Objetivo:
Diseñar y evaluar un sistema de soporte de decisiones para agricultura inteligente que incorpore aspectos de automatización de la fertirrigación y recomendaciones al agricultor
Descripción:
Este proyecto pretende identificar herramientas tecnológicas que desde el área de la computación e informática puedan apoyar los procesos de agricultura inteligente, un término que en los últimos años ha tomado gran relevancia por el desarrollo de nuevas tecnologías. El proyecto pretende generar conocimiento al identificar los aportes y avances que se han llevado a cabo con el desarrollo de tecnologías emergentes, y cómo estas nuevas tecnologías han apoyado al sector agropecuario o presentan un gran potencial para incorporarlas en los procesos de automatización de cosechas y optimización del uso de los recursos requeridos por las plantas para la producción.
Este proyecto pretende, además, apoyarse en el conocimiento de personas afines a la agricultura para identificar áreas en las que la computación podría apoyar en los procesos de agricultura. Al finalizar el proyecto, se podrá contar con herramientas existentes aplicadas a procesos de agricultura inteligente, algunas de las cuales serán implementadas y probadas mediante un prototipo para evaluar su aplicabilidad en procesos de agricultura de precisión. Asimismo, se espera poder identificar aquellas áreas de la agricultura bajo ambientes protegidos, es decir bajo invernaderos, en la cuales se requiere de mayor innovación tecnológica para mejorar los procesos de cultivo.
Investigador principal
Mag. José Antonio Brenes Carranza
Colaboradores
Dra. Gabriela Marín Raventós
Dr. Freddy Soto Bravo
Mag. José Antonio Brenes Carranza
Publicaciones asociadas
Early Detection of Diseases in Precision Agriculture Processes Supported by Technology
Descripción:
One of the biggest challenges for farmers is the prevention of disease appearance on crops. Governments around the world control border product entry to reduce the number of foreign diseases affecting local producers. Evenmore, it is also important to reduce the spread of crop diseases as quickly as possible and in early stages of propagation, to enable farmers to attack them on time, or to remove the affected plants. In this research, we propose the use of convolutional neural networks to detect diseases in horticultural crops. We compare the results of disease classification in images of plant leaves, in terms of performance, time execution, and classifier size. In the analysis, we implement two distinct classifiers, a densenet-161 pre-trained model and a custom created model. We concluded that for disease detection in tomato crops, our custom model has better execution time and size, and the classification performance is acceptable. Therefore, the custom model could be useful to use to create a solution that helps small farmers in rural areas in resource-limited mobile devices.
Tipo de publicación: Book Chapter
Publicado en: Advances in Sustainability Science and Technology
When One Wireless Technology is Not Enough: A Network Architecture for Precision Agriculture Using LoRa, Wi-Fi, and LTE
Descripción:
The world population will reach nearly 10 billion people by 2050, according to the United Nations. Therefore, more food to supply the world's demand will be required in the following years. Precision agriculture emerges as an option to satisfy the growing demand. In smart farming, wireless sensor networks (WSNs) are crucial in the deployment of sensors in crop fields. Precision agriculture includes crop monitoring and fertigation control. Monitoring and control have distinct network requirements. While monitoring stations deployment requires long-range networks, control stations have other requirements like low latency. For that reason, the use of a combination of WSN is necessary. In this paper, we present an option of network architecture for precision agriculture projects. The architecture includes the use of LoRa for monitoring stations and Wi-Fi/LTE for control stations. Currently, we are working on smart fertigation in greenhouses. For the architecture, we consider the typical requirements for smart farming projects, but also our project’s requirements.
Tipo de publicación: Conference Paper
Publicado en: Intelligent Sustainable Systems
Designing a Context-Aware Smart Notifications System for Precision Agriculture
Descripción:
Smart farming solutions seek to help farmers in their daily activities. Their use has shown that it is beneficial for farmers to be aware of the distinct variables affecting the production. For this reason, having alerts and notifications in monitoring and control platforms is crucial. However, in some circumstances, farmers cannot attend to the messages delivered through traditional mechanisms, making it impossible for them to be informed at the right moment. In this paper, we present the design evaluation of an intelligent context-aware smart notifications system for precision agriculture. We consider using distinct notification mechanisms to improve the delivery of notifications to the farmers. We carry out an anticipated user experience evaluation to assess the system’s design and validate the use of the notification mechanisms in distinct scenarios. A total of 48 potential users from Spain and Costa Rica participated in the evaluation. The results show that our proposed system can be very helpful in supporting farmers to be aware of the state of crops. In addition, non-traditional notification mechanisms can potentially keep the farmers informed without affecting their daily activities. Costa Rican potential users value the system’s novelty more than Spanish users.
Tipo de publicación: Conference Paper
Publicado en: Proceedings of the International Conference on Ubiquitous Computing Ambient Intelligence (UCAmI 2022)
Usability assessment of a greenhouse context-aware alert system for small-scale farmers
Descripción:
In the dynamic landscape of modern agriculture, integrating technology holds immense potential to enhance efficiency and productivity for small-scale farmers. This study presents a user-centric evaluation of an intelligent context-aware alert system, tailored for small-scale greenhouse farming. We employed standardized questionnaires, including the NASA Task Load Index and the User Experience Questionnaire, to assess the system's perceived utility, mental workload, and overall user experience. Our findings reveal the high perceived utility of the system among farmers. Farmers participating in the assessment indicated a strong intention to utilize the system for crop monitoring. Moreover, the system demonstrated a moderate mental workload, suggesting ease of use and potential acceptance by users. Our evaluation highlighted an excellent user experience, with scores ranging from very good to extremely good across all dimensions. Furthermore, user preferences for alert mechanisms underscored the importance of adaptable notifications, with voice and text alerts favored for comprehensive information dissemination. Light and voice alerts were preferred during manual tasks. This study highlights the significance of user-centered design in agricultural technology, offering insights to enhance the usability and the adoption of alert systems in small-scale farming environments. The positive reception of the system's utility and the moderate mental workload suggest that such technology can be readily adopted by farmers, thereby improving monitoring and management practices in greenhouse farming. The preference for adaptable alert mechanisms further emphasizes the need for flexible and context-sensitive solutions in agricultural technology.
Tipo de publicación: Journal Article
Publicado en: Front. Comput. Sci.
Scalable Technological Architecture Empowers Small-Scale Smart Farming Solutions
Descripción:
Smart farming technologies have the potential to revolutionize agriculture by enhancing resource efficiency, productivity, and sustainability. However, small-scale farmers in Latin America face challenges in adopting these technologies due to limited resources and technological constraints. In response, we have developed an affordable smart farming solution that empowers small-scale farmers with a comprehensive system that strategically integrates sensors into monitoring stations allowing control over specific actuators. This solution enables precise and resource-efficient production, by using monitoring stations deployed in crop fields, accessible visualization dashboards for farmers to review collected crop data, and a context-sensitive alert module.
Tipo de publicación: Journal Article
Publicado en: Commun. ACM
A cost-efficient smart solution for small-scale farmers: a multidisciplinary approach.
Descripción:
In the near years, the world population will have to deal with a big problem: to pro- duce the food required to satisfy its increasing demand. It is imperative to support farmers to find a solution. In this regard, the information and communication technologies (ICT) sector can help by creating technology which supports agriculture processes to increase the crop production and to reduce the resources consumption. In this paper, we present a cost-efficient solution for small scale farmers. Our platform helps the farmers in the decision-making process by using data recollected from crops and by controlling fertigation. Using it, farmers can be more efficient and waste fewer re- sources.
Tipo de publicación: Conference Proceedings
Research on Optimization Techniques Applied to Precision Agricultural Processes Supported by Technology in Latin America: Opportunities and a Route to Follow
Descripción:
The agricultural sector is facing significant challenges. Producing more food while consuming fewer resources like water, fertilizers, and arable land is probably the most important. Today more than ever, farmers need specialized technological tools to achieve this goal. It is possible to improve agricultural processes by practicing technology-supported precision agriculture. However, more technology development to optimize crop yield is needed worldwide. In this research, we conducted a systematic literature review in which we studied different articles that propose optimization for agricultural processes. We identified some proposals made from multiple researchers at distinct latitudes, focused on optimizing the irrigation and management of pests and diseases. Nevertheless, there are only a few studies that focus on optimizing the crop yield. They do that by controlling the different factors that can affect it. We also found out that only a few studies have been conducted in the Latin American region. Thus, these findings show areas in which there is still a lot of opportunities to contribute to the agro sector in Latin American countries.
Tipo de publicación: Conference Paper
Publicado en: 2020 XLVI Latin American Computing Conference (CLEI)
Use of Hough Transform and Homography for the Creation of Image Corpora for Smart Agriculture
Descripción:
In the context of smart agriculture, developing deep learning models demands large and high- quality datasets for training. However, the current lack of such datasets for specific crops poses a significant challenge to the progress of this field. This research proposes an automated method to facilitate the creation of training datasets through automated image capture and pre-processing. The method’s efficacy is demonstrated through two study cases conducted in a Cannabis Sativa cultivation setting. By leveraging automated processes, the proposed approach enables to create large-volume and high-quality datasets, significantly reducing human effort. The results indicate that the proposed method not only simplifies dataset creation but also allows researchers to concentrate on other critical tasks, such as refining image labeling and advancing artificial intelligence model creation. This work contributes towards efficient and accurate deep learning applications in smart agriculture.
Tipo de publicación: Journal Article
Publicado en: Int. J. Cybern. Inform.
Reinforcement Learning Model in Automated Greenhouse Control
Descripción:
Automated systems, controlled with programmed reactive rules and set-point values for feedback regulation, require supervision and adjustment by experienced technicians. These technicians must be familiar with the scenario where the controlled processes are carried out. In automated greenhouses, achieving optimal environmental values requires the expertise of a specialist technician. This introduces the need for an expert in the installation and the problem of depending on them.
To reduce these inconveniences, the integration of three paradigms is proposed: user-centered design, deployment of data capture technology based on IoT protocols, and a reinforcement learning model. The objective of the reinforcement learning model is to make decisions in the programming of set-points for the climate control of a greenhouse. In this way, the need for manual and repetitive supervision of the specialized technician is reduced; meanwhile, the control is optimized.
The design, led by an expert technician in greenhouse installations, provides the necessary knowledge to transfer to a reinforcement learning model. On the other hand, deploying the required set of sensors and access to external data sources increases the capacity of the learning model to be deployed to current installations. The proposed system was tested in automated greenhouse facilities under the supervision of a specialized technician, validating the usefulness of the proposed system.
Tipo de publicación: Book Chapter
Publicado en: Lecture Notes in Networks and Systems