Performing Department
(N/A)
Non Technical Summary
Arable land per person is projected to decrease by two-thirds of the current available capacity by 2050. This drastic reduction is associated with climate change, reduction in freshwater supply, and population growth. Smart agriculture (SA) has proven to be highly productive, water and land-efficient, and protective of the environment. Thus, it may play a crucial role in climate-resilient food production. SA requires an agricultural workforce that has the knowledge and skills to use advanced agricultural technologies, which necessitates recruitment and training programs to ensure a tech-savvy future workforce. To address that, this project proposes a SAinformal experiential learning (EL) program to I) Expose and attract youth to smart agriculture, II) provide hands-on EL on SA, and III) Align industry and academic partnerships.Here, we propose a modular experiential learning program with four modules: Indoor/outdoor farming, Sensors (IoT) and sensor networks, Data collection and processing, Machine Learning and Artificial Intelligence. Each module will be practiced following experiential learning activities (i.e., ELA 1 to 4), starting by having a seminar explaining the underlying concepts and fundamentals along with a guest speaker highlighting the importance of these topics (ELA1), followed by course-based problem-solving and training in class (ELA2), followed by realistic hands-on training (ELA3), outdoors to practice what was covered in class, and finished by industry worksite visits (ELA4) to observe large scale practice of the covered concepts. This project will familiarize 200 Michigan middle and high school students with data science and artificial intelligence in agriculture.
Animal Health Component
(N/A)
Research Effort Categories
Basic
(N/A)
Applied
(N/A)
Developmental
(N/A)
Goals / Objectives
The goal of this proposed project is to address the critical and widespread vulnerabilities surrounding the future of the agriculture workforce and its cascading impact on Americans. This project meets AFRI Priority area of agriculture systems and technology. Objective 1: Providing inclusive, democratized, and career-promoting training opportunities in the smart agriculture areas and connecting students to resources of diverse institutions and industries.Objective 2: Designing and evaluating an experiential learning platform to train future workforce with the ultimate goal of addressing the smart agriculture workforce shortage.Objective 3: Advancing academia and industry partnership efforts within the Southeast Michigan region to strengthen economic welfare and promote developmental goals for the wider society to align the skillsets of future SA workforce with industry requirements.
Project Methods
Continuous evaluation will take place (a) to track how the proposed project is being implemented, (b) to determine any mid-course modifications needed to improve the effectiveness of the project, and (c) to determine the degree to which objectives for the project are being achieved. The evaluation plan will incorporate both formative and summative evaluation to determine the impact of the activities described in this proposal. The essential formative evaluation questions will consist of the: (1) are activities being conducted as planned (meeting target numbers on time, in the intended way, and with intended groups)? If not, why? (2) what, if any, changes have to be made to make progress toward desired program outcomes? The strength of this evaluation is a result of our comprehensive approach to analyzing multiple data sources quantitatively and qualitatively. Quantitative methodologies will be used to conduct static and longitudinal analyses of project data. First, we will design and administer pre-and post-tests to collect our baseline and post-implementation data. Survey instruments will be developed and administered to assist in the identification of factors that may explain the effectiveness or ineffectiveness of the activities being implemented (e.g., post-seminar surveys; pre-and post-summer program participant surveys; academic and industry personnel surveys; mentoring program surveys). The surveys will also be used to collect students' level of knowledge, preparation, and growth mindsets. Surveys will be administered annually. Assessments will be used to evaluate the learning outcomes of student cohorts. Statistical analyses will be performed on baseline (pre-test) and follow-up (post-test) repeated-measures data. Participants will serve as their own controls in this pre- and post-test, repeated-measures design. Descriptive statistics and parametric and non-parametric statistical analyses will be used to investigate the outcome measures. Second, semi-structured interviews with student cohorts will take place annually. Qualitative data will be analyzed using thematic content analysis in which data is coded around similar concepts until categories are constructed to synthesize findings. Constant comparison method will be employed to analyze the qualitative data from interviews during the iterative process of comparing and contrasting themes and concepts. The circumstances under which these themes occurred will be examined closely by at least two researchers to avoid researcher bias. The finalized themes and subthemes with selected verbatim quotes from participants will be included in the annual report to provide information for tailoring subsequent workshops and project activities. Qualitative analyses will be combined with quantitative analyses to provide a broadly and deeply explored, statistically sound, and descriptively rich portrait that addresses the project objectives.