Abstract
Temperature changes have widespread impacts on the environment, economy, and municipal planning. Generating accurate climate prediction at finer spatial resolution through downscaling could help better assess the future effects of climate change on a local scale. Ensembles of multiple climate models have been proven to improve the accuracy of temperature prediction. Meanwhile, machine learning techniques have shown high performance in solving various predictive modeling problems, which make them a promising tool for temperature downscaling. This study investigated the performance of machine learning (long short-term memory (LSTM) networks and support vector machine (SVM)) and statistical (arithmetic ensemble mean (EM) and multiple linear regression (MLR)) methods in developing multi-model ensembles for downscaling long-term daily temperature. A case study of twelve meteorological stations across Ontario, Canada, was conducted to evaluate the performance of the proposed ensembles. The results showed that both machine learning and statistical techniques performed well at downscaling daily temperature with multi-model ensembles and had similar performance with relatively high accuracy. The R2 of 12 stations ranged between 0.756 and 0.820 and RMSE ranged between 4.318 and 7.063 °C. Both machine learning and statistical ensembles for downscaling had difficulty in predicting extreme values for temperature below − 10 °C and above 20 °C. The results provided technical support for using statistical and machine learning methods to generate high-resolution daily temperature prediction.
Similar content being viewed by others
References
Al-Anazi AF, Gates ID (2010) Support vector regression for porosity prediction in a heterogeneous reservoir: a comparative study. Comput Geosci 36(12):1494–1503. https://doi.org/10.1016/j.cageo.2010.03.022
Anandhi A, Srinivas VV, Kumar DN, Nanjundiah RS (2009) Role of predictors in downscaling surface temperature to river basin in India for IPCC SRES scenarios using support vector machine. Int J Climatol 29(4):583–603. https://doi.org/10.1002/joc.1719
Bartos MD, Chester MV (2015) Impacts of climate change on electric power supply in the Western United States. Nat Clim Chang 5(8):748–752. https://doi.org/10.1038/nclimate2648
Bush E, Lemmen DS, and editors (2019) Canada’s changing climate report. Government of Canada, Ottawa, p 444
Cakir S, Kadioglu M, Cubukcu N (2013) Multischeme ensemble forecasting of surface temperature using neural network over Turkey. Theor Appl Climatol 111(3):703–711. https://doi.org/10.1007/s00704-012-0703-1
Christensen JH, Kjellström E, Giorgi F, Lenderink G, Rummukainen M (2010) Weight assignment in regional climate models. Clim Res 44(2–3):179–194. https://doi.org/10.3354/cr00916
Coulibaly P, Dibike YB, Anctil F (2005) Downscaling precipitation and temperature with temporal neural networks. J Hydrometeorol 6(4):483–496. https://doi.org/10.1175/JHM409.1
Devak M, Dhanya C, Gosain A (2015) Dynamic coupling of support vector machine and K-nearest neighbour for downscaling daily rainfall. J Hydrol 525:286–301. https://doi.org/10.1016/j.jhydrol.2015.03.051
Dibike YB, Coulibaly P (2006) Temporal neural networks for downscaling climate variability and extremes. Neural Netw 19(2):135–144. https://doi.org/10.1016/j.neunet.2006.01.003
Donahue J, Hendricks LA, Rohrbach M, Venugopalan S, Guadarrama S, Saenko K, Darrell T (2017) Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans Pattern Anal Mach Intell 39(4):677–691. https://doi.org/10.1109/TPAMI.2016.2599174
Drucker H, Burges CJ, Kaufman L, Smola AJ, Vapnik V (1997) Support vector regression machines. In advances in neural information processing systems. (pp. 155–161). http://papers.nips.cc/paper/1238-support-vector-regression-machines.pdf
ECCC (n.d.) Digital Archive of Canadian Climatological Data. Retrieved from http://climate.weather.gc.ca/historical_data/search_historic_data_e.html
Fan J, Yue W, Wu L, Zhang F, Cai H, Wang X, Lu X, Xiang Y (2018) Evaluation of SVM, ELM and four tree-based ensemble models for predicting daily reference evapotranspiration using limited meteorological data in different climates of China. Agric For Meteorol 263:225–241. https://doi.org/10.1016/j.agrformet.2018.08.019
Feng J, Lee D-K, Fu C, Tang J, Sato Y, Kato H, McGregor JL, Mabuchi K (2010) Comparison of four ensemble methods combining regional climate simulations over Asia. Meteorog Atmos Phys 111(1–2):41–53. https://doi.org/10.1007/s00703-010-0115-7
Fente DN, Singh DK (2018) Weather Forecasting Using Artificial Neural Network. In 2018 Second international conference on inventive communication and computational technologies (ICICCT), Coimbatore, pp 1757–1761. https://doi.org/10.1109/ICICCT.2018.8473167
Fumo N, Rafe Biswas MA (2015) Regression analysis for prediction of residential energy consumption. Renew Sust Energ Rev 47:332–343. https://doi.org/10.1016/j.rser.2015.03.035
Gaitan CF, Hsieh WW, Cannon AJ, Gachon P (2013) Evaluation of linear and non-linear downscaling methods in terms of daily variability and climate indices: surface temperature in southern Ontario and Quebec, Canada. Atmosphere-Ocean 52(3):211–221. https://doi.org/10.1080/07055900.2013.857639
Giorgi F, Jones C, Asrar GR (2009) Addressing climate information needs at the regional level: the CORDEX framework. World Meteorological Organization (WMO) Bulletin 58(3):175. https://public.wmo.int/en/bulletin/addressing-climate-information-needs-regional-level-cordex-framework
Gornall J, Betts R, Burke E, Clark R, Camp J, Willett K, Wiltshire A (2010) Implications of climate change for agricultural productivity in the early twenty-first century. Philos Trans R Soc Lond Ser B Biol Sci 365(1554):2973–2989. https://doi.org/10.1098/rstb.2010.0158
Graves A (2013) Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850. https://arxiv.org/abs/1308.0850
Hagedorn R, Doblas-Reyes FJ, Palmer TN (2005) The rationale behind the success of multi-model ensembles in seasonal forecasting–I. basic concept. Tellus A: Dynamic Meteorology and Oceanography 57(3):219–233. https://doi.org/10.1111/j.1600-0870.2005.00103.x
Hatfield JL, Prueger JH (2015) Temperature extremes: effect on plant growth and development. Weather and Climate Extremes 10:4–10. https://doi.org/10.1016/j.wace.2015.08.001
Haykin S (1994) Neural networks: a comprehensive foundation. Prentice Hall PTR. https://dl.acm.org/doi/book/10.5555/541500
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780. https://www.mitpressjournals.org/doi/abs/10.1162/neco.1997.9.8.1735
Jain RK, Smith KM, Culligan PJ, Taylor JE (2014) Forecasting energy consumption of multi-family residential buildings using support vector regression: investigating the impact of temporal and spatial monitoring granularity on performance accuracy. Appl Energy 123:168–178. https://doi.org/10.1016/j.apenergy.2014.02.057
Jarsjö J, Törnqvist R, Su Y (2017) Climate-driven change of nitrogen retention–attenuation near irrigated fields: multi-model projections for Central Asia. Environ Earth Sci 76(3):1–12. https://doi.org/10.1007/s12665-017-6418-y
Jeong DI, St-Hilaire A, Ouarda TBMJ, Gachon P (2011) Comparison of transfer functions in statistical downscaling models for daily temperature and precipitation over Canada. Stoch Env Res Risk A 26(5):633–653. https://doi.org/10.1007/s00477-011-0523-3
Jiang H, Zou Y, Zhang S, Tang J, Wang Y (2016) Short-term speed prediction using remote microwave sensor data: machine learning versus statistical model. Math Probl Eng 2016:1–13. https://doi.org/10.1155/2016/9236156
Kendon EJ, Jones RG, Kjellström E, Murphy JM (2010) Using and designing GCM–RCM Ensemble regional climate projections. J Clim 23(24):6485–6503. https://doi.org/10.1175/2010JCLI3502.1
Kim S, Hong S, Joh M, Song S-k (2017). DEEPRAIN: ConvLSTM network for precipitation prediction using multichannel radar data. arXiv preprint arXiv:.02316. https://arxiv.org/abs/1711.02316
Kisi O, Sanikhani H (2015a) Modelling long-term monthly temperatures by several data-driven methods using geographical inputs. Int J Climatol 35(13):3834–3846. https://doi.org/10.1002/joc.4249
Kisi O, Sanikhani H (2015b) Prediction of long-term monthly precipitation using several soft computing methods without climatic data. Int J Climatol 35(14):4139–4150. https://doi.org/10.1002/joc.4273
Kong Y-L, Huang Q, Wang C, Chen J, Chen J, He D (2018) Long short-term memory neural networks for online disturbance detection in satellite image time series. Remote Sens 10(3). https://doi.org/10.3390/rs10030452
Krasnopolsky VM, Lin Y (2012) A neural network nonlinear multimodel ensemble to improve precipitation forecasts over continental US. Adv Meteorol 2012:11. https://doi.org/10.1155/2012/649450
Kratzert F, Klotz D, Brenner C, Schulz K, Herrnegger M (2018) Rainfall–runoff modelling using long short-term memory (LSTM) networks. Hydrol Earth Syst Sci 22(11):6005–6022. https://doi.org/10.5194/hess-22-6005-2018
Krishnamurti T, Kishtawal C, LaRow TE, Bachiochi DR, Zhang Z, Williford CE, Gadgil S, Surendran S (1999) Improved weather and seasonal climate forecasts from multimodel superensemble. Science 285(5433):1548–1550. https://doi.org/10.1126/science.285.5433.1548
Krishnamurti TN, Kishtawal CM, Zhang Z, LaRow T, Bachiochi D, Williford E, Gadgil S, Surendran S (2000) Multimodel ensemble forecasts for weather and seasonal climate. J Clim 13(23):4196–4216. https://doi.org/10.1175/1520-0442(2000)013<4196:meffwa>2.0.co;2
Krishnamurti T, Mishra A, Chakraborty A, Rajeevan M (2009) Improving global model precipitation forecasts over India using downscaling and the FSU superensemble. Part I: 1–5-day forecasts. Mon Weather Rev 137(9):2713–2735. https://doi.org/10.1175/2009MWR2736.1
Kumar A, Mitra A, Bohra A, Iyengar G, Durai V (2012) Multi-model ensemble (MME) prediction of rainfall using neural networks during monsoon season in India. Meteorol Appl 19(2):161–169. https://doi.org/10.1002/met.254
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444. https://doi.org/10.1038/nature14539
Li P, Kwon H, Sun L, Lall U, Kao J (2009) A modified support vector machine based prediction model on streamflow at the Shihmen reservoir, Taiwan. Int J Climatol 30(8):1256–1268. https://doi.org/10.1002/joc.1954
Li Q, Wang S, Lee D-K, Tang J, Niu X, Hui P, Gutowski WJ, Dairaku K, McGregor JL, Katzfey J, Gao X, Wu J, Hong S-Y, Wang Y, Sasaki H (2016) Building Asian climate change scenario by multi-regional climate models ensemble. Part II: mean precipitation. Int J Climatol 36(13):4253–4264. https://doi.org/10.1002/joc.4633
Li X, Li Z, Zhang Q, Zhou P, Huang W (2019) Prediction of long-term near-surface temperature based on NA-CORDEX output. Journal of Environmental Informatics Letters 2(1):10–18. https://doi.org/10.3808/jeil.201900012
Lucas-Picher P, Somot S, Déqué M, Decharme B, Alias A (2012) Evaluation of the regional climate model ALADIN to simulate the climate over North America in the CORDEX framework. Clim Dyn 41(5–6):1117–1137. https://doi.org/10.1007/s00382-012-1613-8
Makridakis S, Spiliotis E, Assimakopoulos V (2018) Statistical and machine learning forecasting methods: concerns and ways forward. PLoS One 13(3):e0194889. https://doi.org/10.1371/journal.pone.0194889
Mearns L, McGinnis S, Korytina D, Arritt R (2017) The NA-CORDEX dataset, version 1.0. NCAR climate data gateway, boulder CO. https://doi.org/10.5065/D6SJ1JCH. Accessed 16 May 2017
Mellit A, Pavan AM, Benghanem M (2013) Least squares support vector machine for short-term prediction of meteorological time series. Theor Appl Climatol 111(1):297–307. https://doi.org/10.1007/s00704-012-0661-7
MECP (2011) Climate action: adapting to change, protecting our future. PIBS 8291, pp 16. http://www.climateontario.ca/doc/publications/ClimateAction-AdaptingToChangeProtectingOurFuture2011.pdf. Accessed 22 May 2019
MECP (2018) Preserving and protecting our environment for future generations: a made-in-Ontario environment plan. Retrieved from https://www.ontario.ca/page/made-in-ontario-environment-plan. Accessed 26 Aug 2019
Mitra A, Iyengar G, Durai V, Sanjay J, Krishnamurti T, Mishra A, Sikka D (2011) Experimental real-time multi-model ensemble (MME) prediction of rainfall during monsoon 2008: large-scale medium-range aspects. J Earth Syst Sci 120(1):27–52. https://doi.org/10.1007/s12040-011-0013-5
Mouatadid S, Easterbrook S, Erler AR (2017) A machine learning approach to non-uniform spatial downscaling of climate variables. In 2017 IEEE international conference on data mining workshops (ICDMW). (pp. 332–341). IEEE. https://doi.org/10.1109/ICDMW.2017.49
Neumann JE, Price J, Chinowsky P, Wright L, Ludwig L, Streeter R, Jones R, Smith JB, Perkins W, Jantarasami L, Martinich J (2014) Climate change risks to US infrastructure: impacts on roads, bridges, coastal development, and urban drainage. Clim Chang 131(1):97–109. https://doi.org/10.1007/s10584-013-1037-4
Perera AH, Euler DL, Thompson ID (2011) Ecology of a managed terrestrial landscape: patterns and processes of forest landscapes in Ontario. UBC Press. https://www.ubcpress.ca/ecology-of-a-managed-terrestrial-landscape
Pour SH, Shahid S, Chung E-S, Wang X-J (2018) Model output statistics downscaling using support vector machine for the projection of spatial and temporal changes in rainfall of Bangladesh. Atmos Res 213:149–162. https://doi.org/10.1016/j.atmosres.2018.06.006
Radhika Y, Shashi M (2009) Atmospheric temperature prediction using support vector machines. International Journal of Computer Theory and Engineering 1(1):55. https://doi.org/10.7763/IJCTE.2009.V1.9
Rozante J, Moreira D, Godoy R, Fernandes A (2014) Multi-model ensemble: technique and validation. Geosci Model Dev Discuss 7(3):2933–2959. https://doi.org/10.5194/gmd-7-2333-2014
Sachindra DA, Ahmed K, Rashid MM, Shahid S, Perera BJC (2018) Statistical downscaling of precipitation using machine learning techniques. Atmos Res 212:240–258. https://doi.org/10.1016/j.atmosres.2018.05.022
Salman AG, Heryadi Y, Abdurahman E, Suparta W (2018) Single layer & multi-layer long short-term memory (LSTM) model with intermediate variables for weather forecasting. Procedia Computer Science 135:89–98. https://doi.org/10.1016/j.procs.2018.08.153
Samouly AA, Luong CN, Li Z, Smith S, Baetz B, Ghaith M (2018) Performance of multi-model ensembles for the simulation of temperature variability over Ontario, Canada. Environ Earth Sci 77(13):1–12. https://doi.org/10.1007/s12665-018-7701-2
Samui P (2008) Slope stability analysis: a support vector machine approach. Environ Geol 56(2):255–267. https://doi.org/10.1007/s00254-007-1161-4
Sharda R, Patil RB (1992) Connectionist approach to time series prediction: an empirical test. J Intell Manuf 3(5):317–323. https://doi.org/10.1007/bf01577272
Shi X, Chen Z, Hao W, Yeung DY, Woo WC (2015) Convolutional LSTM Network: a machine learning approach for precipitation nowcasting. In advances in neural information processing systems. (pp. 802–810). https://arxiv.org/abs/1506.04214
Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. https://arxiv.org/abs/1409.3215
Tang J, Li Q, Wang S, Lee D-K, Hui P, Niu X, Gutowski WJ, Dairaku K, McGregor J, Katzfey J, Gao X, Wu J, Hong S-Y, Wang Y, Sasaki H (2016) Building Asian climate change scenario by multi-regional climate models ensemble. Part I: surface air temperature. Int J Climatol 36(13):4241–4252. https://doi.org/10.1002/joc.4628
Tangang FT, Hsieh WW, Tang B (1998) Forecasting regional sea surface temperatures in the tropical Pacific by neural network models, with wind stress and sea level pressure as predictors. J Geophys Res-OCEANS 103(C4):7511–7522. https://doi.org/10.1029/97JC03414
Tran Anh D, Van SP, Dang TD, Hoang LP (2019) Downscaling rainfall using deep learning long short-term memory and feedforward neural network. Int J Climatol 39(10):4170–4188. https://doi.org/10.1002/joc.6066
Tripathi S, Srinivas VV, Nanjundiah RS (2006) Downscaling of precipitation for climate change scenarios: a support vector machine approach. J Hydrol 330(3–4):621–640. https://doi.org/10.1016/j.jhydrol.2006.04.030
Vapnik V (2013) The nature of statistical learning theory. Springer science & business media. https://doi.org/10.1007/978-1-4757-3264-1
Von Storch H, Hewitson B, Mearns L (2000). Review of empirical downscaling techniques. In Regional climate development under global warming. In general technical report no. 4. Conference proceedings regclim spring meeting, Norway. https://www.researchgate.net/publication/259812780_Review_of_empirical_downscaling_techniques
Wallach D, Mearns LO, Ruane AC, Rötter RP, Asseng S (2016) Lessons from climate modeling on the design and use of ensembles for crop modeling. Clim Chang 139(3–4):551–564. https://doi.org/10.1007/s10584-016-1803-1
Wang X, Huang G, Lin Q, Nie X, Cheng G, Fan Y, Li Z, Yao Y, Suo M (2013) A stepwise cluster analysis approach for downscaled climate projection – a Canadian case study. Environ Model Softw 49:141–151. https://doi.org/10.1016/j.envsoft.2013.08.006
Wang X, Huang G, Lin Q, Liu J (2014) High-resolution probabilistic projections of temperature changes over Ontario, Canada. J Clim 27(14):5259–5284. https://doi.org/10.1175/JCLI-D-13-00717.1
Wang X, Huang G, Liu J, Li Z, Zhao S (2015) Ensemble projections of regional climatic changes over Ontario, Canada. J Clim 28(18):7327–7346. https://doi.org/10.1175/jcli-d-15-0185.1
Wang B, Zheng L, Liu DL, Ji F, Clark A, Yu Q (2018) Using multi-model ensembles of CMIP5 global climate models to reproduce observed monthly rainfall and temperature with machine learning methods in Australia. Int J Climatol 38(13):4891–4902. https://doi.org/10.1002/joc.5705
Wang W, Hong T, Xu X, Chen J, Liu Z, Xu N (2019) Forecasting district-scale energy dynamics through integrating building network and long short-term memory learning algorithm. Appl Energy 248:217–230. https://doi.org/10.1016/j.apenergy.2019.04.085
Yoon H, Hyun Y, Ha K, Lee K-K, Kim G-B (2016) A method to improve the stability and accuracy of ANN- and SVM-based time series models for long-term groundwater level predictions. Comput Geosci 90:144–155. https://doi.org/10.1016/j.cageo.2016.03.002
Zhang X, Xiong Z, Zhang X, Shi Y, Liu J, Shao Q, Yan X (2015) Using multi-model ensembles to improve the simulated effects of land use/cover change on temperature: a case study over Northeast China. Clim Dyn 46(3–4):765–778. https://doi.org/10.1007/s00382-015-2611-4
Zhang J, Zhu Y, Zhang X, Ye M, Yang J (2018) Developing a long short-term memory (LSTM) based model for predicting water table depth in agricultural areas. J Hydrol 561:918–929. https://doi.org/10.1016/j.jhydrol.2018.04.065
Zhao H, Magoulès F (2012) A review on the prediction of building energy consumption. Renew Sust Energ Rev 16(6):3586–3592. https://doi.org/10.1016/j.rser.2012.02.049
Zhu N, Xu J, Wang C, Chen Z, Luo Y (2019) Modeling the multiple time scale response of hydrological drought to climate change in the data-scarce inland river basin of Northwest China. Arab J Geosci 12(7):1–16. https://doi.org/10.1007/s12517-019-4404-2
Acknowledgments
This study is supported by the Natural Sciences and Engineering Research Council of Canada (NSERC) and the McMaster Engineering Big Ideas Initiative of McMaster University. We thank Environment Canada for providing observed temperature data. We acknowledge the World Climate Research Programme’s Working Group on Regional Climate, and the Working Group on Coupled Modeling, former coordinating body of CORDEX and responsible panel for CMIP5. We also thank the climate modeling groups (listed in Table 2 of this paper) for producing and making available their model output. We also acknowledge the U.S. Department of Defense ESTCP for its support of the NA-CORDEX data archive.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, X., Li, Z., Huang, W. et al. Performance of statistical and machine learning ensembles for daily temperature downscaling. Theor Appl Climatol 140, 571–588 (2020). https://doi.org/10.1007/s00704-020-03098-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00704-020-03098-3