When considering AI applications in the energy sector, use cases that come to mind normally include predictive analytics, reporting, and the automation of back-office processes and operations. Modern forecasting models now rely on machine learning (ML) techniques, while Generative AI (GenAI) supports middle-office tasks and market research. Natural Language Processing (NLP) applications also add value across front, middle, and back-office functions. Further use cases would include interfacing and user trainings. But I was excited to find out that there are more tasks for AI to be considered. According to Financial Times publication https://emea01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fon.ft.com%2F4adsq1p&data=05%7C02%7C%7C5ffb169c83234cb9eac508dcff23e713%7C84df9e7fe9f640afb435aaaaaaaaaaaa%7C1%7C0%7C638665776868003073%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=1ufvFNy%2BOcafmiOpYCE6vETdB%2BQQTPNiJsU9kfY4UBs%3D&reserved=0 leading energy companies are deploying distinct AI applications to address industry-specific challenges. One example is in emissions monitoring. Shell, for instance, has developed an AI tool to track methane emissions, which, as Dan Jeavons, Shell’s vice-president of computational science and digital innovation, explains, “uses wind and concentration data to help us understand the origin and quantity released.” Jeavons notes that AI will optimize energy system efficiency by “reducing the amount of power needed to be generated” and could lead to the creation of “entirely new low carbon-footprint energy systems,” while enabling suppliers to monitor greenhouse gas sinks. AI is also expected to enhance the cost-effectiveness and precision… continue reading