AI-Driven Forecasting for Morning Fog Expansion (Sea of Clouds)

Yukitaka Ohashi aFaculty of Biosphere-Geosphere Science, Okayama University of Science, Okayama, Japan

Search for other papers by Yukitaka Ohashi in
Current site
Google Scholar
PubMed
Close
and
Kazuki Hara bGraduate School of Science and Engineering, Okayama University of Science, Okayama, Japan

Search for other papers by Kazuki Hara in
Current site
Google Scholar
PubMed
Close
Restricted access

Abstract

This study attempted to forecast the morning fog expansion (MFE), commonly referred to as the “sea of clouds,” utilizing an artificial intelligence (AI) algorithm. The radiation fog phenomenon that contributes to the sea of clouds is caused by various weather conditions. Hence, the MFE was predicted using datasets from public meteorological observations and a mesoscale numerical model (MSM). In this study, a machine learning technique, the gradient-boosting method, was adopted as the AI algorithm. The Miyoshi basin in Japan, renowned for its MFE, was selected as the experimental region. Training models were developed using datasets from October to December 2018–21. Subsequently, these models were applied to forecast MFE in 2022. The model employing the upper-atmospheric prediction data from the MSM demonstrated the highest robustness and accuracy among the proposed models. For untrained data in the fog season during 2022, the model was confirmed to be sufficiently reliable for forecasting MFE, with a high hit rate of 0.935, a low Brier score of 0.119, and a high area under the curve (AUC) of 0.944. Furthermore, the analysis of the importance of the features elucidated that the meteorological factors, such as synoptic-scale weak wind, temperatures close to the dewpoint temperature, and the absence of middle-level cloud cover at midnight, strongly contribute to the MFE. Therefore, the incorporation of upper-level meteorological elements improves the forecast accuracy for MFE.

Significance Statement

An AI-driven forecasting model for predicting morning fog expansion (MFE), sea of clouds, which often affects local livelihoods, was constructed. Fog forecasting machine learning techniques were utilized in the Japanese region famous for the morning fog. This study revealed that more accurate forecasting models incorporate numerically predicted weather elements sourced from the public routine system rather than real-time observed weather elements. Notably, the upper-level wind speed reflecting synoptic-scale dynamics, surface dewpoint depression, and middle-level cloud cover play significant roles in governing MFE. Therefore, incorporating upper-level meteorological elements into the features to machine learning is crucial for improving the forecasting accuracy of MFE.

© 2024 American Meteorological Society. This published article is licensed under the terms of the default AMS reuse license. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Yukitaka Ohashi, ohashi@ous.ac.jp

Abstract

This study attempted to forecast the morning fog expansion (MFE), commonly referred to as the “sea of clouds,” utilizing an artificial intelligence (AI) algorithm. The radiation fog phenomenon that contributes to the sea of clouds is caused by various weather conditions. Hence, the MFE was predicted using datasets from public meteorological observations and a mesoscale numerical model (MSM). In this study, a machine learning technique, the gradient-boosting method, was adopted as the AI algorithm. The Miyoshi basin in Japan, renowned for its MFE, was selected as the experimental region. Training models were developed using datasets from October to December 2018–21. Subsequently, these models were applied to forecast MFE in 2022. The model employing the upper-atmospheric prediction data from the MSM demonstrated the highest robustness and accuracy among the proposed models. For untrained data in the fog season during 2022, the model was confirmed to be sufficiently reliable for forecasting MFE, with a high hit rate of 0.935, a low Brier score of 0.119, and a high area under the curve (AUC) of 0.944. Furthermore, the analysis of the importance of the features elucidated that the meteorological factors, such as synoptic-scale weak wind, temperatures close to the dewpoint temperature, and the absence of middle-level cloud cover at midnight, strongly contribute to the MFE. Therefore, the incorporation of upper-level meteorological elements improves the forecast accuracy for MFE.

Significance Statement

An AI-driven forecasting model for predicting morning fog expansion (MFE), sea of clouds, which often affects local livelihoods, was constructed. Fog forecasting machine learning techniques were utilized in the Japanese region famous for the morning fog. This study revealed that more accurate forecasting models incorporate numerically predicted weather elements sourced from the public routine system rather than real-time observed weather elements. Notably, the upper-level wind speed reflecting synoptic-scale dynamics, surface dewpoint depression, and middle-level cloud cover play significant roles in governing MFE. Therefore, incorporating upper-level meteorological elements into the features to machine learning is crucial for improving the forecasting accuracy of MFE.

© 2024 American Meteorological Society. This published article is licensed under the terms of the default AMS reuse license. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Yukitaka Ohashi, ohashi@ous.ac.jp
Save
  • Baguskas, S. A., R. E. S. Clemesha, and M. E. Loik, 2018: Coastal low cloudiness and fog enhance crop water use efficiency in a California agricultural system. Agric. For. Meteor., 252, 109120, https://doi.org/10.1016/j.agrformet.2018.01.015.

    • Search Google Scholar
    • Export Citation
  • Bari, D., and T. Bergot, 2018: Influence of environmental conditions on forecasting of an advection-radiation fog: A case study from the Casablanca region, Morocco. Aerosol Air Qual. Res., 18, 6278, https://doi.org/10.4209/aaqr.2016.11.0520.

    • Search Google Scholar
    • Export Citation
  • Burman, P., 1989: A comparative study of ordinary cross-validation, v-fold cross-validation and the repeated learning-testing methods. Biometrika, 76, 503514, https://doi.org/10.1093/biomet/76.3.503.

    • Search Google Scholar
    • Export Citation
  • Castillo-Botón, C., D. Casillas-Pérez, C. Casanova-Mateo, S. Ghimire, E. Cerro-Prada, P. A. Gutierrez, R. C. Deo, and S. Salcedo-Sanz, 2022: Machine learning regression and classification methods for fog events prediction. Atmos. Res., 272, 106157, https://doi.org/10.1016/j.atmosres.2022.106157.

    • Search Google Scholar
    • Export Citation
  • Chawla, N. V., K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, 2002: SMOTE: Synthetic minority over-sampling technique. J. Artif. Intell. Res., 16, 321357, https://doi.org/10.1613/jair.953.

    • Search Google Scholar
    • Export Citation
  • de Souza Mourão, H. A., and H. A. B. F. de Oliveira, 2022: Indoor localization system using fingerprinting and novelty detection for evaluation of confidence. Future Internet, 14, 51, https://doi.org/10.3390/fi14020051.

    • Search Google Scholar
    • Export Citation
  • Dewi, R., Prawito, and H. Harsa, 2021: Fog prediction using artificial intelligence: A case study in Wamena Airport. J. Phys. Conf. Ser., 1528, 012021, https://doi.org/10.1088/1742-6596/1528/1/012021.

    • Search Google Scholar
    • Export Citation
  • Duynkerke, P. G., 1991: Radiation Fog: A comparison of model simulation with detailed observations. Mon. Wea. Rev., 119, 324341, https://doi.org/10.1175/1520-0493(1991)119<0324:RFACOM>2.0.CO;2.

    • Search Google Scholar
    • Export Citation
  • Egan, J. P., 1975: Signal Detection Theory and ROC Analysis. Academic Press, 277 pp.

  • Fabbian, D., R. de Dear, and S. Lellyett, 2007: Application of artificial neural network forecasts to predict fog at Canberra International Airport. Wea. Forecasting, 22, 372381, https://doi.org/10.1175/WAF980.1.

    • Search Google Scholar
    • Export Citation
  • Gao, J., H. Tian, A. Li, J. Song, and X. Zhu, 2023: Analysis of agglomerate fog meteorological characteristics in Anhui province based on traffic accident data. Pure Appl. Geophys., 180, 313333, https://doi.org/10.1007/s00024-022-03187-6.

    • Search Google Scholar
    • Export Citation
  • Gultepe, I., and J. A. Milbrandt, 2007: Microphysical observations and mesoscale model simulation of a warm fog case during FRAM project. Pure Appl. Geophys., 164, 11611178, https://doi.org/10.1007/s00024-007-0212-9.

    • Search Google Scholar
    • Export Citation
  • Haeffelin, M., J.-C. Dupont, N. Boyouk, D. Baumgardner, L. Gomes, G. Roberts, and T. Elias, 2013: A comparative study of radiation fog and quasi-fog formation processes during the ParisFog field experiment 2007. Pure Appl. Geophys., 170, 22832303, https://doi.org/10.1007/s00024-013-0672-z.

    • Search Google Scholar
    • Export Citation
  • Hanley, J. A., and B. J. McNeil, 1982: The meaning and use of the area under a Receiver Operating Characteristic (ROC) curve. Radiology, 143, 2936, https://doi.org/10.1148/radiology.143.1.7063747.

    • Search Google Scholar
    • Export Citation
  • Haque, A. B., A. K. M. N. Islam, and P. Mikalef, 2023: Explainable Artificial Intelligence (XAI) from a user perspective: A synthesis of prior literature and problematizing avenues for future research. Technol. Forecasting Soc. Change, 186, 122120, https://doi.org/10.1016/j.techfore.2022.122120.

    • Search Google Scholar
    • Export Citation
  • Hu, J., and Coauthors, 2021: Nocturnal surface radiation cooling modulated by cloud cover change reinforces PM2.5 accumulation: Observational study of heavy air pollution in the Sichuan Basin, Southwest China. Sci. Total Environ., 794, 148624, https://doi.org/10.1016/j.scitotenv.2021.148624.

    • Search Google Scholar
    • Export Citation
  • Ke, G., Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T.-Y. Liu, 2017: LightGBM: A highly efficient boosting decision tree. NIPS’17: Proc. 31st Int. Conf. on Neural Information Processing Systems, Long Beach, CA, Curran Associates, Inc., 3149–3157, https://dl.acm.org/doi/10.5555/3294996.3295074.

  • Kim, D., E. Kim, and E. Kim, 2023: Performance of decision-tree-based ensemble classifiers in predicting fog frequency in ungauged areas. Wea. Forecasting, 38, 23792393, https://doi.org/10.1175/WAF-D-23-0024.1.

    • Search Google Scholar
    • Export Citation
  • Li, X., and Z. Pu, 2022: Turbulence effects on the formation of cold fog over complex terrain with large-eddy simulation. Geophys. Res. Lett., 49, e2022GL098792, https://doi.org/10.1029/2022GL098792.

    • Search Google Scholar
    • Export Citation
  • Li, X., S. Zhang, D. Koračin, L. Yi, and X. Zhang, 2022: Atmospheric conditions conducive to marine fog over the northeast Pacific in winters of 1979–2019. Front. Earth Sci., 10, 942846, https://doi.org/10.3389/feart.2022.942846.

    • Search Google Scholar
    • Export Citation
  • Lin, D., M. Katurji, L. E. Revell, B. Khan, and A. Sturman, 2023: Investigating multiscale meteorological controls and impact of soil moisture heterogeneity on radiation fog in complex terrain using semi-idealised simulations. Atmos. Chem. Phys., 23, 14 45114 479, https://doi.org/10.5194/acp-23-14451-2023.

    • Search Google Scholar
    • Export Citation
  • Lundberg, S. M., and S.-I. Lee, 2017: A unified approach to interpreting model predictions. NIPS’17: Proc. 31st Int. Conf. on Neural Information Processing Systems, Long Beach, CA, Curran Associates Inc., 4768–4777, https://dl.acm.org/doi/10.5555/3295222.3295230.

  • Maki, M., T. Harimaya, and K. Kikuchi, 1986: Heat budget studies on nocturnal cooling in a basin. J. Meteor. Soc. Japan, 64, 727741, https://doi.org/10.2151/jmsj1965.64.5_727.

    • Search Google Scholar
    • Export Citation
  • Mason, J., 1982: The physics of radiation fog. J. Meteor. Soc. Japan, 60, 486499, https://doi.org/10.2151/jmsj1965.60.1_486.

  • Meske, C., E. Bunde, J. Schneider, and M. Gersch, 2022: Explainable artificial intelligence: Objectives, stakeholders, and future research opportunities. Inf. Syst. Manage., 39, 5363, https://doi.org/10.1080/10580530.2020.1849465.

    • Search Google Scholar
    • Export Citation
  • Miyata, K., 1994: Miyoshibonchi no Kiri no Kenkyu (in Japanese). Keisuisya, 255 pp.

  • Mokhtari, R., S. Fakouriyan, and R. Ghasempour, 2021: Investigating the effect of cloud cover on radiative cooling potential with artificial neural network modeling. Front. Energy Res., 9, 658338, https://doi.org/10.3389/fenrg.2021.658338.

    • Search Google Scholar
    • Export Citation
  • Mosca, E., F. Szigeti, S. Tragianni, D. Gallagher, and G. Groh, 2022: SHAP-based explanation methods: A review for NLP interpretability. Proc. 29th Int. Conf. on Computational Linguistics, Gyeongju, Republic of South Korea, International Committee on Computational Linguistics, 4593–4603, https://aclanthology.org/2022.coling-1.406.

  • Nakanishi, M., 2000: Large-eddy simulation of radiation fog. Bound.-Layer Meteor., 94, 461493, https://doi.org/10.1023/A:1002490423389.

    • Search Google Scholar
    • Export Citation
  • Natekin, A., and A. Knoll, 2013: Gradient boosting machines, a tutorial. Front. Neurorobotics, 7, 21, https://doi.org/10.3389/fnbot.2013.00021.

    • Search Google Scholar
    • Export Citation
  • Negishi, M., and H. Kusaka, 2022: Development of statistical and machine learning models to predict the occurrence of radiation fog in Japan. Meteor. Appl., 29, e2048, https://doi.org/10.1002/met.2048.

    • Search Google Scholar
    • Export Citation
  • Ohashi, Y., M. Iwashita, and M. Kusamoto, 2012: Possibility of predicting basin fog by using the maximum possible cooling amount and surveillance camera images. J. Agric. Meteor., 68, 97106, https://doi.org/10.2480/agrmet.68.2.3.

    • Search Google Scholar
    • Export Citation
  • Ohta, S., and M. Tanaka, 1986: A numerical simulation of the formation and dissipation of radiation fog. J. Meteor. Soc. Japan, 64, 6577, https://doi.org/10.2151/jmsj1965.64.1_65.

    • Search Google Scholar
    • Export Citation
  • Pahlavan, R., M. Moradi, S. Tajbakhsh, M. Azadi, and M. Rahnama, 2021: Fog probabilistic forecasting using an ensemble prediction system at six airports in Iran for 10 fog events. Meteor. Appl., 28, e2033, https://doi.org/10.1002/met.2033.

    • Search Google Scholar
    • Export Citation
  • Parde, A. N., S. D. Ghude, N. G. Dhangar, P. Lonkar, S. Wagh, G. Govardhan, M. Biswas, and R. K. Jenamani, 2022: Operational probabilistic fog prediction based on ensemble forecast system: A decision support system for fog. Atmosphere, 13, 1608, https://doi.org/10.3390/atmos13101608.

    • Search Google Scholar
    • Export Citation
  • Price, J. D., 2019: On the formation and development of radiation fog: An observational study. Bound.-Layer Meteor., 172, 167197, https://doi.org/10.1007/s10546-019-00444-5.

    • Search Google Scholar
    • Export Citation
  • Qiao, N., L. Zhang, C. Huang, W. Jiao, G. Maggs-Kölling, E. Marais, and L. Wang, 2020: Satellite observed positive impacts of fog on vegetation. Geophys. Res. Lett., 47, e2020GL088428, https://doi.org/10.1029/2020GL088428.

    • Search Google Scholar
    • Export Citation
  • Raschka, S., and V. Mirjalili, 2019: Python Machine Learning. 3rd ed. Packt Publishing, 772 pp.

  • Roach, W. T., R. Brown, S. J. Caughey, J. A. Garland, and C. J. Readings, 1976: The physics of radiation fog: I – A field study. Quart. J. Roy. Meteor. Soc., 102, 313333, https://doi.org/10.1002/qj.49710243204.

    • Search Google Scholar
    • Export Citation
  • Román-Cascón, C., G. Steeneveld, C. Yagüe, M. Sastre, J. A. Arrillaga, and G. Maqueda, 2016: Forecasting radiation fog at climatologically contrasting sites: Evaluation of statistical methods and WRF. Quart. J. Roy. Meteor. Soc., 142, 10481063, https://doi.org/10.1002/qj.2708.

    • Search Google Scholar
    • Export Citation
  • Sibindi, R., R. W. Mwangi, and A. G. Waititu, 2023: A boosting ensemble learning based hybrid light gradient boosting machine and extreme gradient boosting model for predicting house prices. Eng. Rep., 5, e12599, https://doi.org/10.1002/eng2.12599.

    • Search Google Scholar
    • Export Citation
  • Singh, A., and H. Sood, 2017: A review on influence of fog on road crash. Int. J. Eng. Res. Technol., 6, 671676.

  • Smith, D. K. E., I. A. Renfrew, J. D. Price, and S. R. Dorling, 2018: Numerical modelling of the evolution of the boundary layer during a radiation fog event. Weather, 73, 310316, https://doi.org/10.1002/wea.3305.

    • Search Google Scholar
    • Export Citation
  • Steeneveld, G. J., R. J. Ronda, and A. A. M. Holtslag, 2015: The challenge of forecasting the onset and development of radiation fog using mesoscale atmospheric models. Bound.-Layer Meteor., 154, 265289, https://doi.org/10.1007/s10546-014-9973-8.

    • Search Google Scholar
    • Export Citation
  • Swets, J. A., 1973: The relative operating characteristic in psychology. Science, 182, 9901000, https://doi.org/10.1126/science.182.4116.990.

    • Search Google Scholar
    • Export Citation
  • Tag, P. M., and J. E. Peak, 1996: Machine learning of maritime fog forecast rules. J. Appl. Meteor., 35, 714724, https://doi.org/10.1175/1520-0450(1996)035<0714:MLOMFF>2.0.CO;2.

    • Search Google Scholar
    • Export Citation
  • Tardif, R., and R. M. Rasmussen, 2007: Event-based climatology and typology of fog in the New York City region. J. Appl. Meteor. Climatol., 46, 11411168, https://doi.org/10.1175/JAM2516.1.

    • Search Google Scholar
    • Export Citation
  • Teshiba, M., H. Hashiguchi, A. Uematsu, H. Tanaka, Y. Ohmori, and S. Fukao, 2004: Fog observations with a millimeter-wave scanning radar at Miyoshi basin, Japan. Earth Planets Space, 56, 259268, https://doi.org/10.1186/BF03353408.

    • Search Google Scholar
    • Export Citation
  • Trigg, J. L., Jr., 2000: A study of morning radiation fog formation. M.S. dissertations, Dept. of Air Force, Air University, Air Force Institute of Technology, 89 pp., https://apps.dtic.mil/sti/pdfs/ADA384334.pdf.

  • Ye, Z. J., M. Segal, J. R. Garratt, and R. A. Pielke, 1989: On the impact of cloudiness on the characteristics of nocturnal downslope flows. Bound.-Layer Meteor., 49, 2351, https://doi.org/10.1007/BF00116404.

    • Search Google Scholar
    • Export Citation
  • Zhou, B., and B. S. Ferrier, 2008: Asymptotic analysis of equilibrium in radiation fog. J. Appl. Meteor. Climatol., 47, 17041722, https://doi.org/10.1175/2007JAMC1685.1.

    • Search Google Scholar
    • Export Citation
  • Zhou, B., and J. Du, 2010: Fog prediction from a multimodel mesoscale ensemble prediction system. Wea. Forecasting, 25, 303322, https://doi.org/10.1175/2009WAF2222289.1.

    • Search Google Scholar
    • Export Citation
  • Zhou, Z.-H., 2009: Ensemble learning. Encyclopedia of Biometrics, S. Z. Li, and A. Jain, Eds., Springer, 270–273, https://doi.org/10.1007/978-0-387-73003-5_293.

All Time Past Year Past 30 Days
Abstract Views 559 559 186
Full Text Views 105 105 33
PDF Downloads 130 130 39