OA20235. See the signals - a route to using AI to spot leading indicators of environments incidents
Salvato in:
| Pubblicato in: | European Journal of Public Health vol. 35, no. Supplement_5 (Nov 2025) |
|---|---|
| Autore principale: | |
| Pubblicazione: |
Oxford University Press
|
| Soggetti: | |
| Accesso online: | Citation/Abstract Full Text - PDF |
| Tags: |
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3271850963 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 1101-1262 | ||
| 022 | |a 1464-360X | ||
| 024 | 7 | |a 10.1093/eurpub/ckaf165.037 |2 doi | |
| 035 | |a 3271850963 | ||
| 045 | 2 | |b d20251101 |b d20251130 | |
| 084 | |a 53202 |2 nlm | ||
| 100 | 1 | |a Leith, D |u Technology COMET, Aberdeen, United Kingdom | |
| 245 | 1 | |a OA20235. See the signals - a route to using AI to spot leading indicators of environments incidents | |
| 260 | |b Oxford University Press |c Nov 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Issue/Problem Organisations in high risk industries, such as water supply and wastewater management, gather large volumes of structured and unstructured data and information about incidents concerning their assets. This ranges from customer reports of issues, through internal observations and near miss reports, to full incident reports. Together this represents a considerable resource to assist in decision making and understanding past, present and future risk. Description Such organisations struggle to draw these sources together and extract meaningful intelligence. This can be due to lack of structure, or a common data structure; or systems unable to communicate together; or a lack of tools to analyse the data to extract actionable intelligence; or poor quality data and information. Artificial intelligence (AI) tools, in particular natural language processing (NLP) and machine learning (ML), present an opportunity to make sense of this information allowing hypotheses to be tested, tracking trends, and pre-empting future incidents. The ultimate goal to achieve is therefore enhance decision making to better target investment and interventions. Results This paper outlines development using the COMET® AI module to ingest large data sources to learn and train models which turn data into actionable intelligence. This approach is illustrated with a case study in the wastewater industry. With the output from this tool an organisation is able to better make decisions on a number of fronts: a) Decide on most appropriate interventions, for example training for maintenance crews; improvements to operating procedures; etc. b) Decide on best targeted investment spend, for example spending capex on improvements to cellar layouts thus preventing future risk rather than on dealing with the aftermath of floods. c) Decide on optimised resource allocation, for example deploying people on tasks which make a difference to reducing future risk. d)Decide on pre-emptive actions, for example tackling latent factors which are increasing over time and likely to become future incident root causes. e) ecide on improvements to data gathering, for example structuring the way in which in incident data is recorded in a common taxonomy. Lessons The work described in this paper has demonstrated that it is possible for the wastewater industry to harness AI technology to analyse tens of thousands of unstructured and structured records relating to environmental incidents to extract unseen conclusions from the patterns that emerge in natural language. Findings can then be displayed, suggesting areas for improvement, and enabling professionals to be more proactive than reactive. Key messages • While it has been demonstrated that such a tool can work with unstructured data, organisations still need to drive to improve the quality of the data which they gather to maximise the benefits which can be derived from using AI, and so improve decision making on interventions and investment. Topic Artificial intelligence, data analytics, HSE data. | |
| 653 | |a Intervention | ||
| 653 | |a Classification | ||
| 653 | |a Machine learning | ||
| 653 | |a Future | ||
| 653 | |a Resource allocation | ||
| 653 | |a Taxonomy | ||
| 653 | |a Crews | ||
| 653 | |a Wastewater | ||
| 653 | |a Data quality | ||
| 653 | |a Risk | ||
| 653 | |a Maintenance training | ||
| 653 | |a Intelligence gathering | ||
| 653 | |a Artificial intelligence | ||
| 653 | |a Wastewater management | ||
| 653 | |a Organizations | ||
| 653 | |a Expenditures | ||
| 653 | |a Decision making | ||
| 653 | |a Data structures | ||
| 653 | |a Investments | ||
| 653 | |a Case studies | ||
| 653 | |a High risk | ||
| 653 | |a Data | ||
| 653 | |a Environmental indicators | ||
| 653 | |a Tracking | ||
| 653 | |a Water supply | ||
| 653 | |a Floods | ||
| 653 | |a Information | ||
| 653 | |a Data processing | ||
| 653 | |a Water resources management | ||
| 653 | |a Reports | ||
| 653 | |a Natural language | ||
| 653 | |a Health risks | ||
| 653 | |a Natural language processing | ||
| 653 | |a Unstructured data | ||
| 653 | |a Economic | ||
| 773 | 0 | |t European Journal of Public Health |g vol. 35, no. Supplement_5 (Nov 2025) | |
| 786 | 0 | |d ProQuest |t ABI/INFORM Global | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3271850963/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3271850963/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |