Login

Course Insights Faculty Insights on Courses They Teach

AGR 33300

Data Science For Agriculture
Spring 2022

About Course Insights
Course Insights is a platform for faculty to share detailed information about the courses they teach. This page is not to be interpreted as being the official course syllabus for this course.
About the Course
Future agricultural professionals will be required to use data in an intensity and volume magnitudes beyond what is required today.  New and cheaper sensors, and our increasing ability to move, store and analyze data is creating a need for professionals who can turn volumes of information into knowledge and inform decisions in agribusiness, on farms, and with governments and organizations.  AGR 33300 brings data alive by teaching data science within the context of agriculture.
 
AGR 33300 COURSE DESCRIPTION:  Credit Hours: 3.00.  Students will apply data processes including identifying data needs, acquiring data, assessing data quality, data wrangling, filtering, merging of disparate but related data sets, visualization, and decision-making in each of several topic areas (forestry, animal science, agronomy, food science, entomology, engineering, economics). Students will understand data ethics.
 
Course Goals/Learning Objectives
LEARNING OBJECTIVES:
  1. Construct a research question that helps address a decision.
  2. Describe different types of experimental designs and discuss the differences between observational and experimental studies.
  3. Identify data needed to address various research questions.
  4. Identify how these data sources are used in data analysis: agronomics, machine data, maps, spreadsheets, sensor data.
  5. Describe how various data sets are acquired.
  6. Describe how the following impact data ethics: ownership, storage, access.
  7. Assess data quality and utility.
  8. Identify potential limitations of a dataset.
  9. Describe the following aspects of data wrangling: data formats, data compatibility, mobility.
  10. Describe the following aspects of data management: storage, curation, metadata, FAIR (findable, accessible, interoperable, reusable).
  11. List reasons for filtering, cleaning, and pre-processing data.
  12. Describe tools for data cleaning.
  13. Integrate disparate data sets.
  14. Describe uses for the following in data visualization: bar charts, line charts, maps, tables.
  15. Use the following tools to analyze data: correlations, mean generation, confidence intervals, simple model building, R Python.
  16. Make decisions based on data outcomes.
Proposed Content Outline
Week
Area
Topic
1
Intro
Orientation to data cycle.  FAIR concept. Import of CSV into Excel & R with some statistical computations. Experimental design, observational vs. experimental studies.
2-3
Food Science
Identifying research questions and data needed:  Ethics of data (ownership, storage, access), data literacy.
4-5
IoT & Autonomy
Data collection and mining:  Importing data to program of choice. Use a sensor in lab. Sourcing data from online. Identification of outliers. Simple data architecture/naming, sharing, metadata
6-7
Animal Science
Data wrangling (formats, compatibility, mobility).  Data from multiple sources.  Finding unique identifiers and getting in similar formats for integration.  Removal or filtering of data points outside the scope of the question. Identifying data gaps.
8
 
Break
9-10
Forestry
Data integration:  Merge/collate disparate data sets. Wrangle coordinate reference systems, import spatial data.  Plot vector and raster data, combine/extract data between layers.
11
Soil & Water
Data visualization:  Aspects of good/bad graphics.  Matching graphic to the data. Exploratory analysis: means, histograms, maps, time-series.
12-13
Crops
Data analysis: Interpolate spatial point data to create a data layer.  Methods of interpolation, cluster analysis, supervised or unsupervised classification, zone delineation. Input data into a crop model to create field recommendations.
14-15
Ag Economics
Decision-making:  Estimate supply/demand curves based on economic theory.Incorporate cost/returns data to perform economic optimization (production functions, cost minimization, profit maximization).
Course Instructors
Jacquelyn Boerman
Assistant Prof, Animal Sciences
Dennis Buckmaster
Prof Ag & Biological Engineering
Nathan DeLay
Assistant Prof Ag Economics
Bruce Erickson
Clinical Assoc. Prof of Digital Ag
John Evans
Assistant Prof, Ag & Bio Engineering
Yaohua "Betty" Feng
Assistant Prof Food Sciences
Jeffrey Holland
Prof Entomology
Guofan Shao
Prof Forestry and Natural Resource
Pre-Requisite: STAT 301
STAT 301 is a requirement for most Agriculture majors

AGR 33300

Course Catalog
AGR 33300 Data Science For Agriculture

Description
Credit Hours: 3.00. Students will apply data processes including identifying data needs, acquiring data, assessing data quality, data wrangling, filtering, and visualization. In each of several topic areas (forestry, animal science, agronomy, food science, entomology, engineering, economics), data-driven insights and improved decision making will be the culmination of applied data skills. Students will understand data ethics and practice data management skills including the merging of disparate but related data sets.
0.000 OR 3.000 Credit hours
Levels: Undergraduate, Graduate, Professional
Schedule Types: Distance Learning, Laboratory, Lecture
Offered By: College of Agriculture
Department: College of Agriculture Admin
Course Attributes
Upper Division
May be offered at any of the following campuses: West Lafayette
Learning Objectives
1. Construct a research question that helps address a decision. 2. Describe different types of experimental designs and discuss the differences between observational and experimental studies. 3. Identify data needed to address various research questions. 4. Identify how these data sources are used in data analysis: agronomics, machine data, maps, spreadsheets, sensor data. 5. Describe how various data sets are acquired. 6. Describe how the following impact data ethics: ownership, storage, access. 7. Assess data quality and utility. 9. Identify potential limitations of a dataset. 10. Describe the following aspects of data wrangling: data formats, data compatibility, mobility. 11. Describe the following aspects of data management: storage, curation, metadata, FAIR (findable, accessible, interoperable, reusable). 12. List reasons for filtering, cleaning, and pre-processing data. 13. Describe tools for data cleaning. 14. Integrate disparate data sets. 15. Describe uses for the following in data visualization: bar charts, line charts, maps, tables. 16. Use the following tools to analyze data: correlations, mean generation, confidence intervals, simple model building, R Python. 17. Make decisions based on data outcomes.
Prerequisites
Undergraduate level STAT 30100 Minimum Grade of D-
Other Information
All Sections for this Course
Having trouble? Self Help Knowledgebase | For assisted support: itap@purdue.edu or 765-494-4000
Purdue University is an equal access/equal opportunity university. If you have trouble accessing
this page because of a disability, please contact ITaP Customer Service at itap@purdue.edu.