Accurately capturing and recording data on construction sites can be a challenge. Human error, a lack of understanding or misjudgement means certain components are able to slip the net. Combining this with ensuring 100% of materials on site are certified and fully meet project requirements makes this a high-risk variable for any project.
A Machine Learning Platform, (QFlow) has been adopted for a trial period to capture and analyse construction data to mitigate against this environmental risk. It eliminates human error and ensures that all deliveries of materials and waste vehicle movements are captured. In addition to recording deliveries of fit-out materials, concrete deliveries are able to be monitored more closely than before, aiding internal carbon footprint tracking and reporting. From the data, we are able to accurately identify the site’s concrete ‘consumption’, enabling a more accurate reflection of the projects embodied carbon and this also provides a baseline figure of which can be considered when setting new project targets and objectives. Similarly, there has historically been a gap in the data provided for fuel consumption, and again this platform captures this.
Waste management is also difficult to accurately monitor. This provides a further high risk element to the project as there is a chance that the waste is not being managed correctly or legally and that Duty of Care requirements are not being upheld. QFlow, reduces this risk as all WTN’s are captured upon entry to the project site. This enables an alert or notification to be sent to the required persons in the event that an unlicensed waste carrier is being used, or if the WTN is inaccurate.