RLB: predictive cost and carbon modelling for project lifecycles is the next step
AI, machine learning and real-time asset data can be combined to develop predictive models for carbon emissions and costs throughout a project’s lifecycle, according to Rider Levett Bucknall (RLB).

“By bringing together parametric design data, insights from the supply chain, predictions about asset behaviour, and trends in global costs, we can create models that learn and adapt. These models can forecast a building’s performance throughout its working life, not just at the point of handover,” writes Jodach Mudaly, a candidate QS at RLB in Africa, in RLB’s Global Annual Report 2026.
He asserts: “Predictive lifecycle models don’t replace the expertise of cost management professionals; instead, they enrich it. This gives consultants a more detailed understanding of cost challenges, carbon pathways and operational impacts. In essence, we’re moving away from a fixed output to a dynamic model that evolves with the project.”
There are three key areas of improvement, according to Mudaly. First, rather than giving clients a set estimate for costs or emissions, predictive models can be used to show a range of possibilities, taking into account factors like material price fluctuations, wear and tear on components, energy market dynamics, and changes in regulations. “Clients get a clearer picture, seeing not just the most likely scenario, but also the best and worst-case outcomes,” he says.
Second, with tools like sensors, digital twins and asset management platforms, real-time insights into performance, maintenance needs, occupancy and energy use can be generated. Mudaly notes: “By incorporating this data back into a smart model, we can adjust future predictions and automatically refresh cost and carbon forecasts.”
Third, AI can be deployed to analyse many combinations of designs, materials and systems to pinpoint set-ups that strike the best balance between lifecycle costs, carbon emissions, operational efficiency and resilience. “This shifts decision-making away from intuition alone and toward evidence-based trade-offs. It helps in justifying decisions to boards, tenants and investors who are looking for clear carbon impact and overall value,” he says.
Delivering carbon and cost modelling
Focusing on how RLB will deliver predictive cost and carbon modelling, Mudaly writes: “Building this capability means taking a thoughtful, step-by-step approach based on a few important areas of focus:
- improve global benchmarking and cost intelligence so we have the solid data needed for accurate predictive modelling;
- broaden our knowledge of sector specifics, climate factors and regulations so our models truly reflect the varying performances and risks in the real world;
- organise and enhance historical data sets to support machine learning and help us interpret long-term trends more effectively;
- enhance our advisory skills in cost, carbon and asset management to make sure the predictions lead to real action for clients; and
- build specific partnerships with digital and sustainability innovators to speed up our capability growth and tap into new technologies.”
RLB’s goal is to gradually weave machine-learning techniques, structured cost and carbon data, and early-stage asset performance modelling into a “well-rounded operational framework”.
He concludes: “Optimising carbon output and costs throughout the lifecycle is a big step forward for our field. It changes our role from just providing information for one-time decisions to continuously guiding them. The future of our industry isn’t about just reacting. It’s all about being proactive, smart and forward-thinking.”