We are creating some awesome events for you. Kindly bear with us.

From source to sink: how data science helps Singapore manage its water resources



In collaboration with GOVTECH




Everyday, Singapore uses about 430 million gallons of water—an amount equivalent to 782 Olympic-sized swimming pools. In a few decades, demand is expected to nearly double. Fresh water is undeniably a necessity, and yet, it’s one resource that Singapore also naturally lacks. Adding fuel to the fire is the looming threat of prolonged dry spells caused by climate change.

Responsible for ensuring Singapore’s water supply in the face of these challenges is PUB, Singapore’s National Water Agency. On a daily basis, operators at PUB need to determine how to smartly allocate water resources to satisfy demand islandwide, a task easier said than done.

To help operators make these decisions, a team composed of PUB engineers and GovTech data scientists built a model that optimally allocates water resources based on operational constraints. Since the model’s implementation, planning time has been reduced from two hours to as low as fifteen minutes. Here’s how GovTech and PUB made every drop count—using data science techniques.

Tapping Singapore’s water resources

Singapore obtains its water from four sources dubbed the “Four National Taps;” namely water from local catchments or reservoirs, imported water, high-grade reclaimed used water called NEWater and desalinated water from the oceans. As climate change warms the world and dries our water bodies, weather-independent sources like the last two are expected to contribute to more of Singapore’s water supply.

It should be noted, though, that not all taps are created equal; some are more expensive than others. Sources like NEWater and desalinated water, for instance, require extensive processing methods that come at a price. Hence, PUB operators will need to determine on a daily basis how to allocate water from these four sources to satisfy water demand islandwide.

To solve this problem, the team used a common optimisation technique known as linear programming for their model. In linear programming, complex relationships are depicted as linear functions, similar to lines on a graph. This greatly simplified many parameters that were coded into the model, including the different water sources and pipes connecting them.

All these factors, along with other operational constraints—like the capacity of treatment plants and storage tanks, as well as size of the water pipes—were taken into account by the team when coding the model. The model then finds the optimised solution for the given objective given the operational constraints.

Therefore, in a hypothetical scenario of cost minimisation, where a PUB operator has to make a decision between drawing water from a raw water treatment plant or a desalination plant, the model will choose the former. “[Between] the raw water treatment plant and the desalination plant,” explained Mr Tan Kai Wei, an associate computational scientist at GovTech’s Data Science Artificial Intelligence Division (DSAID). “It will make sense to draw from the cheaper alternative, which is from the raw water treatment plant.”

Satisfying and satisficing water demand

While the example above gives a glimpse of how the model can work under limited conditions, real life is far more tricky. Demand for water can vary day to day, as can the amount of rainfall. “Last year, July and August were very dry,” recalled Dr. Loke Gar Goei, a quantitative analyst also at GovTech’s DSAID . “The amount of rainfall we had last year in this period was only 1.2% of what would fall in this period historically.”

To ensure the flexibility of their model even in such unexpected situations, the team turned to a technique called satisficing. Instead of choosing the most optimal solution, the model goes for a more conservative option that merely satisfies, or ‘satisfices,’ any operational requirements.

According to the team, their model is the first in the world to attempt the usage of satisficing in managing water resources. In aiming to satisfice instead of optimise, the impact of uncertainty on the model’s decision making capabilities is softened.

The team of data scientists at GovTech’s Data Science Artificial Intelligence Division (DSAID), from left to right: Dr Loke Gar Goei, Chin Chii Yeh and Tan Kai Wei.

Putting the model through the test

Upon completion, the model was trialled on data from last year’s dry spell to establish its effectiveness. The results were encouraging but, given the novelty of the satisficing approach and the quality of available forecast data, the team eventually decided to go for a compromise scenario-based approach where the model is used to optimise for different scenarios instead.

With this approach, the team was still able to automate a large part of the planning process and increase the optimality of derived solutions. Furthermore, the team also developed several innovative programming solutions to ensure easier adoption by operators. All these served to reduce the time required for detailed operations planning and improved operational outcomes.

Beyond reducing the time needed to make decisions, the team is quick to highlight the wider relevance of their unique water management model. “One of the main reasons we wanted to do this is because in a public policy setting, we cannot afford large errors,” shared Dr Loke. “Water is a public good. Because of this, we have to be prudent in the way we go about making decisions.”

For a more in-depth look at how the team created their model, check out this three-part Medium blog post written by GovTech’s Mr Tan Kai Wei.

The team of PUB Engineers, from left to right: Hariharan s/o Ramasamy (Engineer, Joint Operations Department), Daniel John Tan (Engineer, Joint Operations Department), and Ashley Ng (Senior Planner, Policy and Planning Department).


Qlik’s vision is a data-literate world, where everyone can use data and analytics to improve decision-making and solve their most challenging problems. A private company, Qlik offers real-time data integration and analytics solutions, powered by Qlik Cloud, to close the gaps between data, insights and action. By transforming data into Active Intelligence, businesses can drive better decisions, improve revenue and profitability, and optimize customer relationships. Qlik serves more than 38,000 active customers in over 100 countries.


CTC Global Singapore, a premier end-to-end IT solutions provider, is a fully owned subsidiary of ITOCHU Techno-Solutions Corporation (CTC) and ITOCHU Corporation.

Since 1972, CTC has established itself as one of the country’s top IT solutions providers. With 50 years of experience, headed by an experienced management team and staffed by over 200 qualified IT professionals, we support organizations with integrated IT solutions expertise in Autonomous IT, Cyber Security, Digital Transformation, Enterprise Cloud Infrastructure, Workplace Modernization and Professional Services.

Well-known for our strengths in system integration and consultation, CTC Global proves to be the preferred IT outsourcing destination for organizations all over Singapore today.


Planview has one mission: to build the future of connected work. Our solutions enable organizations to connect the business from ideas to impact, empowering companies to accelerate the achievement of what matters most. Planview’s full spectrum of Portfolio Management and Work Management solutions creates an organizational focus on the strategic outcomes that matter and empowers teams to deliver their best work, no matter how they work. The comprehensive Planview platform and enterprise success model enables customers to deliver innovative, competitive products, services, and customer experiences. Headquartered in Austin, Texas, with locations around the world, Planview has more than 1,300 employees supporting 4,500 customers and 2.6 million users worldwide. For more information, visit www.planview.com.


SIRIM is a premier industrial research and technology organisation in Malaysia, wholly-owned by the Minister​ of Finance Incorporated. With over forty years of experience and expertise, SIRIM is mandated as the machinery for research and technology development, and the national champion of quality. SIRIM has always played a major role in the development of the country’s private sector. By tapping into our expertise and knowledge base, we focus on developing new technologies and improvements in the manufacturing, technology and services sectors. We nurture Small Medium Enterprises (SME) growth with solutions for technology penetration and upgrading, making it an ideal technology partner for SMEs.


HashiCorp provides infrastructure automation software for multi-cloud environments, enabling enterprises to unlock a common cloud operating model to provision, secure, connect, and run any application on any infrastructure. HashiCorp tools allow organizations to deliver applications faster by helping enterprises transition from manual processes and ITIL practices to self-service automation and DevOps practices. 


IBM is a leading global hybrid cloud and AI, and business services provider. We help clients in more than 175 countries capitalize on insights from their data, streamline business processes, reduce costs and gain the competitive edge in their industries. Nearly 3,000 government and corporate entities in critical infrastructure areas such as financial services, telecommunications and healthcare rely on IBM’s hybrid cloud platform and Red Hat OpenShift to affect their digital transformations quickly, efficiently and securely. IBM’s breakthrough innovations in AI, quantum computing, industry-specific cloud solutions and business services deliver open and flexible options to our clients. All of this is backed by IBM’s legendary commitment to trust, transparency, responsibility, inclusivity and service.

Send this to a friend