{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T18:37:19Z","timestamp":1792780639846,"version":"4.5.0"},"reference-count":20,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T00:00:00Z","timestamp":1792713600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Institute of Forest Science","award":["FP0700-2022-01-2026"],"award-info":[{"award-number":["FP0700-2022-01-2026"]}],"id":[{"id":"https:\/\/ror.org\/039hpv827","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    Thermally delayed biomass-boiler systems exhibit heterogeneous temporal responses that complicate forecasting and operational warning. This study analysed long-term field data from a biomass-fired boiler system to characterise thermal-response lags and evaluate multi-horizon forecasting of the P1 thermal-storage-tank temperature at 60-, 120-, and 180-min horizons. Robust cross-correlation analysis showed statistically detectable but weak associations between P1 temperature and the combustion-related operational inputs, while daily lag estimates exhibited broad and heterogeneous distributions, indicating that the system could not be represented by a single deterministic response time. Benchmark comparison showed that increasing model complexity did not necessarily improve forecasting performance. The Linear AR model achieved the lowest test RMSE and highest R\n                    <jats:sup>2<\/jats:sup>\n                    at all three horizons, with RMSE values of 1.3774, 2.1605, and 2.6182 \u00b0C and R\n                    <jats:sup>2<\/jats:sup>\n                    values of 0.7809, 0.4616, and 0.2104 at 60, 120, and 180 min, respectively. Lag coverage increased with forecasting horizon, whereas predictive accuracy progressively decreased, demonstrating a trade-off between pointwise accuracy and coverage of delayed thermal responses rather than a universally optimal horizon. Retrospective out-of-band warning analysis further showed that XGBoost recall decreased from 0.5343 at 60 min to 0.1761 at 120 min and 0.0538 at 180 min, while specificity increased from 0.9095 to 0.9546 and 0.9854, respectively. These results indicate that longer-horizon forecasts became increasingly conservative and detected progressively fewer future out-of-band states. Overall, the findings demonstrate that simple temporal models remain highly competitive for this strongly persistent thermal system and that multi-horizon forecasts should be interpreted as predictive risk indicators rather than evidence of causal improvements in boiler control or operational performance.\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0361121","type":"journal-article","created":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T17:38:03Z","timestamp":1792777083000},"page":"e0361121","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-horizon forecasting for decision support in a thermally delayed biomass-fired boiler system"],"prefix":"10.1371","volume":"21","author":[{"given":"Sunyong","family":"Park","sequence":"first","affiliation":[{"name":"National Institute of Forest Science","place":["Dongdaemungu, Seoul, Republic of Korea"],"department":["Forest Industrial Materials Division"]},{"name":"Kangwon National University","place":["Chuncheon, Republic of Korea"],"department":["Department of Biosystems Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiwook","family":"Yang","sequence":"additional","affiliation":[{"name":"National Institute of Forest Science","place":["Dongdaemungu, Seoul, Republic of Korea"],"department":["Forest Industrial Materials Division"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sungyeol","family":"Kim","sequence":"additional","affiliation":[{"name":"National Institute of Forest Science","place":["Dongdaemungu, Seoul, Republic of Korea"],"department":["Forest Industrial Materials Division"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyojung","family":"Hwang","sequence":"additional","affiliation":[{"name":"National Institute of Forest Science","place":["Dongdaemungu, Seoul, Republic of Korea"],"department":["Forest Industrial Materials Division"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"JaeJung","family":"Lee","sequence":"additional","affiliation":[{"name":"National Institute of Forest Science","place":["Dongdaemungu, Seoul, Republic of Korea"],"department":["Forest Industrial Materials Division"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1804-7099","authenticated-orcid":true,"given":"Sunhwa","family":"Ryu","sequence":"additional","affiliation":[{"name":"National Institute of Forest Science","place":["Dongdaemungu, Seoul, Republic of Korea"],"department":["Forest Industrial Materials Division"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,23]]},"reference":[{"issue":"10","key":"pone.0361121.ref001","doi-asserted-by":"crossref","first-page":"1153","DOI":"10.1016\/S0967-0661(02)00060-6","article-title":"Time delay integrating systems: a challenge for process control industries. A practical solution","volume":"10","author":"M Huzmezan","year":"2002","journal-title":"Control Engineering Practice"},{"key":"pone.0361121.ref002","article-title":"Research on thermal inertia in CFB boilers: mechanisms, effects, and a novel retrofit approach","volume":"274","author":"X Hu","year":"2025","journal-title":"Appl Therm Eng"},{"key":"pone.0361121.ref003","doi-asserted-by":"crossref","first-page":"3936","DOI":"10.1021\/acs.iecr.0c06278","article-title":"Dynamic modeling of the reactive side in large-scale fluidized bed boilers","volume":"60","author":"GM Castilla","year":"2021","journal-title":"Ind Eng Chem Res"},{"issue":"2","key":"pone.0361121.ref004","doi-asserted-by":"crossref","first-page":"202","DOI":"10.3390\/e24020202","article-title":"0D Dynamic Modeling and Experimental Characterization of a Biomass Boiler with Mass and Energy Balance","volume":"24","author":"F Mameri","year":"2022","journal-title":"Entropy (Basel)"},{"key":"pone.0361121.ref005","article-title":"Investigation on the dynamic characteristics under load regulation in CFB boiler with whole loop model","volume":"287","author":"X Hu","year":"2024","journal-title":"Chem Eng Sci"},{"key":"pone.0361121.ref006","doi-asserted-by":"crossref","first-page":"1394","DOI":"10.1016\/j.applthermaleng.2018.12.087","article-title":"Dynamic modelling, experimental validation, and thermo-economic analysis of industrial fire-tube boilers with stagnation point reverse flow combustor","volume":"149","author":"M Tognoli","year":"2019","journal-title":"Applied Thermal Engineering"},{"key":"pone.0361121.ref007","doi-asserted-by":"crossref","first-page":"121538","DOI":"10.1016\/j.energy.2021.121538","article-title":"Towards application of machine learning algorithms for prediction temperature distribution within CFB boiler based on specified operating conditions","volume":"237","author":"J Grochowalski","year":"2021","journal-title":"Energy"},{"issue":"5","key":"pone.0361121.ref008","article-title":"Machine learning regression algorithms to predict emissions from steam boilers","volume":"10","author":"BD Ross-Veit\u00eda","year":"2024","journal-title":"Heliyon"},{"issue":"46","key":"pone.0361121.ref009","doi-asserted-by":"crossref","first-page":"45884","DOI":"10.1021\/acsomega.4c05009","article-title":"Forecast of NOx Emissions for a 660MW Coal-Fired Boiler with Multilayered Gradient Boosting Decision Tree Considering Multiple Operating Modes","volume":"9","author":"Z Wang","year":"2024","journal-title":"ACS Omega"},{"key":"pone.0361121.ref010","doi-asserted-by":"crossref","first-page":"127663","DOI":"10.1016\/j.energy.2023.127663","article-title":"Fast prediction of temperature and chemical species distributions in pulverized coal boiler using POD reduced-order modeling for CFD","volume":"276","author":"X Chen","year":"2023","journal-title":"Energy"},{"issue":"1","key":"pone.0361121.ref011","doi-asserted-by":"crossref","first-page":"7434","DOI":"10.1038\/s41598-023-34146-3","article-title":"Toward explainable heat load patterns prediction for district heating","volume":"13","author":"LM Dang","year":"2023","journal-title":"Sci Rep"},{"key":"pone.0361121.ref012","unstructured":"Taieb SB, Hyndman RJ. Boosting multi-step autoregressive forecasts. In: 2014."},{"key":"pone.0361121.ref013","unstructured":"Taieb SB, Hyndman RJ. Department of Econometrics and Business Statistics. 2012. http:\/\/www.buseco.monash.edu.au\/depts\/ebs\/pubs\/wpapers\/"},{"key":"pone.0361121.ref014","doi-asserted-by":"crossref","first-page":"113810","DOI":"10.1016\/j.enbuild.2023.113810","article-title":"A study of deep learning-based multi-horizon building energy forecasting","volume":"303","author":"Z Ni","year":"2024","journal-title":"Energy and Buildings"},{"issue":"7","key":"pone.0361121.ref015","doi-asserted-by":"crossref","first-page":"9675","DOI":"10.1007\/s00202-025-02995-y","article-title":"A multi-energy meta-model strategy for multi-step ahead energy load forecasting","volume":"107","author":"A Mystakidis","year":"2025","journal-title":"Electr Eng"},{"key":"pone.0361121.ref016","doi-asserted-by":"crossref","first-page":"100781","DOI":"10.1016\/j.mlwa.2025.100781","article-title":"A comparative framework for multi-horizon time series forecasting: Neural networks with adaptive preprocessing","volume":"22","author":"A Lazcano","year":"2025","journal-title":"Machine Learning with Applications"},{"key":"pone.0361121.ref017","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.apenergy.2018.06.064","article-title":"Predicting heating demand and sizing a stratified thermal storage tank using deep learning algorithms","volume":"228","author":"A Rahman","year":"2018","journal-title":"Applied Energy"},{"issue":"4","key":"pone.0361121.ref018","doi-asserted-by":"crossref","first-page":"1380","DOI":"10.3390\/s22041380","article-title":"Decision Support System to Classify and Optimize the Energy Efficiency in Smart Buildings: A Data Analytics Approach","volume":"22","author":"M Pe\u00f1a","year":"2022","journal-title":"Sensors (Basel)"},{"key":"pone.0361121.ref019","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.105904","article-title":"An explainable decision support system for predictive process analytics","volume":"120","author":"R Galanti","year":"2023","journal-title":"Eng Appl Artif Intell"},{"key":"pone.0361121.ref020","doi-asserted-by":"crossref","first-page":"126854","DOI":"10.1016\/j.fuel.2022.126854","article-title":"A novel online combustion optimization method for boiler combining dynamic modeling, multi-objective optimization and improved case-based reasoning","volume":"337","author":"W Xu","year":"2023","journal-title":"Fuel"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0361121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T17:38:07Z","timestamp":1792777087000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0361121"}},"subtitle":[],"editor":[{"given":"Muhammad","family":"Shakaib","sequence":"first","affiliation":[{"name":"NED University of Engineering and Technology","place":["PAKISTAN"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,23]]},"references-count":20,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,23]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0361121","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,23]]}}}