{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T14:11:04Z","timestamp":1772115064004,"version":"3.50.1"},"reference-count":52,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T00:00:00Z","timestamp":1754179200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2023-00243861"],"award-info":[{"award-number":["RS-2023-00243861"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Machine learning modeling is a valuable tool for gap-filling or prediction, and its performance is typically evaluated using standard metrics. To enable more precise assessments for time-series data, this study emphasizes the importance of considering time-series consistency, which can be evaluated through amplitude\u2014specifically, the interquartile range and the lower bound of the band in gap-filled time series. To test this hypothesis, a gap-filling technique was applied using long-term (~6 years) high-frequency flux and meteorological data collected at four different levels (1.5, 60, 140, and 300 m above sea level) on a ~300 m tall flux tower. This study focused on turbulent kinetic energy among several variables, which is important for estimating sensible and latent heat fluxes and net ecosystem exchange. Five ensemble machine learning algorithms were selected and trained on three different datasets. Among several modeling scenarios, the stacking model with a dataset combined with derivative data produced the best metrics for predicting turbulent kinetic energy. Although the metrics before and after gap-filling reported fewer differences among the scenarios, large distortions were found in the consistency of the time series in terms of amplitude. These findings underscore the importance of evaluating time-series consistency alongside traditional metrics, not only to accurately assess modeling performance but also to ensure reliability in downstream applications such as forecasting, climate modeling, and energy estimation.<\/jats:p>","DOI":"10.3390\/make7030076","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T07:45:11Z","timestamp":1754466311000},"page":"76","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Significance of Time-Series Consistency in Evaluating Machine Learning Models for Gap-Filling Multi-Level Very Tall Tower Data"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5754-9905","authenticated-orcid":false,"given":"Changhyoun","family":"Park","sequence":"first","affiliation":[{"name":"Institute of Environmental Studies, Pusan National University, Busan 46241, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Stull, R.B. (1988). An Introduction to Boundary Layer Meteorology, Springer.","DOI":"10.1007\/978-94-009-3027-8"},{"key":"ref_2","unstructured":"Arya, P.S. (2001). Introduction to Micrometeorology, Academic Press."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1175\/JCLI-D-11-00029.1","article-title":"Characterization of Turbulent Latent and Sensible Heat Flux Exchange between the Atmosphere and Ocean in MERRA","volume":"25","author":"Roberts","year":"2012","journal-title":"J. Clim."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bonan, G. (2015). Ecological Climatology, Cambridge University Press. [3rd ed.].","DOI":"10.1017\/CBO9781107339200"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2415","DOI":"10.1175\/1520-0477(2001)082<2415:FANTTS>2.3.CO;2","article-title":"FLUXNET: A new tool to study the temporal and spatial variability of ecosystem-scale carbon dioxide, water vapor, and energy flux densities","volume":"82","author":"Baldocchi","year":"2001","journal-title":"B Am. Meteorol. Soc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/S0168-1923(02)00102-8","article-title":"Seasonality of ecosystem respiration and gross primary production as derived from FLUXNET measurements","volume":"113","author":"Falge","year":"2002","journal-title":"Agric. Forest Meteorol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"401","DOI":"10.3402\/tellusb.v50i5.16216","article-title":"Measurements of carbon dioxide on very tall towers: Results of the NOAA\/CMDL program","volume":"50","author":"Bakwin","year":"1998","journal-title":"Tellus B"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"535","DOI":"10.3402\/tellusb.v47i5.16070","article-title":"Measurements of Carbon-Dioxide on a Very Tall Tower","volume":"47","author":"Bakwin","year":"1995","journal-title":"Tellus B"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1278","DOI":"10.1046\/j.1365-2486.2003.00672.x","article-title":"The annual cycles of CO2 and H2O exchange over a northern mixed forest as observed from a very tall tower","volume":"9","author":"Davis","year":"2003","journal-title":"Global Change Biol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"9991","DOI":"10.1029\/2000JD900080","article-title":"Influence of advection on measurements of the net ecosystem-atmosphere exchange of CO2 from a very tall tower","volume":"105","author":"Yi","year":"2000","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"D24101","DOI":"10.1029\/2004JD004936","article-title":"Flux and turbulence measurements at a densely built-up site in Marseille: Heat, mass (water and carbon dioxide), and momentum","volume":"109","author":"Grimmond","year":"2004","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3139","DOI":"10.1021\/es010277e","article-title":"Meteorological measurements of the urban heat budget and CO2 emissions on a city scale","volume":"36","author":"Nemitz","year":"2002","journal-title":"Environ. Sci. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"253","DOI":"10.2134\/jeq2015.02.0115","article-title":"Anthropogenic and Biogenic Features of Long-Term Measured CO2 Flux in North Downtown Houston, Texas","volume":"45","author":"Park","year":"2016","journal-title":"J. Environ. Qual."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"7433","DOI":"10.1016\/j.atmosenv.2005.08.038","article-title":"Measurements of CO2 fluxes from the Mexico City urban landscape","volume":"39","author":"Velasco","year":"2005","journal-title":"Atmos. Environ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"7881","DOI":"10.5194\/acp-12-7881-2012","article-title":"Four-year (2006\u20132009) eddy covariance measurements of CO2 flux over an urban area in Beijing","volume":"12","author":"Liu","year":"2012","journal-title":"Atmos. Chem. Phys."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Costa, R.L., Gomes, H.B., Pinto, D.D.C., Junior, R.L.D., Silva, F.D.D., Gomes, H.B., da Silva, M.C.L., and Herdies, D.L. (2021). Gap Filling and Quality Control Applied to Meteorological Variables Measured in the Northeast Region of Brazil. Atmosphere, 12.","DOI":"10.3390\/atmos12101278"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Kang, M., Ichii, K., Kim, J., Indrawati, Y.M., Park, J., Moon, M., Lim, J.H., and Chun, J.H. (2019). New Gap-Filling Strategies for Long-Period Flux Data Gaps Using a Data-Driven Approach. Atmosphere, 10.","DOI":"10.3390\/atmos10100568"},{"key":"ref_18","first-page":"447","article-title":"Objective Analysis of Meteorological Fields","volume":"92","author":"Gandin","year":"1966","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_19","first-page":"271","article-title":"Statistics for Spatial Data\u2014Cressie, N","volume":"25","author":"Griffith","year":"1993","journal-title":"Geogr. Anal."},{"key":"ref_20","first-page":"101","article-title":"Filling Gaps in Micro-meteorological Data","volume":"12461","author":"Richard","year":"2021","journal-title":"Lect. Notes Artif. Int."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"142","DOI":"10.2480\/agrmet.D-22-00024","article-title":"Gap-filling greenhouse gas fluxes for the closed chamber method at paddy fields using machine learning techniques","volume":"79","author":"Phungern","year":"2023","journal-title":"J. Agric. Meteorol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1007\/s12665-024-11982-8","article-title":"A comparative analysis of machine learning approaches to gap filling meteorological datasets","volume":"83","author":"Lalic","year":"2024","journal-title":"Environ. Earth Sci."},{"key":"ref_23","unstructured":"Mahabbati, A. (2022). Investigating the Application of Machine Learning Models to Improve the Eddy Covariance Data Gap-Filling. [Ph.D. Thesis, The University of Western Australia]."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"131787","DOI":"10.1016\/j.jhydrol.2024.131787","article-title":"A gap filling method for daily evapotranspiration of global flux data sets based on deep learning","volume":"641","author":"Qian","year":"2024","journal-title":"J. Hydrol."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Gao, D.X., Yao, J.Y., Yu, S.T., Ma, Y.L., Li, L., and Gao, Z.M. (2023). Eddy Covariance CO2 Flux Gap Filling for Long Data Gaps: A Novel Framework Based on Machine Learning and Time Series Decomposition. Remote Sens., 15.","DOI":"10.3390\/rs15102695"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"108777","DOI":"10.1016\/j.agrformet.2021.108777","article-title":"Stable gap-filling for longer eddy covariance data gaps: A globally validated machine-learning approach for carbon dioxide, water, and energy fluxes","volume":"314","author":"Zhu","year":"2022","journal-title":"Agric. Forest Meteorol."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Khan, M.S., Jeon, S.B., and Jeong, M.H. (2021). Gap-Filling Eddy Covariance Latent Heat Flux: Inter-Comparison of Four Machine Learning Model Predictions and Uncertainties in Forest Ecosystem. Remote Sens., 13.","DOI":"10.3390\/rs13244976"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1499","DOI":"10.1111\/gcb.14845","article-title":"Gap-filling approaches for eddy covariance methane fluxes: A comparison of three machine learning algorithms and a traditional method with principal component analysis","volume":"26","author":"Kim","year":"2020","journal-title":"Global Change Biol."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Huang, H., and Hsieh, C. (2020). Gap-Filling of Surface Fluxes Using Machine Learning Algorithms in Various Ecosystems. Water, 12.","DOI":"10.3390\/w12123415"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Lee, X., Massman, W., and Law, B. (2005). Handbook of Micrometeorology: A Guide for Surface Flux Measurement and Analysis, Springer.","DOI":"10.1007\/1-4020-2265-4"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1175\/1520-0426(1997)014<0512:QCAFSP>2.0.CO;2","article-title":"Quality control and flux sampling problems for tower and aircraft data","volume":"14","author":"Vickers","year":"1997","journal-title":"J. Atmos. Ocean Tech."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1127\/0941-2948\/2006\/0167","article-title":"Impact of post-field data processing on eddy covariance flux estimates and energy balance closure","volume":"15","author":"Mauder","year":"2006","journal-title":"Meteorol. Z"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1016\/S0022-1694(96)03194-0","article-title":"A system to measure surface fluxes of momentum, sensible heat, water vapour and carbon dioxide","volume":"188","author":"Moncrieff","year":"1997","journal-title":"J. Hydrol."},{"key":"ref_34","unstructured":"Lee, X., Massman, W., and Law, B. (2004). Averaging, detrending and filtering of eddy covariance time series. Handbook of Micrometeorology: A Guide for Surface Flux Measurements, Kluwer Academic."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2069","DOI":"10.1007\/s00484-022-02341-y","article-title":"Environmental factors contributing to variations in CO2 flux over a barley-rice double-cropping paddy field in the Korean Peninsula","volume":"66","author":"Park","year":"2022","journal-title":"Int. J. Biometeorol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","article-title":"Extremely Randomized Trees","volume":"63","author":"Geurts","year":"2006","journal-title":"Mach. Learn."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Chen, T.Q., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the Kdd\u201916: The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_38","unstructured":"Ke, G.L., Meng, Q., Finley, T., Wang, T.F., Chen, W., Ma, W.D., Ye, Q.W., and Liu, T.Y. (2017, January 4\u20139). LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Proceedings of the NIPS\u201917: The 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_39","first-page":"1751","article-title":"Combining information extraction systems using voting and stacked generalization","volume":"6","author":"Sigletos","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1093\/biomet\/78.3.691","article-title":"A Note on a General Definition of the Coefficient of Determination","volume":"78","author":"Nagelkerke","year":"1991","journal-title":"Biometrika"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1901","DOI":"10.1175\/JCLI-D-11-00151.1","article-title":"Estimation of Rain Intensity Spectra over the Continental United States Using Ground Radar-Gauge Measurements","volume":"25","author":"Lin","year":"2012","journal-title":"J. Climate"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"e2019JF005513","DOI":"10.1029\/2019JF005513","article-title":"Physical Interpretation of Rainfall Thresholds or Runoff-Generated Debris Flows","volume":"125","author":"Berti","year":"2020","journal-title":"J. Geophys. Res. Earth"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1547","DOI":"10.5194\/hess-19-1547-2015","article-title":"Evaluation of high-resolution precipitation analyses using a dense station network","volume":"19","author":"Kann","year":"2015","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"ref_44","first-page":"163","article-title":"Basic Laws of Turbulent Mixing in the Surface Layer of the Atmosphere","volume":"24","author":"Monin","year":"1954","journal-title":"Tr. Geofiz. Instituta Akad. Nauk."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1431","DOI":"10.5194\/wes-9-1431-2024","article-title":"Machine-learning-based estimate of the wind speed over complex terrain using the long short-term memory (LSTM) recurrent neural network","volume":"9","author":"Beu","year":"2024","journal-title":"Wind Energy Sci."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Karadag, I., and G\u00fcr, M. (2025). Machine Learning for Wind Speed Estimation. Buildings, 15.","DOI":"10.3390\/buildings15091541"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"2217","DOI":"10.5194\/wes-9-2217-2024","article-title":"Understanding the impact of data gaps on long-term offshore wind resource estimates","volume":"9","author":"Alvarez","year":"2024","journal-title":"Wind Energy Sci."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"145290","DOI":"10.1016\/j.scitotenv.2021.145290","article-title":"Integration of Weather Research and Forecasting (WRF) model with regional coastal ecosystem model to simulate the hypoxic conditions","volume":"771","author":"Hafeez","year":"2021","journal-title":"Sci. Total Environ."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1175\/WAF-D-21-0176.1","article-title":"An Evaluation of Surface Wind and Gust Forecasts from the High-Resolution Rapid Refresh Model","volume":"37","author":"Fovell","year":"2022","journal-title":"Weather Forecast"},{"key":"ref_50","unstructured":"Antor, A.F., and Wollega, E.B. (2020, January 10\u201314). Comparison of Machine Learning Algorithms for WindSpeed Prediction. Proceedings of the 5th NA International Conference on Industrial Engineering and Operations Management, Detroit, MI, USA."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Abdelsattar, M., Ismeil, M.A., Menoufi, K., Abdelmoety, A., and Emad-Eldeen, A. (2025). Evaluating Machine Learning and Deep Learning models for predicting Wind Turbine power output from environmental factors. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0317619"},{"key":"ref_52","unstructured":"Lundberg, S.M., and Lee, S.I. (2017, January 4\u20139). A Unified Approach to Interpreting Model Predictions. Proceedings of the NIPS\u201917: The 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/76\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:22:10Z","timestamp":1760034130000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/76"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":52,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["make7030076"],"URL":"https:\/\/doi.org\/10.3390\/make7030076","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,3]]}}}