1
|
Ma P, Wu Y, Yu N, Jia X, He Y, Zhang Y, Backes M, Wang Q, Wei C. Integrating Vision-Language Models for Accelerated High-Throughput Nutrition Screening. ADVANCED SCIENCE (WEINHEIM, BADEN-WURTTEMBERG, GERMANY) 2024; 11:e2403578. [PMID: 38973336 PMCID: PMC11425866 DOI: 10.1002/advs.202403578] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/05/2024] [Revised: 06/10/2024] [Indexed: 07/09/2024]
Abstract
Addressing the critical need for swift and precise nutritional profiling in healthcare and in food industry, this study pioneers the integration of vision-language models (VLMs) with chemical analysis techniques. A cutting-edge VLM is unveiled, utilizing the expansive UMDFood-90k database, to significantly improve the speed and accuracy of nutrient estimation processes. Demonstrating a macro-AUCROC of 0.921 for lipid quantification, the model exhibits less than 10% variance compared to traditional chemical analyses for over 82% of the analyzed food items. This innovative approach not only accelerates nutritional screening by 36.9% when tested amongst students but also sets a new benchmark in the precision of nutritional data compilation. This research marks a substantial leap forward in food science, employing a blend of advanced computational models and chemical validation to offer a rapid, high-throughput solution for nutritional analysis.
Collapse
Affiliation(s)
- Peihua Ma
- Department of Nutrition and Food Science, College of Agriculture and Natural ResourcesUniversity of MarylandCollege ParkMD20742USA
| | - Yixin Wu
- CISPA Helmholtz Center for Information Security66123SaarbruckenGermany
| | - Ning Yu
- Netflix Eyeline StudiosLos AngelesCA90028USA
| | - Xiaoxue Jia
- Department of Nutrition and Food Science, College of Agriculture and Natural ResourcesUniversity of MarylandCollege ParkMD20742USA
| | - Yiyang He
- Department of Nutrition and Food Science, College of Agriculture and Natural ResourcesUniversity of MarylandCollege ParkMD20742USA
| | - Yang Zhang
- CISPA Helmholtz Center for Information Security66123SaarbruckenGermany
| | - Michael Backes
- CISPA Helmholtz Center for Information Security66123SaarbruckenGermany
| | - Qin Wang
- Department of Nutrition and Food Science, College of Agriculture and Natural ResourcesUniversity of MarylandCollege ParkMD20742USA
| | - Cheng‐I Wei
- Department of Nutrition and Food Science, College of Agriculture and Natural ResourcesUniversity of MarylandCollege ParkMD20742USA
| |
Collapse
|
2
|
Mahlein AK, Arnal Barbedo JG, Chiang KS, Del Ponte EM, Bock CH. From Detection to Protection: The Role of Optical Sensors, Robots, and Artificial Intelligence in Modern Plant Disease Management. PHYTOPATHOLOGY 2024; 114:1733-1741. [PMID: 38810274 DOI: 10.1094/phyto-01-24-0009-per] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/31/2024]
Abstract
In the past decade, there has been a recognized need for innovative methods to monitor and manage plant diseases, aiming to meet the precision demands of modern agriculture. Over the last 15 years, significant advances in the detection, monitoring, and management of plant diseases have been made, largely propelled by cutting-edge technologies. Recent advances in precision agriculture have been driven by sophisticated tools such as optical sensors, artificial intelligence, microsensor networks, and autonomous driving vehicles. These technologies have enabled the development of novel cropping systems, allowing for targeted management of crops, contrasting with the traditional, homogeneous treatment of large crop areas. The research in this field is usually a highly collaborative and interdisciplinary endeavor. It brings together experts from diverse fields such as plant pathology, computer science, statistics, engineering, and agronomy to forge comprehensive solutions. Despite the progress, translating the advancements in the precision of decision-making or automation into agricultural practice remains a challenge. The knowledge transfer to agricultural practice and extension has been particularly challenging. Enhancing the accuracy and timeliness of disease detection continues to be a priority, with data-driven artificial intelligence systems poised to play a pivotal role. This perspective article addresses critical questions and challenges faced in the implementation of digital technologies for plant disease management. It underscores the urgency of integrating innovative technological advances with traditional integrated pest management. It highlights unresolved issues regarding the establishment of control thresholds for site-specific treatments and the necessary alignment of digital technology use with regulatory frameworks. Importantly, the paper calls for intensified research efforts, widespread knowledge dissemination, and education to optimize the application of digital tools for plant disease management, recognizing the intersection of technology's potential with its current practical limitations.
Collapse
Affiliation(s)
- Anne-Katrin Mahlein
- Institute of Sugar Beet Research (IfZ), Holtenser Landstrasse 77 37079 Göttingen, Germany
| | | | - Kuo-Szu Chiang
- Division of Biometrics, Department of Agronomy, National Chung Hsing University, Taichung, Taiwan
| | - Emerson M Del Ponte
- Departamento de Fitopatologia, Universidade Federal de Viçosa, Viçosa, MG 36570-000, Brazil
| | - Clive H Bock
- U.S. Department of Agriculture-Agricultural Research Service Southeastern Fruit and Tree Nut Research Station, Byron, GA 31008, U.S.A
| |
Collapse
|
3
|
Mayokun Odewole M, Saheed Sanusi M, Olushola Sunmonu M, Yerima S, Mobolaji D, Olanrewaju Olaoye J. Digitalization of rice value chain in Nigeria with circular economy inclusion for improved productivity - A review. Heliyon 2024; 10:e31611. [PMID: 38845998 PMCID: PMC11153086 DOI: 10.1016/j.heliyon.2024.e31611] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2024] [Revised: 05/16/2024] [Accepted: 05/20/2024] [Indexed: 06/09/2024] Open
Abstract
Agriculture is a primary sector of production that is important for providing basic raw materials for many sectors. There seemed to be more people practicing it traditionally, and this situation is limiting the buoyancy of agricultural productivity. Traditional agriculture cannot fully thrive in the 21st century. This is because the global human population is currently growing at an alarming rate that is much higher than the agricultural productivity requirements to strike a balance, especially between food demand and supply. Hence, there is a need to take advantage of technology and incorporate it into agriculture with a view to bridging the gaps created by traditional agriculture. In this review paper, agricultural productivity information as it relates to the human population is presented. Also presented was background information on digital technology and its connections to agriculture through the use of some existing digital technology devices for improved productivity. Furthermore, matters relating to the rice value chain, with specific attention to Nigeria, were given extensive consideration. The circular economy (CE) approach was presented as a means of converting the three (3) major rice value chain by-products or wastes (straw, husk, and bran) to other value-added products. The CE will protect the environment and make it more friendly. Also, it will improve productivity, increase income, and create better living conditions for those in the rice value chain in Nigeria.
Collapse
Affiliation(s)
| | | | | | - Suleiman Yerima
- Faculty of Computing Engineering and Media, De Montfort University, Leicester, England, UK
| | - Dare Mobolaji
- Department of Computer Science, University of Ilorin, Nigeria
| | | |
Collapse
|
4
|
Batisha A. Multi-disciplinary strategy to optimize irrigation efficiency in irrigated agriculture. Sci Rep 2024; 14:11433. [PMID: 38763933 DOI: 10.1038/s41598-024-61372-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2024] [Accepted: 05/06/2024] [Indexed: 05/21/2024] Open
Abstract
Equilibrium among water, food, energy, and climate actions is necessary for life to exist, quality, and sustainability. This article explored how to ensure sustainability, and equilibrium in the irrigation processes by proposing irrigation equilibrium indicators (IEIs) for sustainable irrigated agriculture (SIA). The primary purpose of IEIs is to achieve a state of sustainable climate and environmental balance. The pressures driving agriculture and irrigation professionals to enhance the irrigation scheme performance are tremendous in all agricultural communities. Monitoring, assessment, and improvement of agriculture practices and irrigation schemes for enhancing the Climate, water, food, and energy (CWFE) nexus is a must. As an auspicious climate action, IEIs were developed to enhance the irrigation scheme's efficiency, within the scope of SIA. Subsequently, water, agricultural, food, and energy productivity could be optimized. Then, the appropriate equilibrium indicators could identify the actual performance of the CWFE nexus as a whole and the performance of each component. The effective irrigation scheme is the backbone of SIA. IEIs could measure the degree of achieving the overall and specific objectives and designated irrigation processes. The ultimate measure of equilibrium is optimizing sustainable agricultural yields and productivity, ensuring environmental balance, strengthening life quality, and maximizing economic returns.
Collapse
Affiliation(s)
- Ayman Batisha
- Environment and Climate Change Research Institute, National Water Research Center, Cairo, Egypt.
- Council of Future Studies and Risk Management, Academy of Scientific Research and Technology (ASRT), Ministry of Scientific Research, Cairo, Egypt.
| |
Collapse
|
5
|
Tzachor A, Devare M, Richards C, Pypers P, Ghosh A, Koo J, Johal S, King B. Large language models and agricultural extension services. NATURE FOOD 2023; 4:941-948. [PMID: 37932438 DOI: 10.1038/s43016-023-00867-x] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/20/2023] [Accepted: 09/28/2023] [Indexed: 11/08/2023]
Abstract
Several factors have traditionally hampered the effectiveness of agricultural extension services, including limited institutional capacity and reach. Here we assess the potential of large language models (LLMs), specifically Generative Pre-trained Transformer (GPT), to transform agricultural extension. We focus on the ability of LLMs to simplify scientific knowledge and provide personalized, location-specific and data-driven agricultural recommendations. We emphasize shortcomings of this technology, informed by real-life testing of GPT to generate technical advice for Nigerian cassava farmers. To ensure a safe and responsible dissemination of LLM functionality across farming worldwide, we propose an idealized LLM design process with human experts in the loop.
Collapse
Affiliation(s)
- A Tzachor
- CSER, University of Cambridge, Cambridge, UK.
- School of Sustainability, Reichman University, Herzliya, Israel.
| | - M Devare
- International Institute of Tropical Agriculture (IITA), CGIAR, Ibadan, Nigeria
| | - C Richards
- CSER, University of Cambridge, Cambridge, UK
- Department of Engineering, University of Cambridge, Cambridge, UK
| | - P Pypers
- International Institute of Tropical Agriculture (IITA), CGIAR, Ibadan, Nigeria
| | - A Ghosh
- International Center for Tropical Agriculture (CIAT), CGIAR, Nairobi, Kenya
| | - J Koo
- International Food Policy Research Institute (IFPRI), CGIAR, Washington, DC, USA
| | - S Johal
- Agstack Project, Linux Foundation, San Francisco, CA, USA
| | - B King
- Digital and Data Innovation Accelerator, CGIAR, Palmira, Colombia
| |
Collapse
|
6
|
Wilkens U, Lupp D, Langholf V. Configurations of human-centered AI at work: seven actor-structure engagements in organizations. Front Artif Intell 2023; 6:1272159. [PMID: 38028670 PMCID: PMC10664146 DOI: 10.3389/frai.2023.1272159] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2023] [Accepted: 09/29/2023] [Indexed: 12/01/2023] Open
Abstract
Purpose The discourse on the human-centricity of AI at work needs contextualization. The aim of this study is to distinguish prevalent criteria of human-centricity for AI applications in the scientific discourse and to relate them to the work contexts for which they are specifically intended. This leads to configurations of actor-structure engagements that foster human-centricity in the workplace. Theoretical foundation The study applies configurational theory to sociotechnical systems' analysis of work settings. The assumption is that different approaches to promote human-centricity coexist, depending on the stakeholders responsible for their application. Method The exploration of criteria indicating human-centricity and their synthesis into configurations is based on a cross-disciplinary literature review following a systematic search strategy and a deductive-inductive qualitative content analysis of 101 research articles. Results The article outlines eight criteria of human-centricity, two of which face challenges of human-centered technology development (trustworthiness and explainability), three challenges of human-centered employee development (prevention of job loss, health, and human agency and augmentation), and three challenges of human-centered organizational development (compensation of systems' weaknesses, integration of user-domain knowledge, accountability, and safety culture). The configurational theory allows contextualization of these criteria from a higher-order perspective and leads to seven configurations of actor-structure engagements in terms of engagement for (1) data and technostructure, (2) operational process optimization, (3) operators' employment, (4) employees' wellbeing, (5) proficiency, (6) accountability, and (7) interactive cross-domain design. Each has one criterion of human-centricity in the foreground. Trustworthiness does not build its own configuration but is proposed to be a necessary condition in all seven configurations. Discussion The article contextualizes the overall debate on human-centricity and allows us to specify stakeholder-related engagements and how these complement each other. This is of high value for practitioners bringing human-centricity to the workplace and allows them to compare which criteria are considered in transnational declarations, international norms and standards, or company guidelines.
Collapse
Affiliation(s)
- Uta Wilkens
- Institute of Work Science, Ruhr University Bochum, Bochum, Germany
| | | | | |
Collapse
|
7
|
Nabavi E, Browne C. Leverage zones in Responsible AI: towards a systems thinking conceptualization. HUMANITIES & SOCIAL SCIENCES COMMUNICATIONS 2023; 10:82. [PMID: 36909257 PMCID: PMC9984750 DOI: 10.1057/s41599-023-01579-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/05/2022] [Accepted: 02/21/2023] [Indexed: 06/18/2023]
Abstract
There is a growing debate amongst academics and practitioners on whether interventions made, thus far, towards Responsible AI have been enough to engage with the root causes of AI problems. Failure to effect meaningful changes in this system could see these initiatives not reach their potential and lead to the concept becoming another buzzword for companies to use in their marketing campaigns. Systems thinking is often touted as a methodology to manage and effect change; however, there is little practical advice available for decision-makers to include systems thinking insights to work towards Responsible AI. Using the notion of 'leverage zones' adapted from the systems thinking literature, we suggest a novel approach to plan for and experiment with potential initiatives and interventions. This paper presents a conceptual framework called the Five Ps to help practitioners construct and identify holistic interventions that may work towards Responsible AI, from lower-order interventions such as short-term fixes, tweaking algorithms and updating parameters, through to higher-order interventions such as redefining the system's foundational structures that govern those parameters, or challenging the underlying purpose upon which those structures are built and developed in the first place. Finally, we reflect on the framework as a scaffold for transdisciplinary question-asking to improve outcomes towards Responsible AI.
Collapse
Affiliation(s)
- Ehsan Nabavi
- Responsible Innovation Lab, Center for Public Awareness of Sciences, The Australian National University, Canberra, ACT Australia
| | - Chris Browne
- Responsible Innovation Lab, Center for Public Awareness of Sciences, The Australian National University, Canberra, ACT Australia
| |
Collapse
|
8
|
Lehoux P, Rivard L, de Oliveira RR, Mörch CM, Alami H. Tools to foster responsibility in digital solutions that operate with or without artificial intelligence: A scoping review for health and innovation policymakers. Int J Med Inform 2023; 170:104933. [PMID: 36521423 DOI: 10.1016/j.ijmedinf.2022.104933] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2022] [Revised: 11/20/2022] [Accepted: 11/21/2022] [Indexed: 12/12/2022]
Abstract
BACKGROUND Digital health solutions that operate with or without artificial intelligence (D/AI) raise several responsibility challenges. Though many frameworks and tools have been developed, determining what principles should be translated into practice remains under debate. This scoping review aims to provide policymakers with a rigorous body of knowledge by asking: 1) what kinds of practice-oriented tools are available?; 2) on what principles do they predominantly rely?; and 3) what are their limitations? METHODS We searched six academic and three grey literature databases for practice-oriented tools, defined as frameworks and/or sets of principles with clear operational explanations, published in English or French from 2015 to 2021. Characteristics of the tools were qualitatively coded and variations across the dataset identified through descriptive statistics and a network analysis. FINDINGS A total of 56 tools met our inclusion criteria: 19 health-specific tools (33.9%) and 37 generic tools (66.1%). They adopt a normative (57.1%), reflective (35.7%), operational (3.6%), or mixed approach (3.6%) to guide developers (14.3%), managers (16.1%), end users (10.7%), policymakers (5.4%) or multiple groups (53.6%). The frequency of 40 principles varies greatly across tools (from 0% for 'environmental sustainability' to 83.8% for 'transparency'). While 50% or more of the generic tools promote up to 19 principles, 50% or more of the health-specific tools promote 10 principles, and 50% or more of all tools disregard 21 principles. In contrast to the scattered network of principles proposed by academia, the business sector emphasizes closely connected principles. Few tools rely on a formal methodology (17.9%). CONCLUSION Despite a lack of consensus, there is a solid knowledge-basis for policymakers to anchor their role in such a dynamic field. Because several tools lack rigour and ignore key social, economic, and environmental issues, an integrated and methodologically sound approach to responsibility in D/AI solutions is warranted.
Collapse
Affiliation(s)
- P Lehoux
- Department of Health Management, Evaluation and Policy, Université de Montréal, Center for Public Health Research (CReSP), Université de Montréal and CIUSSS du Centre-Sud-de-l'Île-de-Montréal, 7101 Av du Parc, Montréal, Québec H3N 1X9, Canada.
| | - L Rivard
- Center for Public Health Research (CReSP), Université de Montréal, Canada.
| | | | - C M Mörch
- FARI - AI for the Common Good Institute, Université Libre de Bruxelles, 10-12, Cantersteen, 1000 Brussels, Belgium.
| | - H Alami
- Interdisciplinary Research in Health Sciences, Nuffield Department of Primary Care Health Sciences, University of Oxford Radcliffe Primary Care Building, Radcliffe Observatory Quarter, Woodstock Road, Oxford OX2 6GG, United Kingdom.
| |
Collapse
|
9
|
Heyl K, Ekardt F, Roos P, Garske B. Achieving the nutrient reduction objective of the Farm to Fork Strategy. An assessment of CAP subsidies for precision fertilization and sustainable agricultural practices in Germany. FRONTIERS IN SUSTAINABLE FOOD SYSTEMS 2023. [DOI: 10.3389/fsufs.2023.1088640] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/27/2023] Open
Abstract
The Farm to Fork Strategy of the EU aims at sustainable food systems. One objective of the Strategy is to reduce nutrient losses by at least 50% resulting in at least 20% less fertilizer use by 2030. To this end, Member States are expected to extend digital precision fertilization and sustainable agricultural practices through the Common Agricultural Policy. In this context, this article applies a qualitative governance analysis which aims to assess the extent to which the measures proposed by the Farm to Fork Strategy, i.e., digital precision fertilization and sustainable agricultural practices, contribute to the nutrient objective of the Farm to Fork Strategy. The article analyses how these measures are implemented through the Common Agricultural Policy in Germany and Saxony. Results show that the nutrient objective of the Farm to Fork Strategy itself offers shortcomings. Germany offers some, yet overall limited, support for sustainable agricultural practices and digital precision fertilization. Hence, the Common Agricultural Policy will to a limited extend only contribute to the objective of the Strategy. The results furthermore highlight some general shortcomings of digitalization as sustainability strategy in the agricultural sector including typical governance issues (rebound and enforcement problems), and point to the advantages of quantity-based policy instruments.
Collapse
|
10
|
Eastwood CR, Dela Rue B, Edwards JP, Jago J. Responsible robotics design-A systems approach to developing design guides for robotics in pasture-grazed dairy farming. Front Robot AI 2022; 9:914850. [PMID: 35912302 PMCID: PMC9334655 DOI: 10.3389/frobt.2022.914850] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2022] [Accepted: 06/28/2022] [Indexed: 11/13/2022] Open
Abstract
Application of robotics and automation in pasture-grazed agriculture is in an emergent phase. Technology developers face significant challenges due to aspects such as the complex and dynamic nature of biological systems, relative cost of technology versus farm labor costs, and specific market characteristics in agriculture. Overlaying this are socio-ethical issues around technology development, and aspects of responsible research and innovation. There are numerous examples of technology being developed but not adopted in pasture-grazed farming, despite the potential benefits to farmers and/or society, highlighting a disconnect in the innovation system. In this perspective paper, we propose a "responsibility by design" approach to robotics and automation innovation, using development of batch robotic milking in pasture-grazed dairy farming as a case study. The framework we develop is used to highlight the wider considerations that technology developers and policy makers need to consider when envisaging future innovation trajectories for robotics in smart farming. These considerations include the impact on work design, worker well-being and safety, changes to farming systems, and the influences of market and regulatory constraints.
Collapse
|