We are international front runner in applying artificial intelligence, machine learning and cloud computing technologies in smart infrastructure solutions. We work with government and industry partners on projects covering utilities, energy, telecommunications, and transport.
In 2022, Cricket NSW and the UTS Data Science Institute (DSI) launched the Player Journey Intelligence Project to better understand why some players keep swinging for the fences while others walk off the field for good.
Drawing on seven years of community cricket data, DSI researchers developed clustering models to describe the behavioural patterns of community players and to identify the drivers that keep both kids and adults playing.
Our client, the Australian Agricultural Company (AACo), is a renowned and pioneering beef company with a substantial presence in Australian agricultural landscape. Recognizing the importance of sustainable practices and the imperative of carbon sequestration, AACo has encountered the challenge of enabling rangeland farmers to actively manage carbon within soil and vegetation. This aims to enhance enterprise profitability, sustainability, and resilience, all while responding to market demands and meeting carbon targets. Furthermore, the task of measuring soil and vegetation carbon across extensive rangelands, which constitute 75% of Australia's landmass, can incur exorbitant costs. Even with access to this data, comprehending management options and sequestration potential remains elusive. This challenge has spurred the initiation of the Rangeland Carbon Project.
Through this initiative, we have devised innovative solutions that are not only accurate but also cost-effective for estimating landscape carbon levels over time in Australian rangelands. Leveraging advanced technologies such as machine learning and geoanalytics, we (UTS) accurately estimate carbon stored within woody vegetation and soil using remote sensing data and aerial photographs. These approaches significantly reduce the expenses associated with carbon measurement across vast geospatial areas over time. Additionally, our analysis provides insights into sustainable management practices on rangelands that not only enhance productivity but also accelerate soil carbon sequestration. This creates a mutually beneficial scenario for both farmers and the environment. All these methods are seamlessly integrated into an accurate and cost-effective tool for remotely measuring soil and vegetation carbon levels in Australian rangelands.
We have built a Sydney Real-Time Digital Twin Platform, aiming at being the second generation of Digital Twin models for smart cities integrating multiple data sources such as: 3D city model with top layers including real-time public transport movement, transport simulation for incident scenario management in real-time, water pipes layout and IoT sensing data transmission, air quality and car parking real-time transmission, etc.
Digital Twins are powerful tools for operation planning, incident management and asset management. While most Digital Twins worldwide are static (operating at maximum level 2 of maturity), our Sydney Digital Twin model provides an uplift in its power of real-time analytics and deep learning prediction, which raises its functionality to Level 4 of maturity. To the best of our knowledge, this is the first real-time and AI-powered Digital Twin of an Australian city. Our approach represents a powerful step ahead of integrating artificial intelligence with spatial and temporal modelling to improve decision-making and optimise the cities we live in. The innovative aspect of our Sydney Digital Twin consists in its unique combination of 2D, 3D spatial modelling, real-time train movement information, water pipe and IoT sensing information, incident management simulation modelling as well as air quality real-time monitoring.
UTS and Sydney Trains have successfully applied advanced machine learning techniques to develop a timetable robustness evaluation model. The model can assess timetables and response plans to ensure that that timetables/response plans are operationally robust and resilient. The outcome of this application of the intelligent timetable evaluation technology significantly reduces delay-caused losses and increases the operation efficiency, enables the train operating system to meet performance metrics and recover from incidents.
The outcome of this application of the intelligent timetable evaluation technology significantly reduces delay-caused losses and increases the operation efficiency, enables the train operating system to meet performance metrics and recover from incidents. This work shows train operating companies that they can produce highly detailed and granular information to develop targeted timetable design and real-time scheduling strategies. This translates to improved railway network reliability and service to customers, and a reduced cost to serve. The proposed model is a generic model that can be easily applied to other traffic scenes with subtle refinements.
The population of immigrants changes residential distribution and dwelling needs drastically. However, the published census data cannot catch the change, temporally or spatially. The census data, published by Australia of Beare Statistics, can show the population by region every five years. It does not give information for further granularities, so when we need to know the situation of an arbitrary region, we cannot apply the data for precise estimation. Furthermore, the region setting changes yearly, creating more data inconsistency between regions in different years. All these issues hinder the precise analysis and decisions on a development plan.
With machine learning, though, we can interpolate the population or other census indicators for any customised regions, including prediction cross-over regions with known populations or indicators nearby and forecasts for the future. Our web services (as shown in the figure below) provide an interactive function for the user to crop an any-shape polygon, and then we will show up all the related information designed for the cropped region. These can be the population number, distribution as a heat map, the existing dwells, and expected maximum capacity for households and individuals. We can offer the correlation between population and housing to indicate the housing pressure in the region of interest. This information is highly precise compared to existing ABS data and most in-the-market population products.
In 2020, farmers in New Zealand produced about 622,550 metric tonnes of kiwi fruit3 that's more than 20,000 40-foot shipping containers filled to the brim with this sharp, sweet, strange-looking fruit. But, while the fruit itself is abundant, inaccurate forecasts about the future yield and crop size of individual harvests come at significant financial cost to the global kiwifruit industry.
In partnership with kiwifruit marketing company Zespri International, Australian agritech start-up The Yield Technology Solutions was urgently seeking a solution â and they had an inkling that data science might hold the key.
Maintaining water quality throughout the distribution system to the customers tap stands as one of the most formidable challenges faced by water utilities. The increasing unpredictability of droughts and shifts in raw water quality demands innovative solutions to ensure consistent, high-quality water delivery that meets customer needs and regulatory standards. Recognizing this critical need, the Macarthur Water Filtration Plant System Optimisation research project was initiated through a collaborative effort among the UTS Data Science Institute, Sydney Water Corporation, and TRILITY Pty Ltd. This groundbreaking project seeks to identify and implement opportunities to optimize process control and monitoring feedback, resulting in greater consistency in total chlorine residual across the water distribution network.
The UTS Data Science Institute, working closely with Sydney Water and TRILITY, has pioneered a data-driven solution designed to predict total chlorine levels within the Macarthur Delivery System. This innovative solution encompasses several key modules: network topology modelling, estimation of water travel time through the trunk network and distribution system, water quality modelling, and total chlorine prediction. By integrating these components, a comprehensive prediction model for water quality has been developed, enabling accurate and quantitative predictions of total chlorine residuals across the entire reticulation network downstream of the reservoirs.
In the realm of water management, the silent challenge of leaks and breaks echoes across global water networks, disrupting communities and causing immense water loss. Sydney Water, in a groundbreaking collaboration with the UTS Data Science Institute and UTS Robotics Institute, has embarked on a transformative journey to tackle this challenge head-on.
Over the past two years, Sydney Water and DSI have demonstrated world-leading capabilities by adapting acoustic sensing to target non-surfacing leaks, some persisting for five to ten years. The collaboration spans 270 semi-permanent and a variety of lift-and-shift acoustic sensors deployed across seven CBD areas and seven pressure zones, bolstering Sydney Water's leak prevention efforts and minimizing customer disruption and water loss.
In an era of escalating climate uncertainties, extreme weather events wreak havoc on water quality in catchments and reservoirs, impacting the operations of water filtration plants. Sydney Water Corporation, WaterNSW, Melbourne Water Corporation, and TRILITY Pty Ltd faced significant hurdles in adapting to dynamic changes in water quality brought on by heavy rainfall, floods, droughts, storms, extreme temperatures, and bushfires. The conventional approaches struggled to provide real-time insights, leading to lower filter performances and compromised production rates. The urgent need was clear: a solution to quantify the impact of climate change-induced extreme events on water quality in real-time.
The collaborative Research and Development initiative, spearheaded by UTS Data Science Institute, brought together industry leaders to confront this challenge. The project's primary goal was to leverage advanced machine learning methods to build predictive water catchment models. The focus areas were the Macarthur and Nepean water filtration plants in NSW, along with the Upper Yarra Reservoir and Tarago Reservoir catchments in Victoria. The proposed solution involved a robust spatial-temporal machine learning approach, incorporating weather and upstream effects to predict raw water colour, natural organic matter, and turbidity.
Sydney Water, managing over 790km of sewer pressure mains, faced a critical challenge: predicting and preventing failures in this aging infrastructure. In response, they partnered with DSI team to develop an innovative, data-driven solution. The heart of this project was a sophisticated machine learning model using XGBoost technology. This model analysed a vast array of factors, including pipe materials, soil conditions, chemical dosing, and flow rates, to forecast potential failures across the entire network.
This work in translating cutting-edge machine learning techniques to address sewer pressure main failures, a critical issue for water utilities worldwide. The innovative approach integrates data-driven models with forensic engineering and robotic sensing, creating a proactive sewer management system. This method is particularly noteworthy as it represents the first global application of ensemble learning techniques to predict failures in sewer pressure mains, effectively handling the challenge of imbalanced data with sparse failure records. By developing user-friendly interfaces and tailoring solutions to meet specific utility needs, they've enabled Sydney Water to identify and address root causes of failures across their 790km of sewer pressure mains. This work has significant implications for minimizing service disruptions, reducing repair costs, and mitigating environmental hazards. The UTS team's approach not only enhances long-term renewals planning but also provides actionable insights for targeted maintenance, setting a new standard in proactive asset management for water utilities globally.
In the labyrinthine depths beneath the bustling streets of Sydney, a silent battle was being waged against an unseen enemy sewer corrosion. Sydney Water, faced with the challenge of maintaining and safeguarding its extensive network of gravity concrete sewers spanning approximately 823 kilometers, sought a revolutionary solution to combat the widespread and costly issue of corrosion.
Enter a groundbreaking collaboration between Sydney Water and the University of Technology Sydney (UTS), where cutting-edge technology and innovative minds converged to develop a state-of-the-art system. Their mission: to predict and address corrosion hotspots using a combination of machine learning models and robotic systems.
Smart parking solutions have become one of priorities in smart city projects. The major benefits of smart parking include decreasing traffic congestion, reducing energy consumption and reducing car emissions. With over 6.1 million of tourists to the Mornington Peninsula Shire (MPS) annually, MPS Council is facing the increasing challenges to provide both visitors and residents with a quality and fair parking experience. To meet the challenges of increasing demand on parking and effectively managing parking in townships, MPS Council has been running a Smart Parking trial in Rye from January 2020 to June 2020 and the second trial in Mornington from December 2020 to June 2021. Over 700 in-ground and camera car parking bay sensors were installed in Rye and 100 in-ground sensors were installed in Mornington respectively.
During the trial periods, we have been working with the MPS Council on a data analytics project with the objectives to discover parking behaviour patterns and predict the impact of parking-sensor-based parking enforcement. The occupancy and overstay patterns discovered in the project are helpful for the Council to understand the parking behaviours and improve the efficiency of parking enforcement in the trial areas. The prediction of impact of parking-sensor-based parking enforcement helps the Council to plan the further implementation of smart parking in other townships.
Trains are an important means of transportation which serve millions of residents in mega cities. In order to keep the operation running smoothly, the performance of trains, e.g., punctuality and fuel efficiency, need to be reasonably predicted beforehand. Then the operator can carry out timely adjustments on train operation, for example, changing timetable to prevent further delays, planning maintenance to reduce faults, and giving extra time for overcrowded stations, based on the insightful predictions we provided. Modelling such operations, traditionally, is barely possible due to the large varieties of factors, such as complicated train network, unexpected incidents, human activities, etc. Therefore, the outcome of this project aims to build the platform to continuously analyse the train performance and furthermore give reasonable suggestions to the operator by agilely aggregating massive data source.
The solution is built on innovative machine learning techniques including retrieval techniques, ensemble models, monitoring system, and continuous evaluation. The innovated platform can aggregate different types of data sources in an agile manner with minor data format adjustments. It has involved more than 100 factors, from days to seconds, and it will be providing more insights for any hypothesis suggested by experts or knowledge discovered by additional data.
Trains, as an primary transportation mode, play an increasingly important role in keeping a city moving and achieving urban sustainability. The train timetable should be evaluated regarding its punctuality, reliability and robustness before its implementation. However, this is a challenging task due to the train network complexity and patronage fluctuations. This project utilises a wealth of historical train performance, customer and incident data to evaluate a timetable and help create more robust timetables.
We solved the problem by integrating comprehensive data sources, identifying inspiring insights and patterns and developing advanced evaluation models by using cutting-edge machine leaning technique. The solution is based on innovative analytical methods or machine learning techniques, including deep learning, ensemble learning and computer vision. Various breakthroughs from prediction modelling, risk estimation, and complexity learning are presented. The outcomes of this project enable our client evaluate a timetable effectively in several minutes and the evaluation results and insights are presented in a dynamic and interactive manner. These outcomes could help the operation and timetable design teams create more robust timetables.
With the increasing demand for public transportation due to congested highways, trains have become one of the most viable alternatives, especially for daily commuting. While transit agencies are excited with the increasing ridership, they are also challenged with a higher volume of passenger flow and longer queuing lines at the existing stations. Large scale renovation of rail stations to cater for growing passenger demand has been taking place in various sites all over the world. Railway passenger flow data including the arrival and departure of each train, the number of passengers getting on and off at each stop and the number of transferring people in each station can be used for planning facilities, train scheduling and other planning. It is very important to schedule train timetables properly so that they meet the increasing passengers demand.
To improve the current situation and plan for the future, we have developed real-time object detection and tracking models based upon advanced computer vision techniques with the help of installed cameras in the stations. The solutions include using advanced deep learning based object detection technology to recognize trains in each frame (image); tracking the passengers flow on the platforms in continuous frames (images); tracking the passengers stepping on and off the escalator in continuous frames (images); tracking the actual train wheel stop/start time in continuous frames (images). Those data-driven solutions help the train controllers and managers to better understand the passenger demand at a given station and better schedule the future train timetables.
Original Equipment Manufactures (OEMS) of electronic products often offer service warranty to their customers. To maintain high-level customer satisfaction, spare parts are required to be stocked at a sufficient level to support the service. As the suppliers may stop producing certain models due to technological/economic reasons, it is important to order one last quantity of spare parts, known as last time buy (LTB), to mitigate the risk of stock shortage. Spare parts by LTB play a significant role in inventory maintenance workload.
This project is a collaboration between a prominent electronic producer and the team, which endeavours to reduce the workload of inventory maintenance. As an initial step, we have built a visualisation tool that closely monitors the engineering KPIs based on producer's install base and failure data, by utilising our machine learning capability. Currently we are developing predictive models that take into account part failure, install base, stock and warranty data, for forecasting the quantity of LTB. The predictive models are expected to provide failure predictions for parts, and hence optimize the stock management.
Routine inspection of rail network is essential for the safety and efficient operation of trains. Train operators usually conduct inspections of the whole network using the inspection vehicle, capturing tens of millions of images of tracks and surrounding environment. These images will be manually reviewed by track inspectors to find out any defects, which requires years of domain expertise and training. With the building of new rails and aging of existing rails, it is increasingly challenging to manage the workload of inspectors while keeping the high safety standard of the track inspection process.
Our team developed deep learning models to detect regions of interests for suspicious defects. The models are trained using labelled defect images and normal inspection images, and able to detect missing clips/bolts from inspection images with high accuracy. As a result, train operators could extend the range of inspection that previously overlooked due to limited resources, assist inspectors in the decision making process, and improve the efficiency of the inspection process while maintaining high maintaining standard.
Understanding customers expectation on services is the key for broadband service providers. For new service roll-out, service providers need to allocate suitable amount of workforce and resources in appropriate time and location. For existing service regions, service providers aim to maintain top-tier customer service and sustainable revenue. The predictions of activation demand and utility rate could be very challenging due to the involvement of multiple interacting factors such as service types and local demographics.
Our team designed innovative machine learning model for customers demand forecasting in fine-grained spatial and temporal dimensions. The model can handle heterogeneous data, and offers great scalability for large-scale data. The techniques developed in this project could be applied to other customer-centered services. It provides data-driven support for decision making process, which helps the service provider to better manage the life cycle of service roll-out.
Smart parking management based on sensors and real-time data can save drivers' time in finding parking spaces, optimise the usage of parking spaces and support operational staffs to easily monitor and manage parking resource. However, installing sensors at all parking spaces will be expensive and inefficient. This project aims to develop a prediction model for parking space occupancy rates using machine learning techniques. Our solution learns the patterns via historical occupancy records and estimates the occupancy for those spaces without sensors.
Our team has developed an innovative solution to predict occupancy rate of parking spaces based on sensor and transaction records. Our model considered various types of features to learn the patterns of parking behaviour, including location and regulation information, historical sensor parking events, and parking payments. The model can output accurate occupancy rate for parking spaces without sensors at any time.
Water utilities often manages water supply and demand for millions of residential and non-residential properties. It is paramount to guarantee continuous supply, water quality and pressure, as well as to minimise operational costs. In this Intelligent Network Optimisation project, we developed new machine learning models for water demand forecasting, water quality modelling and dosing optimisation, which effectively predict water demand in the near future and define optimal strategies for chlorination. New machine learning models are also being built to optimise energy usage, by balancing pumping regimes and costs while meeting water demand. All these models will work together to optimise water supply network.
We have developed a cash flow forecasting approach based on machine learning techniques. This approach can provide an overview of the company's cash position in a short term in the future. We use machine learning techniques to forecast a company's transactions in the next 8 weeks based on the historical patterns of cash inflows and cash outflows. The cash flow modelling has been divided into three components and we have provided solutions for each component: 1) cash -- predict when and how much cash sales and cash expenses will be received or paid; 2) transfer -- predict when and how much transfer within the company will occur; 3) invoice and bill: predict when payments for invoices and bills will be received or paid.
The cash flow of a company and their bank accounts can be computed by aggregating the predict results for these three components. The outcomes can support businesses to foresee how much cash they will have in their accounts and make informed decisions based on these information.
Sewer corrosion is a serious issue in wastewater systems for Water utilities. The concentration of H2S is a key factor leading to sewer corrosion, but it can be alleviated by dosing of Iron (Ferrous) salts and other chemicals. A chemical dosing profile should be specified to determine the dosing rate based on many dynamic factors, e.g., H2S level, flow volume. In order to improve the dosing effect and save chemicals, the chemical dosing profiles for each Chemical Dosing Unit (CDU) should be optimised according to the dynamic factors.
This project developed a smart toolkit to facilitate the optimization process. The toolkit consists of three major modules, i.e., sewer dosing analysis, H2S estimation and sewer corrosion prediction. It enhances the capability of the Sydney Water teams by improving their performance and investment in controlling H2S, managing corrosion and odour in concrete sewers. The target users of the toolkit are the operators in Water utilities.
There are approximately 800 jack arches underneath the bus lane of the Sydney Harbour Bridge. The jack arches are very difficult to access and are typically inspected at two year intervals according to standard visual inspection practices. RMS required a way to continuously monitor the structural condition of each of the jack arch supports and alert the asset manager and bridge inspector if any issue is detected. An inspection can then be scheduled and preventative maintenance are carried out without disrupting road users.
We have designed and developed a monitoring system including data acquisition, data analytics and a user dashboard to monitor each of the jack arch components in real time using machine learning techniques. Each jack arch has been instrumented with three low-cost tri-axial accelerometers connected to a smart node, resulting in about 2,400 sensors in the system. The acceleration data have been used to train a machine learning model and detect any deviation from the model. This SHM system was awarded "The Most Practical SHM Solutions for Civil / Mechanical Systems Award" at IWSHM - the 10th International Workshop on SHM in 2015.
We have collaborated with a variety of utilities on asset failure predictions since 2011, currently the assets include supply water mains, sewers, and gas pipes. Among the projects, we developed technologies to predict the risk of these assets. The prediction is used for cost-effective maintenance to save cost, reduce uncertainty for asset network, and enhancing the custom experience.
We developed a data-driven solution for predictive maintenance of assets. It is analytics as a service platform that can derive insights from operational data, signal future failure risks, as well as provide decision support for asset owners. It can identify the causal factors of asset failures, prioritize high-risk pipes for renewal and then systematically reduce failure risk over time. The platform is now applied into problems including supply water main failure prediction, sewer choke prediction, and gas pipe leakage prediction. Near doubling of consequence cost saving can be achieved based on the case studies. It is able to recommend high-risk assets, based on failure probabilities, consequence costs, renewal costs, budget constraints, and geographical constraints. The improvement of current prediction results to drive better tactical decisions.