Building trust in AI for HSE

Artificial Intelligence (AI) techniques can help enhance Health, Safety, and Environment (HSE) operations. However, building trust is an important aspect of this system. A new, novel study explores this topic.

How AI can help HSE operations?

AI is the ability of machines to perform tasks that normally require human intelligence, such as learning, reasoning, and decision-making. Natural Language Processing (NLP) is a branch of AI that deals with the analysis and generation of human language, either in text or speech form. By using NLP on HSE data, such as management observations, work orders, audits, and near misses, the oil and gas industry can achieve the following benefits:

• Quickly identify hidden trends and patterns in the data that can indicate potential hazards or risks.
• Uncover and quantify textual data that can provide valuable insights into the HSE performance and behaviour of the workforce and management.
• Create a smart system that can monitor the operational conditions and performance of equipment and systems and alert the users of any issues or failures that can lead to accidents or incidents.
• Target the resources, such as safety coaches, more effectively to prevent adverse events, protect vital equipment, and potentially save lives.

However, for these to be implemented, it is imperative to establish trust in the AI system among the users. Especially during data collection, system roll-outs, and user adoption.

How can we build trust in AI for HSE?

Trust is an important factor for the successful adoption and implementation of AI for HSE. Trust means that the users have confidence in the AI system’s design, development, deployment, operation, evaluation, and improvement. For this to happen, users need to understand how the AI system works, why it does what it does, how confident it is about its outcomes, and how responsible it is for its consequences or impacts.

Trust in AI for HSE: A new and novel study

A study was carried out as part of a pilot project with Petroleum Development Oman (PDO) for IHTIMAM, their behaviour-based safety system. It aims to create a safety partnership between the workforce and management that continually focuses everyone’s attention and actions on their own and others’ daily safety behaviour. You can read more about IHTIMAM here.

The project involved implementing a system that allowed for easy collection, structuring, and pre-processing of data associated with management observations, and developing and implementing a robust set of AI tools that allowed the users to enhance their existing workflows to better identify, quantify, and address HSE risk.

It resulted in creating a new set of leading indicators for HSE awareness, such as risk scores, risk categories, risk drivers, and risk mitigation actions.

The project demonstrates a novel approach to leverage user adoption and use cases in terms of both method and application. Using AI for HSE data collection and analysis can greatly improve HSE operations in the oil and gas industry, but it also requires building trust in the AI system among the users.

Members at the Society of Petroleum Engineers (SPE) can download the complete paper from their Health, Safety, Environment, and Sustainability Technical Discipline page for free from 31 August until 13 September.

Sources

Trust in AI for HSE by HSE Now – JPT – Society of Petroleum Engineers, 29th August, 2023.

Trust in AI for HSE by OnePetro, 31st October, 2022.