestinal digestion on the nutritional properties of ‘calçots’; and (iii) to determine the influence of the environment on the antioxidant properties of ‘calçots’.Multivariate classification of prunus dulcis varieties using leaves of nursery plants and near infrared spectroscopy
http://hdl.handle.net/2117/180937
Multivariate classification of prunus dulcis varieties using leaves of nursery plants and near infrared spectroscopy
Borraz Martínez, Sergio; Simó Cruanyes, Joan; Gras Moreu, Anna Maria; Mestre, Mariàngela; Boqué, Ricard
The emergence of new almond tree (Prunus dulcis) varieties with agricultural interest is forcing the nursery plant industry to establish quality systems to keep varietal purity in the production stage. The aim of this study is to assess the capability of near-infrared spectroscopy (NIRS) to classify different Prunus dulcis varieties as an alternative to more expensive methods. Fresh and dried-powdered leaves of six different varieties of almond trees of commercial interest (Avijor, Guara, Isabelona, Marta, Pentacebas and Soleta) were used.
2020-03-23T13:23:18ZBorraz Martínez, SergioSimó Cruanyes, JoanGras Moreu, Anna MariaMestre, MariàngelaBoqué, RicardThe emergence of new almond tree (Prunus dulcis) varieties with agricultural interest is forcing the nursery plant industry to establish quality systems to keep varietal purity in the production stage. The aim of this study is to assess the capability of near-infrared spectroscopy (NIRS) to classify different Prunus dulcis varieties as an alternative to more expensive methods. Fresh and dried-powdered leaves of six different varieties of almond trees of commercial interest (Avijor, Guara, Isabelona, Marta, Pentacebas and Soleta) were used.Development of a methodology to analyze leaves from Prunus dulcis varieties using near infrared spectroscopy
http://hdl.handle.net/2117/180898
Development of a methodology to analyze leaves from Prunus dulcis varieties using near infrared spectroscopy
Borraz Martínez, Sergio; Boqué, Ricard; Simó Cruanyes, Joan; Mestre, Mariàngela; Gras Moreu, Anna Maria
Near-infrared spectroscopy (NIRS) can be a faster and more economical alternative to traditional methods for
screening varietal mixtures of nursery plants during the propagation process to ensure varietal purity and to
avoid errors in the dispatch batches. The global objective of this work was to develop and optimize a NIR spectral
collection method for construction of robust multivariate discrimination models. Three different varieties of
Prunus dulcis (Avijor, Guara, and Pentacebas) of agricultural interest were used for this study. Sources of variation
were investigated, including the position of the leaves on the trees, differences among trees of the same variety,
and differences at the varietal level. Three types of processed samples were investigated. Fresh leaves, dried
leaves, and dried leaves in powder form were included in each analysis. A study of spectral pre-treatment
methods was also performed, and multivariate methods were applied to analyze the influence of different factors
on classification. These included principal component analysis (PCA), partial least squares discriminant analysis
(PLS-DA), and ANOVA simultaneous component analysis (ASCA). The results indicated that variety was the most
important factor for classification. The spectral pre-treatment that provided the best results was a combination of
standard normal variate (SNV), Savitzky-Golay first derivative, and mean-centering methods. With regard to the
type of processed sample, the highest percentages of correct classifications were obtained with fresh and dried
powdered leaves at both the training set and test set validation levels. This study represents the first step towards
the consolidation of NIRS as a method to identify Prunus dulcis varieties.
2020-03-23T12:09:50ZBorraz Martínez, SergioBoqué, RicardSimó Cruanyes, JoanMestre, MariàngelaGras Moreu, Anna MariaNear-infrared spectroscopy (NIRS) can be a faster and more economical alternative to traditional methods for
screening varietal mixtures of nursery plants during the propagation process to ensure varietal purity and to
avoid errors in the dispatch batches. The global objective of this work was to develop and optimize a NIR spectral
collection method for construction of robust multivariate discrimination models. Three different varieties of
Prunus dulcis (Avijor, Guara, and Pentacebas) of agricultural interest were used for this study. Sources of variation
were investigated, including the position of the leaves on the trees, differences among trees of the same variety,
and differences at the varietal level. Three types of processed samples were investigated. Fresh leaves, dried
leaves, and dried leaves in powder form were included in each analysis. A study of spectral pre-treatment
methods was also performed, and multivariate methods were applied to analyze the influence of different factors
on classification. These included principal component analysis (PCA), partial least squares discriminant analysis
(PLS-DA), and ANOVA simultaneous component analysis (ASCA). The results indicated that variety was the most
important factor for classification. The spectral pre-treatment that provided the best results was a combination of
standard normal variate (SNV), Savitzky-Golay first derivative, and mean-centering methods. With regard to the
type of processed sample, the highest percentages of correct classifications were obtained with fresh and dried
powdered leaves at both the training set and test set validation levels. This study represents the first step towards
the consolidation of NIRS as a method to identify Prunus dulcis varieties.Plant genebanks: present situation and proposals for their improvement. The case of the spanish network
http://hdl.handle.net/2117/180833
Plant genebanks: present situation and proposals for their improvement. The case of the spanish network
Díez Niclós, María José; de la Rosa Fernández, Lucía; Martín, Isaura; Guasch, Luís; Cartea, María Elena; Mallor, Cristina; Casals Missio, Joan; Simó Cruanyes, Joan; Rivera Pinzano, Ana; Anastasio, Germán; Prohens, Jaume; Soler, Salvador; Blanca, Jose; Valcárcel, José Vicente; Casañas, Francesc
Genebanks were created by the middle of the twentieth century to preserve cultivatedbiodiversity when landraces began to be substituted by modern varieties. This move wasgenerally accepted as a necessary step to safeguard the future. After about 75 yearsof collecting and maintaining genetic resources, the increasing ability of biotechnologyto create new variability brings the roles of genebanks in the present and near futureinto question.
2020-03-23T09:06:40ZDíez Niclós, María Joséde la Rosa Fernández, LucíaMartín, IsauraGuasch, LuísCartea, María ElenaMallor, CristinaCasals Missio, JoanSimó Cruanyes, JoanRivera Pinzano, AnaAnastasio, GermánProhens, JaumeSoler, SalvadorBlanca, JoseValcárcel, José VicenteCasañas, FrancescGenebanks were created by the middle of the twentieth century to preserve cultivatedbiodiversity when landraces began to be substituted by modern varieties. This move wasgenerally accepted as a necessary step to safeguard the future. After about 75 yearsof collecting and maintaining genetic resources, the increasing ability of biotechnologyto create new variability brings the roles of genebanks in the present and near futureinto question.