{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:38:33Z","timestamp":1761176313987,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>The monitoring and regulation of industrial emissions are critical to ensuring compliance with environmental standards. While many toxic gases, such as Nitrogen Oxides (NOx), exhibit more predictable behavior, Carbon Monoxide (CO) emissions from gas turbines pose a significant challenge due to their complex, nonlinear dependence on operational parameters, making accurate prediction particularly difficult. Differently from Continuous Emission Monitoring Systems (CEMS) that relies on physical sensors, Predictive Emission Monitoring Systems (PEMS) offer a cost-effective and flexible alternative by leveraging models to dynamically estimate emissions. However, challenges such as model adaptability, distributional shifts, and the need for continuous retraining hinder their reliability. This paper presents a novel Conformal Adaptive Learning approach that integrates Active Learning (AL) and Conformal Prediction (CP) to enhance the efficiency and robustness of PEMS for gas turbines in predicting CO emissions. AL enables the model to iteratively select the most informative data points for labeling, thereby reducing the burden of extensive data collection, while CP provides rigorous uncertainty quantification through prediction intervals. By leveraging CP-based uncertainty estimates to guide AL, we introduce an adaptive re-calibration strategy that dynamically refines the model by prioritizing uncertain predictions for targeted retraining. Our experimental results from real-world gas turbine data, demonstrate highly accurate CO emissions prediction while minimizing retraining sessions. The proposed framework represents an advance in AI-driven industrial monitoring, offering a scalable and more cost-efficient solution that aligns with Industry 4.0 objectives while ensuring regulatory compliance.<\/jats:p>","DOI":"10.3233\/faia251465","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:03:16Z","timestamp":1761127396000},"source":"Crossref","is-referenced-by-count":0,"title":["Efficient Emission Monitoring in Gas Turbines: A Conformal Adaptive Learning Approach"],"prefix":"10.3233","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8233-6334","authenticated-orcid":false,"given":"David Alexander","family":"Moe","sequence":"first","affiliation":[{"name":"Catholic University of the Sacred Heart, Brescia, Italy"},{"name":"Baker Hughes, Florence, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1688-6961","authenticated-orcid":false,"given":"Alberto","family":"Rossi","sequence":"additional","affiliation":[{"name":"Baker Hughes, Florence, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6095-3407","authenticated-orcid":false,"given":"Leonardo","family":"Pulga","sequence":"additional","affiliation":[{"name":"Baker Hughes, Florence, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7005-404X","authenticated-orcid":false,"given":"Laure","family":"Barriere","sequence":"additional","affiliation":[{"name":"Baker Hughes, Florence, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carmine","family":"Allegorico","sequence":"additional","affiliation":[{"name":"Baker Hughes, Florence, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA251465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:03:17Z","timestamp":1761127397000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA251465"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia251465","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}