Logo des Repositoriums

Auflistung nach Schlagwort "smart farming"

1 - 9 von 9
  • Konferenzbeitrag
    Can algorithms help us manage dairy cows?
    (41. GIL-Jahrestagung, Informations- und Kommunikationstechnologie in kritischen Zeiten, 2021) Cockburn, Marianne
    Digitalisation has reached agricultural production and specifically dairy farming, where a wide range of sensing technologies are now available. From farm management systems over body condition scoring systems to those that detect behavioural changes. All these systems have one aim: to offer decision support to the farmer and aid his management decisions. Currently, however, little is known about the return of investment that these systems offer, or even the effectiveness of their functionality. Only little information is available about the underlying algorithms, despite them presenting the essence of performance. Thus, we can only consider the published literature to get an impression of such systems’ outcome. In the current study, we therefore evaluated machine-learning related studies published in the scientific literature between 2015 and 2020. We found that machine-learning algorithms were implemented across all fields of dairy science, but only a minority of them could reliably aid management decisions in practice. In this publication, we aim to give an overview of the achievements of current machine-learning algorithms published in dairy science literature and give an outlook on how they could develop further in the future.
  • Konferenzbeitrag
    Cyberattacks in agribusiness
    (42. GIL-Jahrestagung, Künstliche Intelligenz in der Agrar- und Ernährungswirtschaft, 2022) Hoffmann, Christa; Haas, Roland; Bhimrajka, Nidhish; Penjarla, Naga Srihith
    Cyberattacks are increasing across different industry sectors. The agribusiness sector has seen an accelerating rate of ransomware attacks both upstream as well as downstream. The article analyses attacks which were reported over more than a decade and summarizes the major trends. The increasing connectivity and deployment of sophisticated IT solutions for precision and smart farming makes this sector potentially very vulnerable.
  • Konferenzbeitrag
    A data quality assessment tool for agricultural structured data as support for smart farming
    (43. GIL-Jahrestagung, Resiliente Agri-Food-Systeme, 2023) Schroth, Christof; Kelbert, Patricia; Vollmer, Anna Maria
    In the field of precision farming or smart farming, more and more sensors are used and produce a massive amount of data. Examples are machinery, weather stations, or georeferenced data, which can be used, among other things, by Artificial Intelligence decision support systems to improve or facilitate farmers’ daily work tasks. Even if there are no issues in transferring (Internet of Things) sensor data from machines to farm management information systems, data still contain errors such as missing, implausible, or incorrect data values. In this paper, we present an automated data quality assessment (DQA) tool based on the ISO25012 standard. We describe the process of how we developed this tool with support from practitioners who produce agricultural data in the context of the EU Horizon 2020 project DEMETER. Additionally, we highlight some of the requirements we collected for such a tool and briefly discuss how we addressed them. For example, we learned that in the context of developing smart farming services, the data quality dimensions Accuracy, Completeness, Consistency, and Credibility are the most important ones for practitioners such as farmers, digital service providers, or machine suppliers. Therefore, we included them in the DQA tool and implemented it in Python. It is released under the open-source Apache 2 license. Individual parameters can be provided as input for calculations (e.g., thresholds or time lengths) to meet different users’ needs. The output of the DQA is provided in machine-readable JSON format and can be used for further analysis, e.g., to improve the quality of the data collection or the follow-up data analysis. This can help practitioners develop more valuable smart farming services.
  • Konferenzbeitrag
    The Hofbox as a decentralised solution for agricultural operations
    (INFORMATIK 2023 - Designing Futures: Zukünfte gestalten, 2023) Weis, Martin; Bökle, Sebastian; Bauer, Christian
    In digital farming applications cloud-based software offers are predominantly used, which simplifies software and data handling, but lacks transparency of data storage and usage. Internet access becomes essential, which makes time-critical and weather-dependant applications dependent on internet connectivity posing risks for timely execution. To address these issues, a Hofbox concept is being developed that provides openly available software components on local computer hardware. It is based on a modular structure with automatically installable and configurable microservices. The Hofbox thus enables local data storage and processing as well as targeted data exchange via cloud systems that are organised in a decentralised manner. Machinery rings and farmers are targeted decentralised entities. The connected farm boxes are maintained according to an edge computing approach. All components are open source thus ensuring adaptability and expandability, focusing on the use of geodata for small and medium-sized farms.
  • Konferenzbeitrag
    Living lab research project "5G Smart Country" - Use of 5G technology in precision agriculture exemplified by site-specific fertilization
    (EnviroInfo 2022, 2022) Bhatti, Moid Riaz; Akyol, Ali; Rosigkeit, Henrik; Matzke, Linda; Grabenhorst, Isabel; Gómez, Jorge Marx
    The research project "5G Smart Country" aims at developing ideas for the development and testing of 5G applications for agriculture and forestry under real conditions. Agricultural and forestry data are collected from a wide variety of sources, such as satellites, drones, and robots with special sensors. Artificial intelligence (AI) and data analytics algorithms help make the required decisions, particularly for automatic differentiation between crops and weeds for mechanical weed control, demand-driven fertilization (variable rate application, VRA)—also by means of small-scale application (pointed fertilizing)—automated tracking of wildlife populations, real-time assessment of harvest (smart harvesting), forest inventory maintenance, and targeted logging. Here we present a system architecture and software model for digital crop management and show how multispectral analysis is used to develop vegetation indices to conduct VRA.
  • Konferenzbeitrag
    Route-planning in output-material-flow arable farming operations aiming for soil protection
    (42. GIL-Jahrestagung, Künstliche Intelligenz in der Agrar- und Ernährungswirtschaft, 2022) Focke Martinez, Santiago; Hertzberg, Joachim
    This paper presents two approaches for route planning in output-material-flow arable farming: one for time optimization and one for soil protection. The two approaches were used to plan the routes of one harvester and one transport vehicle performing a harvesting operation in a test field, and were compared by analyzing the operation duration, travel distance, and area driven over by the machines. The results show the benefits and drawbacks of planning the machine routes using the proposed method for soil protection: the plans can reduce the impact of driving over the soil, but it can result in higher operation durations and traveled distances
  • Konferenzbeitrag
    Synthetic fields, real gains
    (44. GIL - Jahrestagung, Biodiversität fördern durch digitale Landwirtschaft, 2024) Wachter, Paul; Kruse, Niklas; Schöning, Julius
    Artificial intelligence (AI) promises transformative impacts on society, industry, and agriculture, while being heavily reliant on diverse, quality data. The resource-intensive “data problem” has initialized a shift to synthetic data. One downside of synthetic data is known as the “reality gap”, a lack of realism. Hybrid data, combining synthetic and real data, addresses this. The paper examines terminological inconsistencies and proposes a unified taxonomy for real, synthetic, augmented, and hybrid data. It aims to enhance AI training datasets in smart agriculture, addressing the challenges in the agricultural data landscape. Utilizing hybrid data in AI models offers improved prediction performance and adaptability.
  • Konferenzbeitrag
    Towards a common understanding of digital transformation in agriculture
    (41. GIL-Jahrestagung, Informations- und Kommunikationstechnologie in kritischen Zeiten, 2021) Hannus, Veronika; Kolbe, Thomas H.
    This article presents a literature-based approach to delimitate the topic of ‘digital transformation in agriculture’. We elaborate a Scopus search string and find six clusters that form and describe this new field of research. Most prominent topic clusters are remote sensing, geographic information systems, internet-of-things and image processing, with the last two being most topical. Social science topics seem to be underrepresented or to have not yet established a direct link in this new research area via key terms. Further, European publications reflect the full range of worldwide research, although there is a slightly stronger focus on environmental issues
  • Konferenzbeitrag
    Towards on-line monitoring and route re-planning in arable crop harvest
    (44. GIL - Jahrestagung, Biodiversität fördern durch digitale Landwirtschaft, 2024) Santiago Focke Martinez, Isaak Ihorst
    Route planning for farming machines can be used as a tool to improve the efficiency of arable farming operations. However, discrepancies between actual process parameters and the parameters used for route planning might result in the need to re-plan using updated/corrected planning parameters. This paper presents a concept for process monitoring and route re-planning in arable harvesting operations, together with updates on a previously presented route-planning tool developed to support re-planning during harvesting, and a set of monitoring components developed to generate field worked-area grid-maps and to monitor deviations between planned inner-field tracks and actual machine transit. The newly implemented re-planning features in the route planner and the monitoring components were tested under a simulated harvesting scenario.