Transforming Stormwater Management with Strategic Insights of City of Greater Geelong

The City of Greater Geelong faced challenges in maintaining its extensive drainage network, worth $642 million and comprising over 2,037 km of pipes. Persistent gaps in infrastructure investment and missed annual rehabilitation targets compounded the risks to the drainage system, necessitating a strategic overhaul. The objective was to establish a reliable and efficient process for drainage renewal, leveraging existing inspection data and advanced technologies. The methodology involved targeted decision-making and machine learning to transform renewal strategies.

Project Snapshot

Transformed stormwater renewal strategies using machine learning and data-driven decision-making.

Addressed backlog inspection data, improving risk prioritization for drainage rehabilitation.

Created a $3.5 million package of actionable repairs in just four weeks.

Secured a sustainable $4 million annual budget for proactive drainage management.

About the client

The City of Greater Geelong, located in Victoria, Australia, is a rapidly growing municipality serving a population of 290,000, expected to reach 400,000. With 2,700 city employees and infrastructure assets valued at billions, the city prioritizes innovation and sustainability in urban management, including its $642 million drainage network.

The Challenge & Opportunity

The City of Greater Geelong were challenged with:

• Meeting targets for previous annual pipe rehabilitation programs.
• An increasing risk to the network due to infrastructure investment gaps.
• Process inefficiencies in prioritizing repairs and preparing tender documents.
  The challenge was to address the identified issues, ensuring long-term sustainability and resilience of the drainage infrastructure.

Solution

To address the City of Greater Geelong’s challenges, VAPAR implemented a multi-faceted approach designed to transform their stormwater renewal strategies and optimize resources:

1. Unlocking the Value of Existing Inspection Data
   A vast backlog of CCTV inspection data had accumulated over the years. VAPAR applied advanced analytics to process and interpret this data, providing actionable insights that would have otherwise required significant manual effort. By doing so, they turned a underutilized data into a valuable strategic asset.
2. Machine Learning Integration for Predictive Asset Management
   Using machine learning algorithms, VAPAR assessed pipe conditions with unprecedented detail and precision. The platform categorized defects based on severity and impact, creating reliable decision cohorts like "No Action," "Clean," "Patch," "Line," or "Dig-Up." This predictive model allowed for efficient prioritization of repairs, focusing investment where it was most needed.
3. Efficient and Data-Driven Decision-Making
   Geelong engineers conducted focused, two-hour weekly sessions over four weeks, where higher-risk inspections were reviewed collaboratively. This streamlined process ensured all stakeholders were aligned on priorities and that decisions were both rapid and data-driven.
4. Streamlined Documentation for Implementation
   Leveraging automation, VAPAR exported targeted data sets directly into tender-ready documentation (CSV & PDF). This reduced the time and effort needed to prepare detailed repair scopes, allowing for seamless integration into procurement workflows.
5. Strategic Planning for Long-Term Impact
   The project emphasized creating a sustainable approach to stormwater renewal. The strategy included balancing above-ground and below-ground factors (e.g., structural grade, surface zone, pipe diameter) related to risk evaluation, to inform a phased investment program over multiple fiscal year.

Results

The collaboration between VAPAR and the City of Greater Geelong yielded significant outcomes, both immediate and long-term:

• Operational Efficiency Gains
  The integration of machine learning drastically reduced the time and resources needed for condition assessments. Over 300 higher-risk inspections were processed in just four weeks, a task that would traditionally require months of manual effort.

• Data-Driven Decision-Making
  By categorizing pipes into distinct cohorts (e.g., "No Action," "Clean," "Patch"), VAPAR enabled the Geelong team to make consistent and reliable decisions. This approach ensured that limited resources were allocated to the most critical needs, evaluating network risks effectively.

• Financial Optimization
  The project unlocked a $3.5 million package of actionable repairs, ensuring these funds were deployed efficiently and transparently. The City also secured an ongoing $4 million annual budget for drainage asset renewal, reflecting confidence in the strategic framework established.

• Risk Mitigation and Future-Proofing
  Immediate repairs to high-risk pipes are scheduled for FY 2025, while proactive inspection and rehabilitation programs will begin from FY 2026 onward. This phased approach minimizes immediate risks while establishing a foundation for sustainable, long-term management.

• Scalability and Simplicity
  The methodology and tools developed are not limited to the City of Greater Geelong but can be scaled and quickly adopted for other municipalities facing similar challenges within their sewer & stormwater networks.

• Enhanced Collaboration and Transparency
  The structured decision-making process and clear tender documentation fostered trust and alignment among stakeholders within the engineering team. This ensured that the outcomes were not only effective but also widely supported within the City’s administration.

"Using VAPAR was 80% more accurate than our previous works process in prior years" Amila Wijekoon - Asset Engineer, City of Greater Geelong

Conclusion

The collaboration between VAPAR and the City of Greater Geelong showcases the transformative potential of leveraging data-driven decision-making and financial planning in infrastructure management. By unlocking the value of existing inspection data and integrating machine learning, the project achieved operational efficiency while ensuring resource allocation was both strategic and impactful.

A $3.5 million repair package was developed in just four weeks, demonstrating the ability to address high-priority risks quickly. Furthermore, the City’s commitment to securing a sustainable $4 million annual budget for drainage asset renewal underscores the confidence in this data-backed framework.

Moving forward, the structured inspection and rehabilitation programs planned for FY 2026 and beyond will set the foundation for a proactive, resilient, and scalable asset management strategy. This project serves as a model for municipalities seeking to bridge the gap between resource constraints and the need for sustainable infrastructure development, proving that innovation, backed by robust data, can deliver tangible financial and operational benefits.