John Shutske

Dr. John Shutske


Research Focus & Metrics

Academic Career Length

32Years (1995-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 September 2025 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Open access
RSRanjan Sapkota
Ranjan Sapkota
Rizwan QureshiRizwan Qureshi
Rizwan Qureshi
Muhammad Usman HadiMuhammad Usman Hadi
Muhammad Usman Hadi
SHSyed Zohaib Hassan
Syed Zohaib Hassan
FSFERHAT SADAK
FERHAT SADAK
MKManoj Karkee
Manoj Karkee
Given the rapid emergence and applications of Multi-Modal Large Language Models (MM-LLMs) across various scientific fields, insights regarding their applicability in agriculture are still only partially explored. This paper conducts an in-depth review of MM-LLMs in agriculture, focusing on understanding how MM-LLMs can be developed and implemented to optimize agricultural processes, increase efficiency, and reduce costs. Recent studies have explored the capabilities of MM-LLMs in agricultural information processing and decision-making. Despite these advancements, significant gaps persist, particularly in addressing domain-specific challenges such as variable data quality and availability, integration with existing agricultural systems, and the creation of robust training datasets that accurately represent complex agricultural environments. Moreover, a comprehensive understanding of the capabilities, challenges, and limitations of MM-LLMs in agricultural information processing and application is still missing. Exploring these areas is crucial to providing the community with a broader perspective and a clearer understanding of MM-LLMs’ applications, establishing a benchmark for the current state and emerging trends in this field. To bridge this gap, this survey reviews the progress of MM-LLMs and their utilization in agriculture, with an additional focus on 11 key research questions (RQs), where 4 RQs are general and 7 RQs are agriculture focused. By addressing these RQs, this review outlines the current opportunities and challenges, limitations, and future roadmap for MM-LLMs in agriculture. The findings indicate that multi-modal MM-LLMs not only simplify complex agricultural challenges but also significantly enhance decision-making and improve the efficiency of agricultural image processing. These advancements position MM-LLMs as an essential tool for the future of farming. For continued research and understanding, an organized and regularly updated list of papers on MM-LLMs is available at https://github.com/JiajiaLi04/Multi-Modal-LLMs-in-Agriculture.

1 November 2022 in Pathogens
Verified
Journal Article
Open access
PDF file
JGJuliano Leonel Goncalves
Juliano Leonel Goncalves
JCJuliana L. de Campos
Juliana L. de Campos
ASAndrew Steinberger
Andrew Steinberger
NSNasia Safdar
Nasia Safdar
AKAshley Kates
Ashley Kates
PRPamela L Ruegg
Pamela L Ruegg
The aim of this research was to describe the incidence and treatments of mastitis and other common bovine diseases using one year of retrospective observational data (n = 50,329 cow-lactations) obtained from herd management software of 37 large dairy farms in Wisconsin. Incidence rate (IR) was defined as the number of first cases of each disease divided by the number of lactations per farm. Clinical mastitis (CM) remains the most diagnosed disease of dairy cows. Across all herds, the mean IR (cases per 100 cow-lactations) was 24.4 for clinical mastitis, 14.5 for foot disorders (FD), 11.2 for metritis (ME), 8.6 for ketosis (KE), 7.4 for retained fetal membranes (RFM), 4.5 for diarrhea (DI), 3.1 for displaced abomasum (DA), 2.9 for pneumonia (PN) and 1.9 for milk fever (MF). More than 30% of cows that had first cases of CM, DA, RFM, DI, and FD did not receive antibiotics. Of those treated, more than 50% of cows diagnosed with PN, ME and CM received ceftiofur as a treatment. The IR of mastitis and most other diseases was greater in older cows (parity ≥ 3) during the first 100 days of lactation and these cows were more likely to receive antibiotic treatments (as compared to younger cows diagnosed in later lactation). Cows of first and second parities in early lactation were more likely to remain in the herd after diagnosis of disease, as compared to older cows and cows in later stages of lactation. Most older cows diagnosed with CM in later lactation were culled before completion of the lactation. These results provide baseline data for disease incidence in dairy cows on modern U.S. dairy farms and reinforce the role of mastitis as an important cause of dairy cow morbidity.

1 November 2023 in Agriculture
Verified
Journal Article
Open access
PDF file
GMGlen Morris
Glen Morris
SEShawn Ehlers
Shawn Ehlers
JSJohn Shutske
John Shutske
Agricultural biosecurity is a pressing global issue that must be given continuous attention by researchers, producers, consumers, and government agencies responsible for food security. This article examines the relevant literature specifically related to recommended practices for U.S. small-scale farms and ranches to minimize potential disease susceptibility in animals and humans. Current training and educational resources appear to focus on mechanisms of disease transmission and ecological and/or social factors that support mitigation efforts. Training against biological incursion and knowledge of diseases are typically focused on serving the continuing educational needs of veterinarians, epidemiological groups, and animal health technicians for large-scale facilities. However, there is a gap in the available resources that could be beneficial to keepers of livestock, smaller farmers, and ranchers who lack the financial capability to employ the most proven prevention or mitigation strategies. There have been limited comprehensive reviews in the U.S. of disease control, perception, education, or analysis on current prevention measures among small-scale producers. Findings from a review of the literature were used to formulate disease-prevention training resources and outreach strategies directed at U.S. small-scale farm operators and those likely to be involved in disease outbreak situations (e.g., veterinarians, first responders, and family members). The evaluation of the current types and causes of diseases, along with their respective level of current threat to agriculture, was a fundamental strategy to achieve this goal while reviewing literature focused on U.S. biosecurity and international biosecurity. Developing an evidence-based approach to prevention measures for biosecurity operations will allow for more effective execution and adoption of protocols for small-scale farms.

1 January 2023 in Journal of Agricultural Safety and Health
Verified
Journal Article
Open access
PDF file
JSJohn Shutske
John Shutske
Highlights Generative artificial intelligence will play a major role in the daily work of agricultural safety and health professionals. Properly trained large language models can assist educators, researchers, and clinicians in responding to agricultural safety and health questions. Numerous issues and obstacles must be overcome to use LLMs in these settings, including accuracy and completeness of responses, bias, and intellectual property concerns. Keywords: Agricultural safety, Artificial intelligence, Bias, ChatGPT, Consultation, Extension, Generative AI, Health, Education, Intellectual Property, Large language models, LLM, Teaching.

1 December 2023 in Journal of Dairy Science
Verified
Journal Article
Open access
JCJ. Leite de Campos
J. Leite de Campos
JGJuliano Leonel Goncalves
Juliano Leonel Goncalves
AKA. Kates
A. Kates
ASAndrew Steinberger
Andrew Steinberger
ASA. Sethi
A. Sethi
PRPamela L Ruegg
Pamela L Ruegg
The objective of this observational study was to describe variations in partial direct costs of clinical mastitis (CM) treatments among 37 dairy herds using data obtained from herd management records. Animal health and drug purchase records were retrospectively collected from 37 Wisconsin dairy herds for a period of 1 yr. Each farm was visited to verify case definitions, recording accuracy, and detection criteria of CM cases. Descriptive statistics were used to summarize cost of drugs and milk discard. Differences in costs among protocols, intramammary (IMM) products, parities, DIM, and recurrence were analyzed using ANOVA. Of 20,625 cases of CM, 31% did not receive antimicrobial treatment. The average cost of drugs and milk discard (including cases that were not treated) was $192.36 ± 8.90 per case and ranged among farms from $118.13 to $337.25. For CM cases treated only with IMM antimicrobials, milk discard accounted for 87% of total costs and was highly influenced by duration of therapy. Differences in costs were observed among parities, recurrence, and stage of lactation at case detection. Eight different treatment protocols were observed, but 64% of cases were treated using only IMM antimicrobials. Treatment costs varied among protocols, however cases treated using both IMM and injectable antimicrobials as well as supportive therapy had the greatest costs as they were also treated for the longest duration. Ceftiofur was used for 82% of cases that received IMM antimicrobials while ampicillin was used for 51% of cases treated using injectable antimicrobials. With the exception of ceftiofur and pirlimycin IMM products, many IMM products were given for durations that exceeded the maximum labeled duration. For cases treated using only IMM therapy, as compared with observed costs, we estimated that partial direct costs could be reduced by $65.20 per case if the minimum labeled durations were used. Overall, partial direct costs per case varied among herds, cow factors, and treatment protocols and were highly influenced by the duration of therapy.

28 December 2022 in Journal of Agromedicine
Verified
Journal Article
Closed access
JSJohn Shutske
John Shutske
The move toward more highly automated and robotic agriculture including full autonomy, where a machine operates without a human continuously guiding and controlling its function is still in its inf...