This thesis presents an innovative agricultural automation technique which focuses on addressing the significant perception challenges posed by occlusion within environments such as farms and greenhouses. Automated systems tasked with duties like pruning face considerable difficulties due to occlusion, complicating the accurate identification of plant features. To tackle these challenges, this work introduces a novel approach utilizing a LiDAR camera mounted on a robot arm, enhancing the system's ability to scan plants and dynamically adjust the arm's trajectory based on machine learning-derived segmentation. This adjustment significantly increases the detection area of plant features, improving identification accuracy and efficiency. Building on foreground isolation and instance segmentation, the thesis then presents an automated method for identifying optimal pruning points using best pose view images of indeterminate tomato plants. By integrating advanced image processing techniques, the proposed method ensures the pruning process by targeting branches with the highest leaf load. Experimental validation of the proposed method was conducted in a simulated environment, where it demonstrated substantially enhanced performance. In terms of pruning point identification, the method achieved impressive results with 94% precision, 90% recall, and 92% F1 score for foreground isolation. Furthermore, the segmentation of isolated images significantly outperformed non-isolated ones, with improvements exceeding 30%, 27%, and 30% in precision, recall, and F1 metrics, respectively. This validation also confirmed the method's effectiveness in accurately identifying pruning points, achieving a 67% accuracy rate when compared against manually identified pruning points. These results underscore the robustness and reliability of the approach in automating pruning processes in agricultural settings. / Master of Science / This thesis explores new methods for improving automated farming systems, particularly focusing on enhancing tasks like pruning where visibility of plant features can be significantly obstructed by overlapping leaves and branches. Central to this study is the development of an innovative approach using a special camera mounted on a robotic arm, which scans plants to determine the best vantage points for precise interactions. This setup not only identifies the optimal positions for viewing but also adjusts the robot's movements in real-time to ensure it can accurately perform pruning task. The innovative approach employed here leverages advanced technology to dynamically adjust the trajectory of the robotic arm based on real-time imaging. This enables the robot to better detect essential features of plants, which is crucial to make informed decision of where to prune the plant. By improving the robot's ability to clearly see and interact with plants, the system facilitates more precise and efficient operations. Tests conducted in simulated environments have demonstrated that this method significantly enhances the robot's capability to isolate and identify plant features accurately. These improvements make it possible for the robot to subsequently identify pruning points, potentially reducing the time and labor typically required in traditional manual operations. Overall, this research indicates that integrating advanced sensing and machine learning technologies into agricultural automation can revolutionize farming practices, making them more efficient and less dependent on human labor, especially in environments where traditional methods are less effective.

Submitted by Michele Mologni (mologni@unoeste.br) on 2018-07-27T17:21:00Z No. of bitstreams: 1 Joice Yuri Minamiguchi.pdf: 1305334 bytes, checksum: ce408a4b1cb0c85010e11bc39b0761d9 (MD5) / Made available in DSpace on 2018-07-27T17:21:00Z (GMT). No. of bitstreams: 1 Joice Yuri Minamiguchi.pdf: 1305334 bytes, checksum: ce408a4b1cb0c85010e11bc39b0761d9 (MD5) Previous issue date: 2017-12-19 / Orchid seeds do not have practically reserve of energy and are not able to absorb what exists, necessitating a symbiosis with mycorrhizal fungi for germination to occur. During the aclorophyll stage of embryo development, these are the dependent on the mycorrhizal association, because fungi provide simple sugars to the plant from digested pelotons. The objective of this work was to isolate mycorrhizal fungi of orchid in cultivated and wild plants, that could promote the germination and development of seedlings of different species. Roots of nine species of orchids were collected for the isolation by peloton, four of natural environment, three from in vitro culture that developed and grew in greenhouse orchid and two who were born spontaneously in the greenhouse orchid. This methodology promoted the isolation of nine anamorphic rhizoctonioid from two species from a natural environment, Prescotia sp and Oeceoclades maculata and of a spontaneous species in greenhouse orchid, Arundina bambusifolia. In pots of three species of orchids, Vanda sp., Cattleya tigrina and Cattleya walkeriana, were placed baiting containing seeds of the same. This methodology obtainedthe isolation of eight anamorphic rhizoctonioid fung from Cattleya tigrina and Cattleya walkeriana. Were made the quantitative and qualitative morphological characterizations of the 17 isolates obtained by the two methodologies, and these characteristics were used for the formation of groups by the grouping method UPGMA. This method together with the morphological characteristics made it possible to classify four genera of mycorrhiza, Epulorhiza, Ceratorhiza, Moniliopsis and Rhizoctonia-like. The isolates were separated into 7 different groups, and one isolate from each group was used for the symbiotic germination of six species of orchids, Cattleya brevicaulis, Cattleya tigrina, Cattleya walkeriana, Cattleya labiata, Dendrobium signatum and Encyclia cordigera. Posteriorly confirmation of the mycorrhizal association was made, of protocorm resulting from symbiotic germination. Ninety days after seeding, seedlings of the six species that germinated were transferred to flasks, and 180 days after seeding were evaluated growth and dry mass variables. The methodology of isolation by peloton promoted the isolation of mycorrhiza from plants of natural environment and from a spontaneous in greenhouse orchid, the baiting methodology was able to promote the isolation of mycorrhiza from plants that were born and developed in a controlled environment. Of the seven inoculum, six were efficient to promote the germination of the six species tested, but only five inoculum presented growth of seedlings. One inoculum is no specific, presenting better results, improving seedling growth in five of the evaluated species. / Sementes de orquídea praticamente não possuem reserva de energia e não são capazes de absorver as que possuem, necessitando de uma simbiose com fungos micorrízicos para que ocorra a germinação. Durante a fase aclorofilada do desenvolvimento do embrião, estes são dependentes da associação micorrízica, pois os fungos fornecem açúcares simples oriundos de pelotons digeridos pela planta. O objetivo deste trabalho foi isolar fungos micorrízicos de orquídeas cultivadas e silvestres, que pudessem promover a germinação e o desenvolvimento de plântulas de diferentes espécies. Raízes de nove espécies de orquídeas foram coletadas para o isolamento por peloton, quatro de ambiente natural, três oriundas de cultivo in vitro aclimatizadas e crescidas em um orquidário e de duas que nasceram espontaneamente no orquidário. Esta metodologia obteve o isolamento de nove fungos rizoctonióides anamorfos de duas espécies oriundas de ambiente natural, Prescotia sp e Oeceoclades maculata e de uma espécie espontânea no orquidário, Arundina bambusifolia. Nos vasos de três espécies Vanda sp., Cattleya tigrina e Cattleya walkeriana, foram colocados pacotes de isca contendo sementes das mesmas. Esta metodologia obteve o isolamento de oito fungos rizoctonióides anamorfos de Cattleya tigrina e Cattleya walkeriana. Foram feitas as caracterizações morfológicas quantitativas e qualitativas dos 17 isolados obtidos pelas duas metodologias, e essas características foram usadas para a formação de grupos pelo método de agrupamento UPGMA. Esse método juntamente com as características morfológicas possibilitou a classificação de quatro gêneros de micorrizas, Epulorhiza, Ceratorhiza, Moniliopsis e Rhizoctonia-like. Os isolados foram separados em sete grupos diferentes, e um isolado de cada grupo foi utilizado para a germinação simbiótica de seis espécies de orquídeas, Cattleya brevicaulis, Cattleya tigrina, Cattleya walkeriana, Cattleya labiata, Dendrobium signatum e Encyclia cordigera. Posteriormente foi feita a confirmação da associação micorrízica, dos protocórmios resultantes da germinação simbiótica. Noventa dias após a semeadura, plântulas das seis espécies que germinaram foram transferidas para frascos, e 180 dias após a semeadura foram avaliadas variáveis de crescimento e de massa seca. A metodologia de isolamento por peloton promoveu o isolamento de micorrizas de plantas de ambiente natural e de uma espontânea em orquidário. A metodologia por isca foi capaz de promover o isolamento de micorrizas de plantas que nasceram e se desenvolveram em ambiente controlado. Dos sete inóculos, seis foram eficientes para promover a germinação de sementes das seis espécies testadas, mas somente cinco inóculos exibiram crescimento de plântulas. Um inóculo demonstrou ser não específico, apresentando melhor resultado melhorando o crescimento de plântulas em cinco das espécies avaliadas.

No description available.

The world is facing a food shortage as the world’s population increases and arable land decreases. Despite this, the food industry is wasteful, and 30% - 40% of all produced food is lost before reaching the end consumer. Emerging technologies aim to increase the amount of food that can be grown per m2 or allow the growing of food in climates or on lands previously impossible. Four main farming techniques utilising these emerging technologies are Controlled Environment Agriculture, Hydroponic Farming, Urban Farming and Vertical farming. When used together, these techniques form the basis for what can be called a Plant Factory. Despite the positive effects these technologies have on the production rate, few Plant Factories have managed to achieve profitability. By creating support for developing the post-harvesting system for a plant factory, this thesis aims to aid in the development of profitable plant factories. The thesis uses Design Research Methodology to achieve this aim in three parts. The first part identifies the underlying factors of the post-harvesting system affecting plant factory profitability. The second presents a set of support components that will aid the developers to improve key factors affecting profitability. The third part is a case study where the support components applicability at targeting the key factors are evaluated, and suggestions for further improvements and testing of the support is suggested.  Further, using Design Research Methodology, the methods used to develop support in this thesis are presented to easily be replicated by other researchers to aid them in developing support for other industries and circumstances. The suitability of the developed support was tested using the principles of an initial DS-II. The developed support proved very useful for the investigated case, and with its conditions, the application evaluation was considered a partial success. Two key factors were successfully improved and indicated that the intended support is ready for a comprehensive DS-II. A third support component needs more work to provide the intended support fully. Therefore a second  PS iteration is recommended before a comprehensive DS-II is done to increase its value.

<p>This thesis aims to evaluate a Modular Manufacturing (MM) technical approach to Controlled Environment Agriculture (CEA) for cultivating plant food crops in a repurposed urban space. The specific approach was to fit a modular hydroponic CEA system into an insulated cooler box with environmental control to act as a micro plant factory. The feasibility of the approach was evaluated and a benchmark comparison between repurposed urban space and controlled lab environments was produced.</p><p>Possessing accessibility and affordability to desired quantitatively and nutritious food is a pillar for a healthy lifestyle, yet food insecurity is a growing problem worldwide, in industrial as well as industrializing nations. Food insecurity is defined as “lacking the ability to meet nutritional needs at one or multiple times during the year.” [1] Though Developing countries tend to score poorly on the Food Security Index [2], the issue is common in developed countries as well, where countries like the U.S. Possess a household food insecurity rate of above 10% [1]. Especially, subgroups of the urban population and university students in developed countries are represented at a higher rate concerning food insecurity [3], due to food insecurity’s dependence on socioeconomic factors such as purchasing power and local accessibility.</p><p>Bringing production close to the consumers or to the Point-of-Need (PoN) would be a valuable tool for supplementing traditional food crop production and increasing access to high-quality food for groups exposed to food insecurity. This is especially attractive in densely populated areas and college campuses, where real estate is prime. Bringing production to the PoN does however carry certain challenges, such as severe resource restrictions, which are not present in traditional agricultural production in rural areas where there is vast access to land, water, and plenty of sunlight. Pushing the boundaries of CEA research, technology, and application areas will be crucial for the utilization of nontraditional agricultural land, agricultural resource optimization, and food security improvements in difficult-to-farm environments to facilitate delivery to PoN.</p><p><br></p><p><b>Salient outcomes:</b> The salient outcomes of this research were that a MM platform was proven to be feasible for CEA cultivation of food crops in a repurposed urban space as well as a controlled location. Specimens cultivated in a repurposed urban space were shown to have a lower growth rate compared to a controlled location, but the important comparison is to the currently nonexistent productivity in such spaces.</p><p><b>Intellectual merit:</b> The MM CEA platform was designed, prototyped, and tested using components-of-the-shelf (COTS) as recommended by frugal engineering methodology [4]. This manufacturing platform was engineered for a case study for repurposing unused “garage space” on the college campus at Purdue University. The platform was further used for a set of studies to evaluate the feasibility of the MM platform and the production efficiency of the platform not only in a repurposed urban space but also across harsh environments across winter-spring seasons. Romaine lettuce cultivars were used as a sample plant for winter and spring studies due to their property as a popular consumable, nutritious, and relatively short growth time for better productivity. The following research issues were addressed by this research: (1) design of a modular manufacturing module; (2) testing of the module in the indoor controlled lab environment; (3) advancing design based on findings in no.2; (4) CEA testing of the integration of multiple modules (two and water supply) in the Purdue University garage (living lab) and the indoor lab environment.</p><p><b>Broader Impact:</b> The results from this research could serve as a proof-of-concept to validate the feasibility of functional modules and their integration in scaled-up urban food crop production using repurposed space. This case study especially could open opportunities for college campuses across the US (and the world), to repurpose multi-storied garage spaces for healthy food production at PoN, for example, accessible to students’ dorms and cafeterias. This MM model could further be extended to other forms of urban areas for food security and production in communities in the vicinity of garages and similar spaces in form. Utilizing unrecognized space resources in an otherwise resource-restricted environment could be the supplemental production needed to fight food desertification and insecurity in urban locations. Bringing food production to the PoN would increase the accessibility of high-quality and nutritious fresh produce, improving conditions for localized food insecurity problems.</p>

<p dir="ltr">Controlled environment agriculture (CEA) is a practice of food production under optimized conditions to intensify production yield, and thus has potential for addressing food security for a growing population. Aquaculture and aquaponics are two types of CEA that can produce aquatic animals along with plants using non-arable lands and lower inputs of water and nutrients. However, their operations have high energy consumption and generate considerable nutrient-rich sludge and wastewater, making their environmental performance an emerging research focus. This thesis quantitively analyzed the environmental sustainability of aquaponics and aquaculture production using life cycle assessment (LCA).</p><p dir="ltr">The LCA on aquaponics evaluated a marine aquaponics production system that grew shrimp, red orache, minutina and okahajiki, and analyzed the effect of salinity, C/N ratio, and shrimp-to-plant stocking density. The grow-out stage accounted for over 90% of total environmental impacts with electricity use as the predominant contributor. The marine aquaponic production exhibited best environmental performance when operated at low salinity (10 ppt), and high C/N ratio (15) and stocking density (5:1), which can be further improved by 95–99% via the use of wind power as electricity source. Additionally, variation in the prices of aquaponic products was found to improve the system’s environmental impacts by up to 8%.</p><p dir="ltr">The aquaculture LCA focused on shrimp recirculating aquaculture systems (RAS) and evaluated the environmental feasibility of microalgae-based wastewater treatment. Microalgae treatment effectively removed 74% of phosphate in RAS wastewater and thus reduced the freshwater eutrophication potential by 55%. However, its remediation performance was inferior to activated sludge treatment due to different operation scales. Electricity was the principal hotspot of microalgae treatment and made up over 99% of all the environmental impacts, which can be considerably decreased by reducing coal use in the electricity supply. Three utilization pathways for algal biomass (feed ingredient, biodiesel and biogas) were investigated; however, only biogas production was found to show environmental benefits to marine eutrophication remediation owing to the low biomass quantity produced.</p><p dir="ltr">While <a href="" target="_blank">aquaculture and aquaponics</a> play important roles in meeting the globally growing demand for seafood, this thesis provides valuable life cycle inventory data for these fields. Moreover, the LCA models developed in this thesis are useful decision-making tools for aquaculture and aquaponic producers to adapt farming practices with lower environmental footprint.</p>

Les missions spatiales habitées de longue durée nécessitent des systèmes de support-vie efficaces recyclant l’air, l’eau et la nourriture avec un apport extérieur minimum en matière et énergie. L’air et l’eau peuvent être recyclés par des méthodes purement physico-chimiques, tandis que la production de nourriture ne peut être faite sans la présence d’organismes vivants. Le projet Micro-Ecological Life Support System Alternative (MELiSSA, alternative de système de support-vie micro-écologique) de l’Agence Spatiale Européenne inclut des plantes supérieures cultivées dans une chambre close contrôlée, associée à d’autres compartiments microbiens. Le contrôle à long terme de la chambre de culture et du système de support-vie entier requiert des modèles prédictifs efficaces. Le bouclage du bilan massique et la prédiction de la réponse de la plante dans un environnement extraterrestre inhabituel mettent en avant l’importance de modèles mécanistes basés sur le principe des bilans de matière et d’énergie.Une étude bibliographique poussée a été réalisée afin de lister et analyser les modèles de croissance de plantes supérieures existants. De nombreux modèles existent, ils simulent la plupart des processus de la plante. Cependant aucun des modèles structurés globaux n’est suffisamment mécaniste ni équilibré en terme d’échange de masse pour une application dans un système de support-vie clos. Ainsi, une nouvelle structure est proposée afin de simuler tous les termes du bilan massique au niveau de la plante, en incluant les différentes échelles de l’étude : les processus généraux, l’échelle de l’organe et l’échelle de la molécule. Les résultats d’une première approche utilisant des lois physiques mécanistes simples pour les échanges de matière et d’énergie, une stoechiométrie unique pour la production de biomasse et quelques lois empiriques pour la prédiction des paramètres architecturaux sont illustrés et comparés avec des résultats expérimentaux obtenus dans un environnement contrôlé. Une analyse mathématique du modèle est réalisée et tous ces résultats sont discutés afin de proposer les prochaines étapes de développement. Ceci est décrit en détail pour l’inclusion de modèles de processus plus complexes dans les futures versions du modèle ; les expériences qui devraient être réalisées ainsi que les mesures nécessaires sont proposées. Ceci conduit à la description d’une nouvelle conception de chambre de culture expérimentale. / For long-term manned space missions, it is necessary to develop efficient life support systems recycling air, water and food with a minimum supply of matter and energy. Air and water can be recycled from purely physico-chemical systems; however food requires se presence of living organisms. The Micro-Ecological Life Support System Alternative (MELiSSA) project of the European Space Agency includes higher plants grown in a closed and controlled chamber associated with other microbial compartments. The long-term control of the growth chamber and entire life support system requires efficient predictive models. The mass balance closure and the prediction in uncommon extraterrestrial environments highlight the importance of mechanistic models based on the mass and energy balances principles.An extensive bibliographic study has been performed in order to list and analyse the existing models of higher plant growth. Many models already exist, simulating most of the plant processes. However none of the global, structured models is sufficiently mechanistic and balanced in terms of matter exchange for an application in closed life support systems. Then a new structure is proposed in order to simulate all the terms of the mass balance at the plant level, including the different scales of study: general processes, organ scale and molecular scale. The results of the first approach using simple mechanistic physical laws for mass and energy exchange, a unique stoichiometry for biomass production and few empirical laws for the prediction of architectural parameters are illustrated and compared with experimental results obtained in a controlled environment. A mathematical analysis of the model is performed and all these results are discussed in order to propose further developments. This is described in detail for the implementation of more complex models of processes in the future model versions; the experiments that should be performed including the main measurements are proposed. This leads to the description of a new design of experimental growth chamber.

[pt] À medida que a população cresce, mais alimentos precisarão ser produzidos nas próximas quatro décadas do que nos últimos 10.000 anos. No entanto, o mundo moderno ainda depende da produção de monoculturas de alto rendimento, cada vez mais ameaçada por condições climáticas incomuns, escassez de água e terra insuficiente. A fim de superar esses problemas e alimentar o mundo, é necessário um caminho prático para fornecer alimentos frescos, com qualidade e em escala, com mínima dependência do clima e com uso de água e pegada de carbono reduzidos. Uma abordagem razoável é construir fazendas verticais dentro das cidades em um ambiente fechado repleto de sensores e iluminação artificial controlada por software para uma produção e gestão eficiente do plantio de alimentos. Esta tese propõe a instanciação de um modelo, chamado Ciclo do Software dos Lugares (SoPC), que é capaz de responder a estímulos ambientais em um sistema fechado de produção de plantas com iluminação artificial que possibilite a criação de ambientes com auto-aprendizagem. Esta tese descreve o SoPC, as abordagens e processos de implementação de uma mini fábrica de plantas com iluminação artificial com base na discussão em cinco ciclos de pesquisa-ação. / [en] As the population grows, more food will need to be produced in the next four decades than has been in the past 10,000 years. However, the modern world still depends on high yield monoculture production which is increasingly threatened by unusual weather, water shortages, and insufficient land. In order to overcome these problems and feed the world, a practical path to provide quality fresh healthy food at scale with minimal weather dependency, water usage and reduced carbon footprint is necessary. One reasonable approach is to build vertical farms inside the cities in a close environment full of sensors and artificial lighting controlled by software for efficient production of food crops. This thesis proposes a model, entitled Software of Places Cycle (SoPC), that should be able to answer to environmental stimuli in a closed plant production system using artificial lighting in order to create a self-learning environment. This thesis describes the SoPC, the approaches and processes of implementing a mini Plant Factory using Artificial Lighting based on the discussion on five action-research cycles. The thesis main contribution is a conceptual model to guide the development and maintenance of a mini-PFAL (m-PFAL), a minor contribution is the deployment of the SoP, i.e., the very notion of having software dedicated to a specific place.

No description available.

No description available.