Creating a Universal Depth-to-Load Conversion Technique for the Conterminous United States Using Random Forests
Publication: Journal of Cold Regions Engineering
Volume 36, Issue 1
Abstract
As part of an ongoing effort to update the ground snow load maps in the US, this paper presents an investigation into snow densities for the purpose of predicting ground snow loads for structural engineering design with ASCE 7. Despite their importance, direct measurements of snow load are sparse, compared with measurements of snow depth. As a result, it is often necessary to estimate snow load using snow depth and other readily accessible climate variables. Existing depth-to-load conversion methods, each of varying complexity, are well suited for snow load estimation for a particular region or station network, but none is consistently effective across regions and station networks. In this paper, a random forest regression model is proposed for estimating annual maximum snow loads in the conterminous US that makes use of climate reanalysis data and overcomes the limitations of existing methods. The effectiveness of the random forest model is demonstrated through accuracy comparisons of existing depth-to-load conversion techniques using a compilation of national and state-level data sources. The accuracy comparisons show that the random forest model is competitive for all regions and station networks, whereas other methods are competitive only for certain regions or station networks. These results highlight the feasibility of developing a single depth-to-load conversion method that appropriately characterizes region and climate specific differences in the snow depth–load relationship across the conterminous US. Such universal models are an essential component for creating a unified set of national snow load requirements that eliminate the case study regions currently defined in current national standards.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
This research was made possible through funding led by ASCE and the Structural Engineering Institute in collaboration with funding from several organizations. The groups that provided significant monetary support to this effort were (in alphabetical order): Factory Mutual, Metal Building Manufacturer’s Association, National Council of Structural Engineering Associations, Nucor, Simpson Gumpertz and Heger, the State of Montana, the Steel Deck Institute, the Steel Joist Institute, Structural Engineers Association of Montana, Wiss Janney, and Elstner Associates. Preliminary analyses were also supported in part by Utah State University’s Undergraduate Research and Creative Opportunity Grant Program.
Further help from the Snow and Rain Load Subcommittee and the steering committee overseeing this research went above and beyond expectations. Many long hours were spent exchanging expertise on national and local concerns resulting in the work contained in this paper and the forthcoming updates to the ASCE 7 Chapter 7 specifications. Thanks to Abbie Liel and Scott Russell for chairing the task group and steering committee overseeing this work. Special thanks to Jim Harris, Mike O’Rourke, Jim Buska, David Thompson, and Jerry Stephens for their boundless time, effort, knowledge, experience, and aid. Additionally, committee members John Duntemann, Richard Nielson, Jared DeBock, Johnn Judd, Hossein Mostafaei, John Corless, John-Paul Cardin, Sean Homem, Gary Ehrlich, Sterling Strait, Vince Sagan, and Thomas DiBlasi all provided time, expertise, local knowledge, review, and support to this work. Yan Sun at Utah State University provided helpful guidance regarding the proposed statistical methodologies. Graduate students Jadon Wagstaff at Utah State University and Salam Al-Rubaye at the University of Nebraska-Lincoln were also instrumental. Lastly, undergraduates Miranda Rogers and Scout Jarman were very helpful and provided much needed support in data processing.
References
Avanzi, F., C. de michele, and A. Ghezzi. 2015. “On the performances of empirical regressions for the estimation of bulk snow density.” Geogr. Fis. Din. Quat. 38: 105–112.
Bean, B., M. Maguire, and Y. Sun. 2018. The Utah snow load study. Rep. No. 4591. Dept. of Civil and Environmental Engineering, Utah State Univ.
Bean, B., M. Maguire, Y. Sun, J. Wagstaff, S. A. Al-Rubaye, J. Wheeler, S. Jarman, and M. Rogers. 2021. The 2020 national snow load study. Rep. No. 276. Logan, UT: Dept. of Mathematics and Statistics, Utah State Univ.
Breiman, L. 2001a. “Random forests.” Mach. Learn. 45 (1): 5–32. https://doi.org/10.1023/A:1010933404324.
Breiman, L. 2001b. “Statistical modeling: The two cultures (with comments and a rejoinder by the author).” Statist. Sci. 16 (3): 199–231. https://doi.org/10.1214/ss/1009213726.
Breiman, L., J. H. Friedman, R. A. Olshen, and C. J. Stone. 1984. Classification and regression trees. Monterey, CA: Wadsworth and Brooks.
Copland, L. 2020. “Properties of glacial ice and glacier classification.” In Reference module in earth systems and environmental sciences. Amsterdam, Netherlands: Elsevier.
Daly, C., M. Halbleib, J. I. Smith, W. P. Gibson, M. K. Doggett, G. H. Taylor, J. Curtis, and P. P. Pasteris. 2008. “Physiographically sensitive mapping of climatological temperature and precipitation across the conterminous United States.” Int. J. Climatol. 28 (15): 2031–2064. https://doi.org/10.1002/joc.v28:15.
DeBock, D. J., J. R. Harris, A. B. Liel, R. M. Patillo, and J. M. Torrents. 2016. Colorado design snow loads. Rep. No. Aurora, CO: Structural Engineers Association of Colorado.
DeBock, D. J., A. B. Liel, J. R. Harris, B. R. Ellingwood, and J. M. Torrents. 2017. “Reliability-based design snow loads. I: Site-specific probability models for ground snow loads.” J. Struct. Eng. 143 (7): 04017046. https://doi.org/10.1061/(ASCE)ST.1943-541X.0001731.
Gustafsson, D., N. Sundstrom, and A. Lundberg. 2012. “Estimation of snow water equivalent of dry snowpacks using a multi-offset ground penetrating radar system.” In Proc., 69th Eastern Snow Conf., 197–206. Claryville, NY: Frost Valley YMCA.
Hill, D. F., E. A. Burakowski, R. L. Crumley, J. Keon, J. M. Hu, A. A. Arendt, K. Wikstrom Jones, and G. J. Wolken. 2019. “Converting snow depth to snow water equivalent using climatological variables.” Cryosphere 13 (7): 1767–1784. https://doi.org/10.5194/tc-13-1767-2019.
Hosking, J. R. M., J. R. Wallis, and E. F. Wood. 1985. “Estimation of the generalized extreme-value distribution by the method of probability-weighted moments.” Technometrics 27 (3): 251–261. https://doi.org/10.1080/00401706.1985.10488049.
Jones, K. F., and S. F. Daly. 2019. “Snow depth and snow water equivalent data at stations included in the GHCN database.” In Proc., 76th Eastern Snow Conf., 78–100. Fairlee, Vermont: Eastern Snow Conference. Accessed April 1, 2020. http://www.proceedings.com/52970.html.
Krstajic, D., L. J. Buturovic, D. E. Leahy, and S. Thomas. 2014. “Cross-validation pitfalls when selecting and assessing regression and classification models.” J. Cheminf. 6 (1): 125. https://doi.org/10.1186/1758-2946-6-10.
Liel, A. B., D. J. DeBock, J. R. Harris, B. R. Ellingwood, and J. M. Torrents. 2017. “Reliability-based design snow loads. II: Reliability assessment and mapping procedures.” J. Struct. Eng. 143 (7): 04017047. https://doi.org/10.1061/(ASCE)ST.1943-541X.0001732.
Lundberg, A., C. Näslund, and C. Andersson. 2006. “Snow density variations: Consequences for ground-penetrating radar.” Hydrol. Processes 20: 1483–1495. https://doi.org/10.1002/(ISSN)1099-1085.
Maine Geological Survey. 2020. “Maine snow survey data.” Accessed April 3, 2020. https://mgs-maine.opendata.arcgis.com/datasets/maine-snow-survey-data.
Marchand, W.-D., and A. Killingtveit. 2004. “Statistical properties of spatial snowcover in mountainous catchments in Norway.” Hydrol. Res. 35 (2): 101–117. https://doi.org/10.2166/nh.2004.0008.
McCreight, J. L., and E. E. Small. 2014. “Modeling bulk density and snow water equivalent using daily snow depth observations.” Cryosphere 8 (2): 521–536. https://doi.org/10.5194/tc-8-521-2014.
Meehleis, K., T. Folan, S. Hamel, R. Lang, and G. Gienko. 2020. “Snow load calculations for Alaska using GHCN data (1950–2017).” J. Cold Reg. Eng. 34 (3): 04020011. https://doi.org/10.1061/(ASCE)CR.1943-5495.0000218.
Meløysund, V., B. Leira, K. V. Høiseth, and K. R. Lisø. 2007. “Predicting snow density using meteorological data.” Meteorol. Appl. 14 (4): 413–423. https://doi.org/10.1002/(ISSN)1469-8080.
Menne, M., et al. 2012a. “Global historical climatology network data - daily.” https://doi.org/10.7289/V5D21VHZ. Version 3.27, Date Downloaded: 08-25-2020.
Menne, M. J., I. Durre, R. S. Vose, B. E. Gleason, and T. G. Houston. 2012b. “An overview of the global historical climatology network-daily database.” J. Atmos. Oceanic Technol. 29 (7): 897–910. https://doi.org/10.1175/JTECH-D-11-00103.1.
Meyer, H., C. Reudenbach, S. Wöllauer, and T. Nauss. 2019. “Importance of spatial predictor variable selection in machine learning applications – moving from data reproduction to spatial prediction.” Ecol. Modell. 411: 108815. https://doi.org/10.1016/j.ecolmodel.2019.108815.
NOAA (National Oceanic and Atmospheric Administration). 2021. NOAA medium resolution shoreline. Washington, DC: NOAA.
NOHRSC (National Operational Hydrologic Remote Sensing Center). 2004. Snow data assimilation system (SNODAS) data products at NSIDC, version 1. Chanhassen, MN: National Snow and Ice Data Center.
NRCC (Northeast Regional Climate Center). 2020. “New York snow survey data.” http://www.nrcc.cornell.edu/. Data obtained through personal correspondence with Northeast Regional Climate Center.
NRCS (Natural Resources Conservation Service). 2020. “Snow telemetry (SNOTEL) and snow course data and products.” Accessed January 4, 2021. https://www.wcc.nrcs.usda.gov/snow/.
Pomeroy, J. W., D. M. Gray, K. R. Shook, B. Toth, R. L. H. Essery, A. Pietroniro, and N. Hedstrom. 1998. “An evaluation of snow accumulation and ablation processes for land surface modelling.” Hydrol. Processes 12 (15): 2339–2367. https://doi.org/10.1002/(ISSN)1099-1085.
PRISM Climate Group, Oregon State University 2004. “30-year normals.” Accessed August 30, 2021. https://prism.oregonstate.edu/normals/.
Sack, R. L., and A. Sheikh-Taheri. 1986. Ground and roof snow loads for Idaho. Moscow, ID: Dept. of Civil Engineering, Univ. of Idaho.
SEAO (Stuctural Engineer Association of Oregon). 2007. Snow load analysis for Oregon. Portland, OR: SEAO.
Sturm, M., J. Holmgren, and G. E. Liston. 1995. “A seasonal snow cover classification system for local to global applications.” J. Clim. 8 (5): 1261–1283. https://doi.org/10.1175/1520-0442(1995)008%A11261:ASSCCS%BF2.0.CO;2.
Sturm, M., B. Taras, G. E. Liston, C. Derksen, T. Jonas, and J. Lea. 2010. “Estimating snow water equivalent using snow depth data and climate classes.” J. Hydrometeorol. 11 (6): 1380–1394. https://doi.org/10.1175/2010JHM1202.1.
Tabler, R. D. 1980. “Geometry and density of drifts formed by snow fences.” J. Glaciol. 26 (94): 405–419. https://doi.org/10.1017/S0022143000010935.
Theisen, G. P., M. J. Keller, J. E. Stephens, F. F. Videon, and J. P. Schilke. 2004. Snow loads for structural design in Montana. Bozeman, MT: Dept. of Civil Engineering, Montana State Univ.
Tobiasson, W., and A. Greatorex. 1997. “Database and methodology for conducting site specific snow load case studies for the United States.” In Proc., 3rd Int. Conf. on Snow Engineering, edited by I. Izumi, T. Nakamura and R.L. Sack, 249–256. Rotterdam, Netherlands: AA Balkema.
Wang, T., A. Hamann, D. Spittlehouse, and C. Carroll. 2016. “Locally downscaled and spatially customizable climate data for historical and future periods for north america.” PLoS One 11 (6): 1–17.
Wheeler, J., B. Bean, and M. Maguire. 2021. “Supplementary files for ćreating a universal depth-to-load conversion technique for the conterminous United States using random forests.” Accessed August 27, 2021. https://doi.org/10.26078/NKDT-T278.
Information & Authors
Information
Published In
Journal of Cold Regions Engineering
Volume 36 • Issue 1 • March 2022
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Jan 28, 2021
Accepted: Sep 25, 2021
Published online: Nov 26, 2021
Published in print: Mar 1, 2022
Discussion open until: Apr 26, 2022
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Jadon Wagstaff, Brennan Bean, Jesse Wheeler, Marc Maguire, Yan Sun, Adaptive Mapping of Design Ground Snow Loads in the Conterminous United States, Journal of Structural Engineering, 10.1061/JSENDH.STENG-12396, 150, 1, (2024).
- Kenneth Pomeyie, Brennan Bean, Yan Sun, Comparing Extreme Value Estimation Techniques for Short-Term Snow Accumulations, Journal of Data Science, 10.6339/23-JDS1086, (1-23), (2023).