Cloud-Based AI System Achieves 90% Accuracy in Detecting Sewer Blockages to Reduce River Pollution

In this post:

  • Collaborative effort achieves 90% accuracy in detecting sewer blockages using cloud-based AI, promising reduced river pollution.
  • The ‘Pollution Incident Reduction Plan’ aims to cut pollution incidents by 50% by 2025 through early intervention.
  • Automated AI monitoring and detection enhance environmental protection, showcasing the potential of technology to safeguard watercourses.

A remarkable collaboration between the University of Sheffield, Yorkshire Water, and Siemens has resulted in a cloud-based artificial intelligence (AI) system that boasts nearly 90% accuracy in detecting sewer blockages. This groundbreaking development promises to play a pivotal role in reducing river pollution caused by sewer overflow incidents.

Tackling pollution with a strategic plan

The AI system’s development aligns with the ambitious ‘Pollution Incident Reduction Plan,’ which aims to cut pollution incidents by a substantial 50% before 2025. The plan prioritizes early intervention to prevent pollution stemming from combined sewer overflows (CSOs). These CSOs serve as relief valves for sewer systems, releasing excess water into nearby water bodies during heavy rainfall to prevent downstream flooding. However, when blockages or other issues disrupt the system, pollution incidents can occur unnecessarily.

The collaborative effort relies on advanced sensor technology to monitor water depth in CSOs and various parts of the sewer network in real-time. Given the extensive number of sensors involved, manual analysis becomes unfeasible, necessitating the implementation of an automated AI system. Developed in partnership with Siemens, the AI-based solution is known as the Siemens Water (SIWA) Blockage Predictor.

Predictive power of AI

The SIWA Blockage Predictor leverages AI to predict water depths by analyzing rainfall data and comparing it to actual measurements through a sophisticated Fuzzy Logic (FL) algorithm. Whenever unexpectedly high water depths are detected, an alert is promptly generated for water utilities, enabling them to take preventive measures and avoid pollution incidents. The primary goal is to identify potential blockages in their early stages to ensure they are addressed before causing pollution.

A newly published peer-reviewed journal article assesses the SIWA Blockage Predictor’s performance over both a two-year ‘historic’ period and a six-month ‘live’ period. The article also conducts a comparative analysis against the previous analytics solution. The results are nothing short of impressive, with the AI system correctly identifying 88.4% of confirmed issues across the full dataset, compared to the previous solution’s paltry 26.6% accuracy rate. The full article, titled “Cloud-Based Artificial Intelligence Analytics to Assess Combined Sewer Overflow Performance,” is available in the Journal of Water Resources Planning and Management.

Future prospects for environmental protection

Dr. Will Shepherd, Principal Investigator from the University of Sheffield’s Department of Civil and Structural Engineering, emphasized the importance of this innovation in maintaining environmentally friendly sewer systems. He highlighted that sewer networks were not originally designed to handle heavy rainfall and that CSOs serve as vital relief valves to prevent flooding. Driven by a commitment to reducing pollution incidents, the collaborative effort focuses on identifying and addressing blockages before they lead to river and watercourse contamination.

Professor Joby Boxall, Professor of Water Infrastructure Engineering in the University of Sheffield’s Department Civil and Structural Engineering, emphasized the significance of a collaborative approach in achieving success. He stressed the importance of recognizing and respecting the unique needs and ambitions of each partner while building and maintaining a high level of trust.

Dr. Stephen Mounce, Director of Mounce HydroSmart, expressed excitement about how this project showcases the transformation of AI and data analytics from research prototypes in early-stage projects to mature, generic solutions deployed on cloud-based platforms. He noted the real-world deployment of the system to over 2,000 assets at Yorkshire Water.

Dr. John Gaffney, Product Owner of SIWA Blockage Predictor, hailed this collaboration as an exemplary case of a technology company taking high Technology Readiness Level (TRL) research from a university, productizing it, and demonstrating its value through peer-reviewed science to an end user. He underscored the product’s vital role in safeguarding watercourses, making the project particularly rewarding.

The collaboration between the University of Sheffield, Yorkshire Water, and Siemens has yielded a remarkable achievement in AI-driven environmental protection. The cloud-based AI system’s ability to detect sewer blockages with nearly 90% accuracy offers a promising solution to reduce river pollution. As technology continues to evolve, innovative solutions like the SIWA Blockage Predictor demonstrate AI’s potential to play a pivotal role in safeguarding our natural environment. With a firm commitment to early intervention and a reduction in pollution incidents, this collaborative effort offers hope for cleaner, healthier waterways in the future.

Disclaimer. The information provided is not trading advice. Cryptopolitan.com holds no liability for any investments made based on the information provided on this page. We strongly recommend independent research and/or consultation with a qualified professional before making any investment decisions.

Share link:

Most read

Loading Most Read articles...

Stay on top of crypto news, get daily updates in your inbox

Related News

Subscribe to CryptoPolitan