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.

Computer vision coupled to deep learning is a promising technique with multiple applications in the industry. In this work, the potential of this technique has been assessed in the classification of two varieties of almond trees ( Prunus dulcis ), Soleta and Pentacebas . For that, a convolutional neural network named VGG16 was used. The most appropriate configuration for model training was studied, which included the comparison between two different filling modes ( reflect and nearest ) in the data augmentation step, the evaluation of the batch size and the analysis of the image sizes. The robustness of the model was also checked, and information was obtained about how the model extracts the information from the images. The results showed that the reflect fill mode was more effective than the nearest one. The best results were obtained using batches with 30 and 40 images, with an image size of (224 × 224) pixels. The verification of the robustness proved the capability of the technique as a promising tool for plant varietal identification.

HydroSoil is a measurement campaign, funded by the European Space Agency (ESA), where the temporal evolutions of two crops, barley and corn, have been continuously monitored during the whole crop period by means of a C-band Fully Polarimetric C-band Ground-Based Synthetic Aperture Radar (GB-SAR). SAR data has been collected together with ancillary data, and both are being processed to demonstrate the retrieval of soil moisture and vegetation parameters in an agricultural field under controlled conditions, to simulate the frequent acquisitions of GeoSAR missions.

Denitrification is one of the key processes of the global nitrogen (N) cycle driven by bacteria. It has been widely known for more than 100 years as a process by which the biogeochemical N-cycle is balanced. To study this process, we develop an individual-based model called INDISIM-Denitrification. The model embeds a thermodynamic model for bacterial yield prediction inside the individual-based model INDISIM and is designed to simulate in aerobic and anaerobic conditions the cell growth kinetics of denitrifying bacteria. INDISIM-Denitrification simulates a bioreactor that contains a culture medium with succinate as a carbon source, ammonium as nitrogen source and various electron acceptors. To implement INDISIM-Denitrification, the individual-based model INDISIM was used to give sub-models for nutrient uptake, stirring and reproduction cycle. Using a thermodynamic approach, the denitrification pathway, cellular maintenance and individual mass degradation were modeled using microbial metabolic reactions. These equations are the basis of the sub-models for metabolic maintenance, individual mass synthesis and reducing internal cytotoxic products. The model was implemented in the open-access platform NetLogo. INDISIM-Denitrification is validated using a set of experimental data of two denitrifying bacteria in two different experimental conditions. This provides an interactive tool to study the denitrification process carried out by any denitrifying bacterium since INDISIM-Denitrification allows changes in the microbial empirical formula and in the energy-transfer-efficiency used to represent the metabolic pathways involved in the denitrification process. The simulator can be obtained from the authors on request.

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. The most important variables to discriminate between these varieties were studied through of three scientifically accepted indicators (Variable importance in projection¸ selectivity ratio and vector of the regression coefficients). The results showed that the 7000 to 4000 cm−1 range contains the most useful variables, which allowed to decrease the complexity of the data set. Concerning to the classification models, a high percentage of correct classifications (90–100%) was obtained, where dried-powdered leaves showed better results than fresh leaves. However, the classification rate of both kinds of leaves evidences the capacity of the near-infrared spectroscopy to discriminate Prunus dulcis varieties. We demonstrate with these results the capability of the NIRS technology as a quality control tool in nursery plant industry.

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.

Site-specific management of crops represents an important improvement in terms of efficiency and efficacy of the different labours, and its implementation has experienced a large development in the last decades, especially for field crops. The particular case of the spray application process for what are called “specialty crops” (vineyard, orchard fruits, citrus, olive trees, etc.) represents one of the most controversial and influential actions directly related with economical, technical, and environmental aspects. This study was conducted with the main objective to find possible correlations between data obtained from remote sensing technology and the actual canopy characteristics. The potential correlation will be the starting point to develop a variable rate application technology based on prescription maps previously developed. An unmanned aerial vehicle (UAV) equipped with a multispectral camera was used to obtain data to build a canopy vigour map of an entire parcel. By applying the specific software DOSAVIÑA ® , the canopy map was then transformed into a practical prescription map, which was uploaded into the dedicated software embedded in the sprayer. Adding to this information precise georeferenced placement of the sprayer, the system was able to modify the working parameters (pressure) in real time in order to follow the prescription map. The results indicate that site-specific management for spray application in vineyards result in a 45% reduction of application rate when compared with conventional spray application. This fact leads to a equivalent reduction of the amount of pesticide when concentration is maintained constant, showing once more that new technologies can help to achieve the goal of the European legislative network of safe use of pesticides.

DOSAVINA is a new tool (website and app for smartphones) developed for calculating the optimal volume rates and pesticide doses to apply during spray application processes in vineyards. DOSAVINA also calculates and recommends the optimal working parameters for working pressure, forward speed, and number and types of nozzles. DOSAVINA was developed by the Unit of Agricultural Machinery at the Universitat Politecnica de Catalunya, and is available for iOS and Android devices. It is also available on the DOSAVINA website (https://dosavina.upc.edu). The developed tool can be used also for the calibration of spray applications on fruit trees (as well as on citrus orchards, olive trees, almond trees, and many other vertical crops) once the volume rate has been established. The system, which is based on a modified version of the leaf wall area (LWA) method, calculates the optimal volume rate for vineyards by considering the effects of leaf density, canopy width, and sprayer type. System testing took biological efficacy into consideration and measured the main factors used for characterizing spray processes, coverage, and distribution over the entire canopy. Results showed that water and pesticide use could be reduced by more than 20% while still meeting economic, environmental, and food quality requirements. The design of the tool is aligned with European requirements concerning pesticide use, as established in the European Directive for a Sustainable Use of Pesticides.

We have developed an individual-based model for denitrifying bacteria. The model, called INDISIM-Paracoccus, embeds a thermodynamic model for bacterial yield prediction inside the individual-based model INDISIM, and is designed to simulate the bacterial cell population behavior and the product dynamics within the culture. The INDISIM-Paracoccus model assumes a culture medium containing succinate as a carbon source, ammonium as a nitrogen source and various electron acceptors such as oxygen, nitrate, nitrite, nitric oxide and nitrous oxide to simulate in continuous or batch culture the different nutrient-dependent cell growth kinetics of the bacterium Paracoccus denitrificans. The individuals in the model represent microbes and the individual-based model INDISIM gives the behavior-rules that they use for their nutrient uptake and reproduction cycle. Three previously described metabolic pathways for P. denitrificans were selected and translated into balanced chemical equations using a thermodynamic model. These stoichiometric reactions are an intracellular model for the individual behavior-rules for metabolic maintenance and biomass synthesis and result in the release of different nitrogen oxides to the medium. The model was implemented using the NetLogo platform and it provides an interactive tool to investigate the different steps of denitrification carried out by a denitrifying bacterium. The simulator can be obtained from the authors on request.

Modelling cellular metabolism is a strategic factor in investigating microbial behaviour and interactions, especially for bio-technological processes. A key factor for modelling microbial activity is the calculation of nutrient amounts and products generated as a result of the microbial metabolism. Representing metabolic pathways through balanced reactions is a complex and time-consuming task for biologists, ecologists, modellers and engineers. A new computational tool to represent microbial pathways through microbial metabolic reactions (MMRs) using the approach of the Thermodynamic Electron Equivalents Model has been designed and implemented in the open-access framework NetLogo. This computational tool, called MbT-Tool (Metabolism based on Thermodynamics) can write MMRs for different microbial functional groups, such as aerobic heterotrophs, nitrifiers, denitrifiers, methanogens, sulphate reducers, sulphide oxidizers and fermenters. The MbT-Tool's code contains eighteen organic and twenty inorganic reduction-half-reactions, four N-sources (NH4+, NO3−, NO2−, N2) to biomass synthesis and twenty-four microbial empirical formulas, one of which can be determined by the user (CnHaObNc). MbT-Tool is an open-source program capable of writing MMRs based on thermodynamic concepts, which are applicable in a wide range of academic research interested in designing, optimizing and modelling microbial activity without any extensive chemical, microbiological and programing experience.

Soil organic matter dynamics are essential for terrestrial ecosystem functions as they affect biogeochemical cycles and, thus, the provision of plant nutrients or the release of greenhouse gases to the atmosphere. Most of the involved processes are driven by microorganisms. To investigate and understand these processes, individual-based models allow analyzing complex microbial systems' behavior based on rules and conditions for individual entities within these systems, taking into account local interactions and individual variations. Here, we present a streamlined, user-friendly and open version of the individual-based model INDISIM-SOM, which describes the mineralization of soil carbon and nitrogen. It was implemented in NetLogo, a widely used and easily accessible software platform especially designed for individual-based simulation models. Including powerful means to observe the model behavior and a standardized documentation, this increases INDISIM-SOM's range of potential uses and users, and facilitates the exchange among soil scientists as well as between different modeling approaches.

The individual's adaptive behavior to environmental conditions through different behavior- rules is one of the strongest aspects of an individual-based model (IBM). Microbial IBMs consider individuals as discrete entities that follow behavior-rules that dictate how microorganisms interact with their surrounding environment and other microbes, so that the microorganisms and the environment can change their characteristics. This makes it possible to explore connections between micro-level microorganism behaviors and macro-level patterns that emerge from their interactions. INDISIM- Paracoccus is a bacterial IBM used to model the growth and development of the bacteria Paracoccus denitrificans in batch and continuous cultures under aerobic and anaerobic conditions. It embeds thermodynamic properties in individual cells, which can simulate the behavior of the cell population more realistically and mechanistically than other approaches. The IBM's development and application with some intracellular detail and complexity constitute a key advantage in the investigation and understanding of the different steps of denitrification carried out by a denitrifying bacterium.

This contribution develops and implements INDISIM-Saccha, a spatially explicit IBM model to analyze the dynamics of Saccharomyces cerevisiae anaerobic cultures evolving in a liquid medium with glucose as a main carbon source and organic and inorganic nitrogen sources. The model has been parameterized, calibrated and its adequacy assessed using available experimental data. The growth of the yeast population and the glucose depletion were simulated, and changes in the ethanol production kinetics resulting from differences in the size distribution of the cells making up the inocula were examined in silico. Uncertainty on the initial estimated values of the model parameters was reduced by means of an iterative process involving a computational full factorial experiment, and the parameter values reproducing simultaneously glucose depletion and growth curves of batch cultures in two initial glucose concentrations were selected. The model adequacy was assessed with multiple both individual and population patterns not previously used in the calibration process carried out. Three virtual experiments were conducted from inocula with different cell size distributions. The maximum yeast cell number, the specific growth rate and the time to achieve the maximum ethanol produced were studied. Although the ethanol obtained was similar in the three studied situations, the time required to achieve it was significantly different, fermentations started by inocula made up of greater cells showed increased productivity. Due to the importance of S. cerevisiae in both fundamental research and industrial production contexts, having a calibrated computational model capable of studying the structures of this yeast population and the profiles of the fermentations carried out by it represents a noteworthy advancement in the field of microbial ecology. (C) 2014 Elsevier B.V. All rights reserved.

This work addresses and aims to fulfil a very clear need in teaching biosystem engineering. When introducing students to the complexity of soil processes, one of the frustrations that teachers often experience is the impossibility to demonstrate practically, in the lab, some of the concepts and processes discussed in class. Either the experiments take far longer than a typical laboratory session or they require access to specific equipment. To deal with this situation, it would be ideal for students to be able to do virtual experiments. The purpose of this work is to display the individual-based simulation model INDISIM-SOM, available free from a website, and to show how it can be used in experiments or as a teaching-learning instrument in the classroom. The computational model has been designed specifically for the study of soil organic matter and is based mainly on the activity conducted by two different prototypes of microorganisms. One option of using INDISIM-SOM is as a way to introduce the individual-based model as a methodology to improve understanding of the agents involved in soil microbial system and their processes. Another option is to develop the ability to work with simulators by connecting concepts and helping students in the development of modelling competence. Virtual experiments were carried out as an example of what may be expected from using the INDISIM-SOM web simulator. Temporal evolutions of five virtual soils with different organic C content and proportional content in organic N, easily hidrolyzable N, nitrate and ammonia were generated and discussed.

The individual-based model INDISIM-SOM, made up by biotic and abiotic elements, encompasses a wide range of physical, chemical, and microbiological processes that control the short-term dynamics of soil C and N, namely, decomposition, mineralization or immobilization of C and N, and humification. In order to model the addition of slurry and mineral N into soils, a new version of INDISIM-SOM, called INDISIM-SOMFERTL, whcih allows study of the variables linked to turnover of soil C and N, has been developed. The parameterization and initialization of the new simulator has been modified with respect to INDISIM-SOM, together with some of the sub-models involved, mainly those linked to ammonia adsorption and desorption and the use of labile N or labile C as energetic sources for microbial maintenance. New values for some parameters were obtained in order to fit the simulations to a set of experimental data.

The fate of soil carbon and nitrogen compounds in soils in response to climate change is currently the object of significant research. In particular, there is much interest in the development of a new generation of micro-scale models of soil ecosystems processes. Crucial to the elaboration of such models is the ability to describe the growth and metabolism of small numbers of individual microorganisms, distributed in a highly heterogeneous environment. In this context, the key objective of the research described in this article was to further develop an individual-based soil organic matter model, INDISIM-SOM, first proposed a few years ago, and to assess its performance with a broader experimental data set than previously considered. INDISIM-SOM models the dynamics and evolution of carbon and nitrogen associated with organic matter in soils. The model involves a number of state variables and parameters related to soil organic matter and microbial activity, including growth and decay of microbial biomass, temporal evolutions of easily hydrolysable N, mineral N in ammonium and nitrate. CO2 and O-2. The present article concentrates on the biotic components of the model. Simulation results demonstrate that the model can be calibrated to provide good fit to experimental data from laboratory incubation experiments performed on three different types of Mediterranean soils. In addition, analysis of the sensitivity toward its biotic parameters shows that the model is far more sensitive to some parameters, i.e., the microbial maintenance energy and the probability of random microbial death, than to others. These results suggest that, in the future, research should focus on securing better measurements of these parameters, on environmental determinants of the switch from active to dormant states, and on the causes of random cell death in soil ecosystems. (C) 2011 Elsevier B.V. All rights reserved.

INDISIM-SOM models the dynamics and evolution of C and N related to organic matter in soils by using individual-based simulations. It is an Individual-based Model that controls a group of microbial cells at each time step, using a set of time-dependent variables for each microorganism. The space is divided into square cells. In each spatial cell, the amounts of different types of organic compounds are controlled. These are identified as polymerized organic C and N, labile organic C and N, and mineral compounds such us N-NH4, N-NO3, CO2, and O-2. The model takes into account the activity of two types of microorganisms: decomposers (heterotrophic) and nitrifiers. Metabolic pathways and sources of C and N that they can use are identified. Some state variables and parameters related to soil organic matter and microbial activity are studied. This study presents a website at which the simulator INDISIM-SOM is accessible, and explains how to carry out some virtual experiments, in order to further advance the skills associated with this individual simulation model.

Controlled microbial activity is the core of many industrial processes. Such dynamic microbial processes must be carefully studied to optimize their application. They are usually tackled by means of continuous mathematical modelling at the population level (top-down). An alternative approach is individual-based modelling (IbM) (bottom-up). INDISIM is a discrete and spatially explicit IbM. It sets the rules that govern each microbe and its interaction with its local environment, as well as the significant environmental processes. Then it performs simulations that include a large number of microbes, and the behaviour of the whole system emerges. The rules are changed to reproduce the behaviour of microbes depending on the system to be studied. Two adaptations of INDISIM to study yeast fermentations and multi-species composting are presented in this article (INDISIM-YEAST and INDISIM-COMP), proof of INDISIM's versatility. A few representative results are also shown.

Ethanol produced from lignocellulosic biomass through a number of conversion pathways presents a more viable alternative to fossil fuels because non-food feedstocks are used. The approaches for ethanol production from biomass, such as wood, can be classified into three general pathways: hydrolysis fermentation (hydrolysis followed by fermentation of the sugars), gasification biosynthesis (gasification followed by biosynthesis to ethanol), and gasification chemical synthesis (gasification followed by catalytic synthesis to ethanol). To compare performance of the three pathways, a black-box system model was utilized with relevant assumptions to analyze their mass and energy conversion efficiencies. Their processing times were also estimated. A comprehensive comparison of the modeling results showed that from a process engineering standpoint, the feasibility of the biomass refining pathways ordered from high to low is gasification chemical synthesis, hydrolysis fermentation, then gasification biosynthesis. Calculations of a performance index, a singular number incorporating the major input and output and processing time of a pathway that was defined, also supported this order.