DATA6000 : CAPSTONE INDUSTRY CASE
STUDIES
Methodology Summary
Presentation
INDUSTRY REVIEW :
Analysing Crop Yield
Variability and
Economic Impacts in
Australian Broadacre
Farming
Introduction
Australian agriculture is an essential industry, demonstrating
resilience in an arid climate and a major contributor to GDP and
employment. Cover crops on broader acres, that is, wheat,
barley, and canola, are important for both domestic and foreign
soil consumption, making this crop production dynamic
important for
(1) figuring out sustainable practices, given threats from new
diseases/cis viruses; cost challenges; climate resilience; and
(2) the economy domestically and internationally.
Data Analytics
Methodology
• The data analytics methodology used was Descriptive
Analytics and Predictive Modeling.
• Reasons for the Choice:
⚬ Descriptive analytics provides a clear understanding of
historical trends and helping identify patterns in crop
yield variability and economic factors.
⚬ Predictive modeling using Tableau's forecasting tools
helps predict future outcomes based on historical data
and enabling better strategic planning.
Flow Chart
Key Analytical
Details
• Statistical Analytics : Descriptive Analytics & Predictive
Modeling
• Data Volume used :
⚬ Wheat: 41,200,000 tonnes
⚬ Barley: 13,500,000 tonnes
⚬ Canola: 8,900,000 tonnes
• Data Input :
⚬ Raw data from ABS for 2022-23 financial year.
⚬ Variables: Crop type, production, area, and local value.
• Output :
⚬ Forecasted crop yield trends.
⚬ Quantified economic impacts of price fluctuations
Visualization & Evaluation of
Result
• Descriptive Analytics Insights
⚬ Crop Yield Distribution:
￭ Stacked bar chart shows significant differences in crop
yield across Australian regions.
￭ Wheat is dominant in regions like Western Australia
and New South Wales.
• Predictive Analytics Insights
⚬ Forecasting Crop Yields:
￭ Time-series analysis was used to predict future crop
outputs under various climate scenarios.
￭ Exponential smoothing techniques provided reliable
predictions on crop yield fluctuations.
Evaluation of model &
Significance
• Title: Evaluation of the Model
⚬ Addressing Business Problems:
￭ Predictive models, such as regression analysis,
forecast the impact of climate on crop yields.
￭ Helps in understanding the economic implications of
price fluctuations on farmers' income.
• Title: Significance of Analytics
⚬ Strategic Planning:
￭ Insights inform policy-making related to resource
allocation and climate adaptation strategies.
￭ Aids stakeholders in making informed decisions for
agricultural sustainability.
Reflection on Techniques & Peer
Review
• Title: Reflection on Techniques Used
⚬ Efficacy of Software & Methods:
￭ Tableau’s visual and statistical functions effectively
created interactive dashboards.
￭ Regression and time-series analysis were key in
understanding crop-climate relationships.
• Title: Peer Discussion Review Value
⚬ Peer Feedback:
￭ Week 6 peer review identified gaps, such as the need
for more dynamic models.
￭ Improved methodology and adjusted forecasting to
account for agricultural patterns.
Broad Results
• Crop Yield Variability:
⚬ Significant regional variations in crop yields across
Australian territories, with wheat dominating Western
Australia and New South Wales.
⚬ Fluctuations in crop outputs due to varying climate
conditions, including droughts and rainfall patterns.
• Economic Impact:
⚬ Fluctuating crop prices directly affect farmer incomes and
the overall economic stability of broadacre farming.
⚬ Diverse crop production in certain regions offers risk
management benefits.
Insights related to the Business
problem
• Business Problem: Understanding how climate conditions
impact crop yields and the economic implications of price
variability.
• Key Insights:
⚬ Climate plays a critical role in determining crop outputs;
targeted agricultural practices can help mitigate the risks
of climatic variability.
⚬ Predictive modeling provides valuable insights into future
crop yields and economic trends, helping to prepare for
possible fluctuations in production and prices.
⚬ The analysis supports the need for region-specific
agricultural strategies and policies to enhance
Reflection on Data & Analytics
techniques
• Role of Data:
⚬ The data provided insights into crop yields, climate
impacts and economic factors, serving as the foundation
for analysis.
• Limitations of the Data and Analytics:
⚬ The data did not include variables like soil health,
irrigation patterns, or pest management, which could
enhance the predictive accuracy.
⚬ Forecasting models are based on historical patterns and
may not fully account for unprecedented climatic events
or policy changes.
⚬ The use of Tableau for visualization and forecasting was
Conclusion
Climate is the main driver of regional differences, with the
analysis showing large variability in yields across Australia. Even
more than soy is in the agricultural landscape—especially in
Western Australia and New South Wales. Specific to broadacre
farming, tailored farming practices and climate adaptation
policies are critical to managing risks, building sustainability,
and enhancing farm economics.
Thank You