Over the last decade climate-smart agriculture (CSA) has been promoted as a new approach to deal with the impacts of climate change on agriculture while simultaneously trying to mitigate emissions and improve food security. This approach suggests that these multiple goals – adaptation, mitigation and food security - could be achieved simultaneously by adopting specific technologies. At its core, CSA describes agricultural interventions that can 1) sustainably increase agricultural productivity, and hence food security and farm incomes; 2) help adapt and build resilience of agricultural systems to climate change; and 3) reduce greenhouse gas emissions from agriculture (including crops, livestock and fisheries). The main focus of CSA is on smallholder producers, many of whom are already marginalized by existing food production systems, their livelihoods increasingly affected by changes in climate. Unsustainable agricultural practices are common amongst these groups. However, there is an increasing awareness of the need to sustain the natural resource base in order to maintain or increase productivity. Malawi is one of the poorest and least developed countries in the world, with chronic food insecurity affecting large parts of the population, and climate variability increasingly noticeable across the country. Agriculture is practiced predominantly on small holdings, with more than 80% of the population depending on land-based income. In this context, the introduction of climate-smart projects and technologies with the potential to deliver triple wins could improve farmers’ incomes and food security, increase their resilience to climate change impacts, as well as deliver global benefits via climate change mitigation. This dissertation looks at the adoption levels of various, potentially climate-smart agricultural practices by smallholder dairy farmers in Malawi, with the view of establishing the current level of engagement in these practices, and identifying the factors that influence adoption. Results show the importance of the socio-economic and institutional factors in explaining the probability of adopting different agricultural practices. In particular, the findings indicate the importance of well-informed and targeted extension support as one of the major enabling factors for the adoption of improved practices. The findings further show that farmers’ climate change perceptions play a key role in the adoption of climate-smart practices. Overall, the thesis concludes that a number of currently unsustainable dairy farm management practices could be improved upon to achieve double or triple-win benefits within a reasonably short timescale, many of them at low cost. In addition, limited adoption rates of several sustainable practices that are already in place could be improved with the provision of more training, knowledge sharing and extension advice and support on the benefits of these practices. However, the thesis argues that before implementing projects and policies that promise triple wins, a careful evaluation of benefits, including mitigation, adaptation, and food security, and risks must be carried out, as triple wins will not be achievable in many cases due to the local and external constraints including lack of skills and knowledge, and lack of funding. In this respect, whether climate-smart agriculture could become a globally sustainable approach to the climate change problem in agriculture, remains to be seen.

Yes / Internet of Things (IoT)-based smart agriculture systems are increasingly being used to improve agricultural yield. IoT devices used for agricultural monitoring are often deployed in outdoor environments in remote areas. Due to the exposure to harsh environments and the nature of deployment, sensors and other devices are susceptible to an increased rate of failure, which can take a system to unsafe and dangerous states. Failure of a smart agriculture system can cause significant harm to nature and people and reduce agricultural production. To address the concerns associated with the failure of the system, it is necessary to understand how the failures of the components of a system can contribute to causing the overall system failure. This paper adopts Fault Tree Analysis, a widely used framework for failure behaviour analysis in other safety-critical domains, to demonstrate the qualitative failure analysis of smart irrigation systems based on the components’ failure. / The full-text of this article will be released for public view at the end of the publisher embargo on 10 Dec 2024.

Creating a robust supply chain is one of the factors for more sturdy agriculture. Most of the agricultural produce is getting wasted while storing and transporting the goods. AgroString in Section 3 system collects real-time temperature and humidity data from the IoAT edge device and performs secure data storage and transmission through a distributed ledger. Research and studies are being conducted to forecast the availability of clear groundwater with the help of traditional techniques to meet worldwide food requirements. Collecting quality data from various groundwater sites for storing and sharing for further analysis has become a more significant challenge. Our current work, Section 4, G-DaM, increases the value and reliability of groundwater data by implementing Distributed ledger with a public Blockchain, Ethereum, on the edge layer. Agriculture uses 65% of the world's freshwater for farming, half of which goes wasted; the same is the scenario for energy. We design an insurance system called IncentiveChain, which uses a distributed ledger on edge to incentivize farmers whenever they use resources at a needed level to give similar or more agricultural yield in Section 5. In the current research, we address some of the problems in data management and implement state-of-the-art distributed ledger designs and computing capabilities on the edge layer to show performance improvements in data from smart farming.

No description available.

O Smart Farming (SF) é um novo conjunto de tecnologias que podem ser usadas para melhorar a tomada de decisões e a automação em atividades agrícolas. Para isso, alguns agricultores começaram a utilizar a Internet das Coisas (IoT), que é uma tecnologia que permite que os objetos sejam detectados ou controlados remotamente em infraestruturas de rede existentes. Esse processo tende a criar oportunidades para uma integração mais direta do mundo físico com sistemas baseados em computador, gerando maior eficiência, precisão e benefícios econômicos para os usuários de SF. Além das novas áreas como IoT, Computação em Nuvem, Cognitive Computing e Big Data, dois campos contribuíram para o desenvolvimento de SF: Agricultura de Precisão (AP) e Tecnologia da Informação (TI).A presente tese analisou o processo de inovação no contexto da SF, desde a produção de conhecimento científico até a fase de difusão dessas tecnologias na agricultura, sendo que, o objeto de estudo contemplou as propriedades rurais de grãos. A discussão e análise realizadas no trabalho têm como base teórica o aporte da economia evolucionária e o paradigma tecnoeconômico usado para analisar revoluções tecnológicas. O trabalho consistiu de três etapas metodológicas distintas A primeira, de caráter exploratório, foi realizada por meio de entrevistas com especialistas de diferentes áreas, visando melhor compreender o tema estudado. Na segunda etapa, realizou-se um levantamento na literatura científica acerca do tema. De posse dessas informações, operacionalizou-se uma pesquisa empírica para analisar a adoção dessas tecnologias no ambiente real. Para isso, foram aplicados 119 questionários com produtores de grãos da região Sul do Brasil (Paraná, Santa Catarina e Rio Grande do Sul), sendo adotada amostragem estratificada, pois foram considerados produtores cujas propriedades produzissem 50% ou mais da receita bruta em grãos.Com base nos resultados, foi possível inferir que as tecnologias de SF encontram-se no processo de gestação e emergência. Observou-se um intenso desenvolvimento científico em tecnologias como IoT e ambientes inteligentes, bem como um forte efeito de "spillover" de outras indústrias para a agricultura. Entretanto, espera-se que nos próximos anos, o número de inovações disponíveis ao mercado na área de SF cresça. Os principais fatores de adoção de SF observados no trabalho foram: a) aumento de produtividade, b) melhor qualidade de processo, c) redução de custos, e d) maior conhecimento de áreas cultivadas. Da mesma forma, alguns fatores aumentaram a adoção de tecnologias em diferentes intensidades e maneiras. A educação teve o efeito significativo e positivo na adoção de tecnologias georeferenciadas de amostragem de solo A adoção do piloto de pulverização do piloto automático e softwares de gerenciamento teve influência positiva do tamanho da área. Os resultados da tese sinalizaram que um maior grau de escolaridade, tende a aumentar probabilidade de adoção dessas tecnologias. As principais barreiras que atrasam a entrada dos produtores de grãos na SF foram: a) o preço dos equipamentos, b) baixa qualificação do trabalho rural c) a precariedade do acesso à Internet nas regiões rurais brasileiras, e d) necessidade de inserir muitos dados e informações em software. Verificou-se assim que as máquinas empregadas nos sistemas produtivos de grãos estão passando pelo processo de digitalização, especialmente pelo aumento da disponibilidade de equipamentos com sensores e processos automatizados. No entanto, na percepção do produtor rural, grande número de técnicos e consultores ainda não está adaptado ao novo contexto da agricultura. Com isso, permanece o questionamento acerca da capacidade do produtor e dos consultores técnicos de acompanhar e aproveitar o potencial das tecnologias de SF na tomada de decisão na propriedade rural. Os resultados desse trabalho, inéditos no contexto brasileiro, avançam no sentido de compreender a difusão da SF no contexto brasileiro. / Smart Farming (SF) is a modern set technologies that can be used to improve decision making and automation throughout agricultural activities. To accomplish this, some farmers are using the Internet of Things (IoT), which is new technology that allows objects to be sensed or controlled remotely across existing network infrastructures. Further, it can create opportunities for more direct integration of the physical world into computer-based systems, which can result in improved efficiency, accuracy, and economic benefits for SF users. Besides the new areas such as IoT, Cloud Computing, Cognitive Computing and Big Data, two fields have contributed to the development of SF: Precision Agriculture (PA) and Information Technology (IT). The present study analyzed SF’s innovative processes, beginning with the production of scientific knowledge through to SF’s final diffusion of these technologies into agriculture. The discussion and analysis are based on the theoretical contributions of the evolutionary economy and the techno-economic paradigms and were used to analyze technological revolutions. The work consisted of three distinct methodological steps First, to better understand the subject being studied, interviews were conducted with researchers and market professionals, from different areas, such as agriculture, electronics engineering and mechanization. During the second stage, text mining was used to analyze scientific literature on SF. In the third step an empirical research was carried out to analyze the adoption of SF technologies in real environment. To operationalize this step, a questionnaire was sent to grain farmers from the southern region of Brazil, which included Paraná, Santa Catarina, and Rio Grande do Sul. Since these grain' farmers produced 50% or more of the gross revenue in grains were included in the database. After the surveys were completed, the empirical data was used to analyze the adoption of these technologies. Based on the results, it was possible to infer that SF technologies are in the process of gestation and emergence. There has been intense scientific development in technologies, such as IoT and smart environments. Additionally, there has been a strong spillover effect from industries to agriculture. Because of this, it is expected that the number of SF innovations available to the market will grow over the next several years The study indicated main factors that a farmer chose to adopt SF were: potential increase in productivity, better process quality, cost reduction, and a greater knowledge of cultivated areas. Additionally, adding in these factors, education had the positive effect on the adoption of georeferenced soil sampling. The adoption of an autopilot spray pilot and management software was positively influenced by the size of the area. The results of the study have indicated that a higher level of schooling tends to increase the probability of adopting these technologies. It was also found that high equipment costs, the low qualification of rural workers, the precariousness of Internet access in Brazilian rural regions, and the need to insert a lot of data and information in specific programs available to take advantage of SF technologies are the main barriers faced by grain producers, which contribute to their delay in implementing SF technologies. Additionally, it has been verified that the machines used in the grain production systems are becoming digitalized—the availability of equipment with sensors and automated processes are rapidly increasing. However, from the famers’ perception, many technicians and consultants, such as agronomists and agricultural engineers, have not yet adapted to the new context of agriculture, with growing implementation of SF technologies amongst farmers. Thus, the question remains whether farmers and technical consultants can take advantage of available SF technologies and, if so, whether they can use these technologies to help them make decisions and monitor their farming practices. The results of this research can be used to further understand how SF technologies are being used among Brazilian grain producers.

O Smart Farming (SF) é um novo conjunto de tecnologias que podem ser usadas para melhorar a tomada de decisões e a automação em atividades agrícolas. Para isso, alguns agricultores começaram a utilizar a Internet das Coisas (IoT), que é uma tecnologia que permite que os objetos sejam detectados ou controlados remotamente em infraestruturas de rede existentes. Esse processo tende a criar oportunidades para uma integração mais direta do mundo físico com sistemas baseados em computador, gerando maior eficiência, precisão e benefícios econômicos para os usuários de SF. Além das novas áreas como IoT, Computação em Nuvem, Cognitive Computing e Big Data, dois campos contribuíram para o desenvolvimento de SF: Agricultura de Precisão (AP) e Tecnologia da Informação (TI).A presente tese analisou o processo de inovação no contexto da SF, desde a produção de conhecimento científico até a fase de difusão dessas tecnologias na agricultura, sendo que, o objeto de estudo contemplou as propriedades rurais de grãos. A discussão e análise realizadas no trabalho têm como base teórica o aporte da economia evolucionária e o paradigma tecnoeconômico usado para analisar revoluções tecnológicas. O trabalho consistiu de três etapas metodológicas distintas A primeira, de caráter exploratório, foi realizada por meio de entrevistas com especialistas de diferentes áreas, visando melhor compreender o tema estudado. Na segunda etapa, realizou-se um levantamento na literatura científica acerca do tema. De posse dessas informações, operacionalizou-se uma pesquisa empírica para analisar a adoção dessas tecnologias no ambiente real. Para isso, foram aplicados 119 questionários com produtores de grãos da região Sul do Brasil (Paraná, Santa Catarina e Rio Grande do Sul), sendo adotada amostragem estratificada, pois foram considerados produtores cujas propriedades produzissem 50% ou mais da receita bruta em grãos.Com base nos resultados, foi possível inferir que as tecnologias de SF encontram-se no processo de gestação e emergência. Observou-se um intenso desenvolvimento científico em tecnologias como IoT e ambientes inteligentes, bem como um forte efeito de "spillover" de outras indústrias para a agricultura. Entretanto, espera-se que nos próximos anos, o número de inovações disponíveis ao mercado na área de SF cresça. Os principais fatores de adoção de SF observados no trabalho foram: a) aumento de produtividade, b) melhor qualidade de processo, c) redução de custos, e d) maior conhecimento de áreas cultivadas. Da mesma forma, alguns fatores aumentaram a adoção de tecnologias em diferentes intensidades e maneiras. A educação teve o efeito significativo e positivo na adoção de tecnologias georeferenciadas de amostragem de solo A adoção do piloto de pulverização do piloto automático e softwares de gerenciamento teve influência positiva do tamanho da área. Os resultados da tese sinalizaram que um maior grau de escolaridade, tende a aumentar probabilidade de adoção dessas tecnologias. As principais barreiras que atrasam a entrada dos produtores de grãos na SF foram: a) o preço dos equipamentos, b) baixa qualificação do trabalho rural c) a precariedade do acesso à Internet nas regiões rurais brasileiras, e d) necessidade de inserir muitos dados e informações em software. Verificou-se assim que as máquinas empregadas nos sistemas produtivos de grãos estão passando pelo processo de digitalização, especialmente pelo aumento da disponibilidade de equipamentos com sensores e processos automatizados. No entanto, na percepção do produtor rural, grande número de técnicos e consultores ainda não está adaptado ao novo contexto da agricultura. Com isso, permanece o questionamento acerca da capacidade do produtor e dos consultores técnicos de acompanhar e aproveitar o potencial das tecnologias de SF na tomada de decisão na propriedade rural. Os resultados desse trabalho, inéditos no contexto brasileiro, avançam no sentido de compreender a difusão da SF no contexto brasileiro. / Smart Farming (SF) is a modern set technologies that can be used to improve decision making and automation throughout agricultural activities. To accomplish this, some farmers are using the Internet of Things (IoT), which is new technology that allows objects to be sensed or controlled remotely across existing network infrastructures. Further, it can create opportunities for more direct integration of the physical world into computer-based systems, which can result in improved efficiency, accuracy, and economic benefits for SF users. Besides the new areas such as IoT, Cloud Computing, Cognitive Computing and Big Data, two fields have contributed to the development of SF: Precision Agriculture (PA) and Information Technology (IT). The present study analyzed SF’s innovative processes, beginning with the production of scientific knowledge through to SF’s final diffusion of these technologies into agriculture. The discussion and analysis are based on the theoretical contributions of the evolutionary economy and the techno-economic paradigms and were used to analyze technological revolutions. The work consisted of three distinct methodological steps First, to better understand the subject being studied, interviews were conducted with researchers and market professionals, from different areas, such as agriculture, electronics engineering and mechanization. During the second stage, text mining was used to analyze scientific literature on SF. In the third step an empirical research was carried out to analyze the adoption of SF technologies in real environment. To operationalize this step, a questionnaire was sent to grain farmers from the southern region of Brazil, which included Paraná, Santa Catarina, and Rio Grande do Sul. Since these grain' farmers produced 50% or more of the gross revenue in grains were included in the database. After the surveys were completed, the empirical data was used to analyze the adoption of these technologies. Based on the results, it was possible to infer that SF technologies are in the process of gestation and emergence. There has been intense scientific development in technologies, such as IoT and smart environments. Additionally, there has been a strong spillover effect from industries to agriculture. Because of this, it is expected that the number of SF innovations available to the market will grow over the next several years The study indicated main factors that a farmer chose to adopt SF were: potential increase in productivity, better process quality, cost reduction, and a greater knowledge of cultivated areas. Additionally, adding in these factors, education had the positive effect on the adoption of georeferenced soil sampling. The adoption of an autopilot spray pilot and management software was positively influenced by the size of the area. The results of the study have indicated that a higher level of schooling tends to increase the probability of adopting these technologies. It was also found that high equipment costs, the low qualification of rural workers, the precariousness of Internet access in Brazilian rural regions, and the need to insert a lot of data and information in specific programs available to take advantage of SF technologies are the main barriers faced by grain producers, which contribute to their delay in implementing SF technologies. Additionally, it has been verified that the machines used in the grain production systems are becoming digitalized—the availability of equipment with sensors and automated processes are rapidly increasing. However, from the famers’ perception, many technicians and consultants, such as agronomists and agricultural engineers, have not yet adapted to the new context of agriculture, with growing implementation of SF technologies amongst farmers. Thus, the question remains whether farmers and technical consultants can take advantage of available SF technologies and, if so, whether they can use these technologies to help them make decisions and monitor their farming practices. The results of this research can be used to further understand how SF technologies are being used among Brazilian grain producers.

O Smart Farming (SF) é um novo conjunto de tecnologias que podem ser usadas para melhorar a tomada de decisões e a automação em atividades agrícolas. Para isso, alguns agricultores começaram a utilizar a Internet das Coisas (IoT), que é uma tecnologia que permite que os objetos sejam detectados ou controlados remotamente em infraestruturas de rede existentes. Esse processo tende a criar oportunidades para uma integração mais direta do mundo físico com sistemas baseados em computador, gerando maior eficiência, precisão e benefícios econômicos para os usuários de SF. Além das novas áreas como IoT, Computação em Nuvem, Cognitive Computing e Big Data, dois campos contribuíram para o desenvolvimento de SF: Agricultura de Precisão (AP) e Tecnologia da Informação (TI).A presente tese analisou o processo de inovação no contexto da SF, desde a produção de conhecimento científico até a fase de difusão dessas tecnologias na agricultura, sendo que, o objeto de estudo contemplou as propriedades rurais de grãos. A discussão e análise realizadas no trabalho têm como base teórica o aporte da economia evolucionária e o paradigma tecnoeconômico usado para analisar revoluções tecnológicas. O trabalho consistiu de três etapas metodológicas distintas A primeira, de caráter exploratório, foi realizada por meio de entrevistas com especialistas de diferentes áreas, visando melhor compreender o tema estudado. Na segunda etapa, realizou-se um levantamento na literatura científica acerca do tema. De posse dessas informações, operacionalizou-se uma pesquisa empírica para analisar a adoção dessas tecnologias no ambiente real. Para isso, foram aplicados 119 questionários com produtores de grãos da região Sul do Brasil (Paraná, Santa Catarina e Rio Grande do Sul), sendo adotada amostragem estratificada, pois foram considerados produtores cujas propriedades produzissem 50% ou mais da receita bruta em grãos.Com base nos resultados, foi possível inferir que as tecnologias de SF encontram-se no processo de gestação e emergência. Observou-se um intenso desenvolvimento científico em tecnologias como IoT e ambientes inteligentes, bem como um forte efeito de "spillover" de outras indústrias para a agricultura. Entretanto, espera-se que nos próximos anos, o número de inovações disponíveis ao mercado na área de SF cresça. Os principais fatores de adoção de SF observados no trabalho foram: a) aumento de produtividade, b) melhor qualidade de processo, c) redução de custos, e d) maior conhecimento de áreas cultivadas. Da mesma forma, alguns fatores aumentaram a adoção de tecnologias em diferentes intensidades e maneiras. A educação teve o efeito significativo e positivo na adoção de tecnologias georeferenciadas de amostragem de solo A adoção do piloto de pulverização do piloto automático e softwares de gerenciamento teve influência positiva do tamanho da área. Os resultados da tese sinalizaram que um maior grau de escolaridade, tende a aumentar probabilidade de adoção dessas tecnologias. As principais barreiras que atrasam a entrada dos produtores de grãos na SF foram: a) o preço dos equipamentos, b) baixa qualificação do trabalho rural c) a precariedade do acesso à Internet nas regiões rurais brasileiras, e d) necessidade de inserir muitos dados e informações em software. Verificou-se assim que as máquinas empregadas nos sistemas produtivos de grãos estão passando pelo processo de digitalização, especialmente pelo aumento da disponibilidade de equipamentos com sensores e processos automatizados. No entanto, na percepção do produtor rural, grande número de técnicos e consultores ainda não está adaptado ao novo contexto da agricultura. Com isso, permanece o questionamento acerca da capacidade do produtor e dos consultores técnicos de acompanhar e aproveitar o potencial das tecnologias de SF na tomada de decisão na propriedade rural. Os resultados desse trabalho, inéditos no contexto brasileiro, avançam no sentido de compreender a difusão da SF no contexto brasileiro. / Smart Farming (SF) is a modern set technologies that can be used to improve decision making and automation throughout agricultural activities. To accomplish this, some farmers are using the Internet of Things (IoT), which is new technology that allows objects to be sensed or controlled remotely across existing network infrastructures. Further, it can create opportunities for more direct integration of the physical world into computer-based systems, which can result in improved efficiency, accuracy, and economic benefits for SF users. Besides the new areas such as IoT, Cloud Computing, Cognitive Computing and Big Data, two fields have contributed to the development of SF: Precision Agriculture (PA) and Information Technology (IT). The present study analyzed SF’s innovative processes, beginning with the production of scientific knowledge through to SF’s final diffusion of these technologies into agriculture. The discussion and analysis are based on the theoretical contributions of the evolutionary economy and the techno-economic paradigms and were used to analyze technological revolutions. The work consisted of three distinct methodological steps First, to better understand the subject being studied, interviews were conducted with researchers and market professionals, from different areas, such as agriculture, electronics engineering and mechanization. During the second stage, text mining was used to analyze scientific literature on SF. In the third step an empirical research was carried out to analyze the adoption of SF technologies in real environment. To operationalize this step, a questionnaire was sent to grain farmers from the southern region of Brazil, which included Paraná, Santa Catarina, and Rio Grande do Sul. Since these grain' farmers produced 50% or more of the gross revenue in grains were included in the database. After the surveys were completed, the empirical data was used to analyze the adoption of these technologies. Based on the results, it was possible to infer that SF technologies are in the process of gestation and emergence. There has been intense scientific development in technologies, such as IoT and smart environments. Additionally, there has been a strong spillover effect from industries to agriculture. Because of this, it is expected that the number of SF innovations available to the market will grow over the next several years The study indicated main factors that a farmer chose to adopt SF were: potential increase in productivity, better process quality, cost reduction, and a greater knowledge of cultivated areas. Additionally, adding in these factors, education had the positive effect on the adoption of georeferenced soil sampling. The adoption of an autopilot spray pilot and management software was positively influenced by the size of the area. The results of the study have indicated that a higher level of schooling tends to increase the probability of adopting these technologies. It was also found that high equipment costs, the low qualification of rural workers, the precariousness of Internet access in Brazilian rural regions, and the need to insert a lot of data and information in specific programs available to take advantage of SF technologies are the main barriers faced by grain producers, which contribute to their delay in implementing SF technologies. Additionally, it has been verified that the machines used in the grain production systems are becoming digitalized—the availability of equipment with sensors and automated processes are rapidly increasing. However, from the famers’ perception, many technicians and consultants, such as agronomists and agricultural engineers, have not yet adapted to the new context of agriculture, with growing implementation of SF technologies amongst farmers. Thus, the question remains whether farmers and technical consultants can take advantage of available SF technologies and, if so, whether they can use these technologies to help them make decisions and monitor their farming practices. The results of this research can be used to further understand how SF technologies are being used among Brazilian grain producers.

Cotton is harvested with large and heavy machines that are very efficient but have some disadvantages. They can harvest the crop only once at the end of the growing season. Since cotton bolls do not mature uniformly, the early opened bolls expose their fiber to weather for extended periods, reducing lint quality. In addition, the machines can also compact the soil, reducing water and fertilizer usage efficiencies and crop yields in the following years. Robotic cotton harvesting offers a promising solution to these issues. Smaller robotic harvesters could go to the field multiple times during the season to pick cotton bolls as soon as they open. Such harvesters could be lightweight, minimizing the risk of soil compaction. This dissertation research includes designing an end-effector for robotic cotton harvesting, designing a robotic platform and integrating the custom-designed end-effector, and developing multiple manipulation control algorithms. The robotic platform has a 3-DOF (degrees of freedom) manipulator and a ZED 2i stereo camera. The robot was tested under lab and field conditions to evaluate its performance in object detection, localization, and picking. The tests proved that manipulating the arm while picking a boll increased the picking ratio – the weight of the picked seed cotton over the whole weight of the seed cotton that the robot attempted to pick – by up to 23%. However, it increased the cycle time. Therefore, the control algorithm was improved to a closed-loop system to touch just the unpicked areas of a boll. The best control algorithm, i.e., I-FMW (improved-feedback-based manipulation while picking), could achieve a 72.0% picking ratio with a cycle time of 8.8 s during lab tests. The field tests were conducted to find the contribution of three main systems (detection, localization, and picking) to the losses. The tests showed that detection, localization, and picking subsystems could achieve performance of 78.1%, 70.0%, and 83.1% respectively. Therefore, detection and localization systems must be improved. Utilizing better sensors, modifying detection and localization algorithms, adding the boll orientation information, and controlling illumination conditions as much as possible would improve the picking performance and make the robot a step closer to a commercial product.

Yes / The agricultural industry has the potential to undergo a revolutionary transformation with the use of Internet of Things (IoT) technology. Crop monitoring can be improved, waste reduced, and efficiency increased. However, there are risks associated with system failures that can lead to significant losses and food insecurity. Therefore, a proactive approach is necessary to ensure the effective safety assessment of new IoT systems before deployment. It is crucial to identify potential causes of failure and their severity from the conceptual design phase of the IoT system within smart agricultural ecosystems. This will help prevent such risks and ensure the safety of the system. This study examines the failure behaviour of IoT-based Smart Irrigation Systems (SIS) to identify potential causes of failure. This study proposes a comprehensive Model-Based Safety Analysis (MBSA) framework to model the failure behaviour of SIS and generate analysable safety artefacts of the system using System Modelling Language (SysML). The MBSA approach provides meticulousness to the analysis, supports model reuse, and makes the development of a Fault Tree Analysis (FTA) model easier, thereby reducing the inherent limitations of informal system analysis. The FTA model identifies component failures and their propagation, providing a detailed understanding of how individual component failures can lead to the overall failure of the SIS. This study offers valuable insights into the interconnectedness of various component failures by evaluating the SIS failure behaviour through the FTA model. This study generates multiple minimal cut sets, which provide actionable insights into designing dependable IoT-based SIS. This analysis identifies potential weak points in the design and provides a foundation for safety risk mitigation strategies. This study emphasises the significance of a systematic and model-driven approach to improving the dependability of IoT systems in agriculture, ensuring sustainable and safe implementation.

Le riz est devenu une denrée de grande consommation au Bénin et les études prospectives le présentent comme la céréale qui sera la plus consommée en Afrique de l’Ouest dans les prochaines décennies. Malgré le potentiel rizicole dont dispose le Bénin et les stratégies nationales de promotion du riz, l’offre domestique est faible par rapport aux ambitions affichées par ce pays de parvenir à la souveraineté alimentaire. Cette thèse vise à analyser les mesures de politiques de souveraineté alimentaire en matière de riz dans une perspective de sécurité alimentaire durable. Des enquêtes exploratoires et approfondies ont été réalisées auprès des riziculteurs. Des données quantitatives et qualitatives ont été collectées à l’aide de questionnaires et guides d’entretien. Les résultats de cette recherche montrent que le riz local dispose d’un avantage comparatif par rapport au riz importé. Cependant, des efforts doivent être faits pour réduire les coûts de production afin de rendre le riz malanvillois plus compétitif. Le niveau d’instruction, l’accès au crédit, l’expérience en riziculture et le statut social du producteur peuvent contribuer à améliorer le taux d’adoption des technologies et augmenter la productivité. Une politique rizicole combinant simultanément une politique de soutien du prix, de subvention d’engrais spécifiques au riz, de culture attelée et agricole climato-intelligente augmenterait la production et permettrait de parvenir à la souveraineté alimentaire. / Rice has become a primary consumed product in Benin. Studies have revealed it will become the most consumed cereal in west Africa within the next decades. Despite the resources Benin possesses favouring rice culture and the government measures to promote it, the household supply remains unsatisfactory when compared to the objective set by the country to reach food sovereignty. The present essay analyses the government policies in order to reach a sustainable food sovereignty through rice culture. In depth, exploratory surveys have been conducted among the rice farmers. Qualitative and quantitative data was collected through structured questionnaires and guided interviews revealing the comparative advantage local rice has over imported one. Efforts have yet to be made in order for Malanville rice famers to reduce their production costs and become more competitive. Education level, access to loans, rice farmers experience as well as their social status are the key factors influencing the implementation of new technologies allowing an increase of productivity. Rice production and food sovereignty should be attained by implementing simultaneously income support policies, funded fertilizers, climate-smart culture and ploughing by oxen.