Numerical Forecast Correction of Temperature and Wind Using a Single-Station Single-Time Spatial LightGBM Method
Abstract
:1. Introduction
- (1)
- A novel spatial lightGBM method is proposed to capture local spatial information of observation stations for improved correction performance.
- (2)
- A single-station single-time training strategy is used for spatial lightGBM model learning. This strategy can reflect the differences in the geographic location of different stations because of decoupling the spatiotemporal correlation of stations.
- (3)
- The mechanism of the single-station single-time training strategy is explained by calculating the importance of each meteorological element to the temperature prediction of the spatial lightGBM. Our strategy can reflect the differences of different stations due to topographic effects.
2. Data and Sample Construction
2.1. Model Data
2.2. Observation Data
2.3. Sample Construction
3. Method
3.1. LightGBM Model
3.2. The Single-Station Single-Time Spatial LightGBM
4. Results and Discussion
4.1. Evaluation Index
- The RMSE is defined as:
- 2.
- The accuracy rate of less than 2 °C and 1 °C is defined as follows:
- 3.
- The wind speed classification forecast accuracy rate is defined as follows:
4.2. Experimental Results and Discussion
4.2.1. Correction Performance Analysis
4.2.2. Comparison with Competing Correction Methods
4.2.3. Advantages of the Single-Station Single-Time Strategy
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Xue, J.; Liu, Y. Numerical weather prediction in China in the new century—Progress, problems and prospects. Adv. Atmos. Sci. 2007, 24, 1099–1108. [Google Scholar] [CrossRef]
- Xue, H.L.; Shen, X.S.; Chou, J.F. A forecast error correction method in numerical weather prediction by using recent multiple-time evolution data. Adv. Atmos. Sci. 2013, 30, 1249–1259. [Google Scholar] [CrossRef]
- Li, H.; Yu, C.; Xia, J.; Wang, Y.; Zhu, J.; Zhang, P. A Model Output Machine Learning Method for Grid Temperature Forecasts in the Beijing Area. Adv. Atmos. Sci. 2019, 36, 112–126. [Google Scholar] [CrossRef]
- Półrolniczak, M.; Kolendowicz, L.; Czernecki, B.; Taszarek, M.; Tóth, G. Determination of Surface Precipitation Type Based on the Data Fusion Approach. Adv. Atmos. Sci. 2021, 38, 387–399. [Google Scholar] [CrossRef]
- Kunić, Z.; Ženko, B.; Boshkoska, B.M. FOCUSED–Short-Term Wind Speed Forecast Correction Algorithm Based on Successive NWP Forecasts for Use in Traffic Control Decision Support Systems. Sensors 2021, 21, 3405. [Google Scholar] [CrossRef]
- Li, L.; Xu, Y.; Yan, L.; Wang, S.; Liu, G.; Liu, F. A Regional NWP Tropospheric Delay Inversion Method Based on a General Regression Neural Network Model. Sensors 2020, 20, 3167. [Google Scholar] [CrossRef] [PubMed]
- Wang, P.; Li, J.; Schmit, T.J. The impact of low latency satellite sounder observations on local severe storm forecasts in regional NWP. Sensors 2020, 20, 650. [Google Scholar] [CrossRef] [Green Version]
- Howard, T.; Clark, P. Correction and downscaling of NWP wind speed forecasts. Meteorol. Appl. 2010, 14, 105–116. [Google Scholar] [CrossRef]
- Verspeek, J. Improved ASCAT Wind Retrieval Using NWP Ocean Calibration. IEEE Trans. Geosci. Remote Sens. 2012, 50, 2488–2494. [Google Scholar] [CrossRef] [Green Version]
- Dong, L.; Ren, L.; Gao, S.; Gao, Y.; Liao, X. Studies on wind farms ultra-short term NWP wind speed correction methods. In Proceedings of the 2013 25th Chinese Control and Decision Conference (CCDC), Guiyang, China, 25–27 May 2013. [Google Scholar]
- Auligné, T.; McNally, A.P.; Dee, D.P. Adaptive bias correction for satellite data in a numerical weather prediction system. Q. J. R. Meteorol. Soc. 2007, 133, 631–642. [Google Scholar] [CrossRef]
- Wang, B.; Lu, J.; Yan, Z.; Luo, H.; Li, T.; Zheng, Y.; Zhang, G. Deep Uncertainty Quantification: A Machine Learning Approach for Weather Forecasting. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, UK, 19–23 August 2018. [Google Scholar]
- Lauret, P.; Diagne, H.M.; David, M. A Neural Network Post-processing Approach to Improving NWP Solar Radiation Forecasts. Energy Procedia 2014, 57, 1044–1052. [Google Scholar] [CrossRef]
- Liu, Y.; Wang, Y.; Li, L.; Han, S.; Infield, D. Numerical weather prediction wind correction methods and its impact on computational fluid dynamics based wind power forecasting. J. Renew. Sustain. Energy 2016, 8, 770–778. [Google Scholar] [CrossRef] [Green Version]
- Buhan, S.; Özkazanç, Y.; Çadırcı, I. Wind Pattern Recognition and Reference Wind Mast Data Correlations With NWP for Improved Wind-Electric Power Forecasts. IEEE Trans. Ind. Inform. 2017, 12, 991–1004. [Google Scholar] [CrossRef]
- McCandless, T.; Jiménez, P.A. Examining the Potential of a Random Forest Derived Cloud Mask from GOES-R Satellites to Improve Solar Irradiance Forecasting. Energies 2020, 13, 1671. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Du, P. Ensemble Machine Learning-Based Wind Forecasting to Combine NWP Output With Data From Weather Station. IEEE Trans. Sustain. Energy 2019, 10, 2133–2141. [Google Scholar] [CrossRef]
- Yanyan, K.; Haochen, L.; Jiangjiang, X.; Yingxin, Z. Post-processing for NWP Outputs Based on Machine Learning for 2022 Winter Olympics Games over Complex Terrain, EGU General Assembly 2020. In Proceedings of the EGU General Assembly Conference, Online, 4–8 May 2020. [Google Scholar] [CrossRef]
- Devi, R.M.; Prasetya, T.A.E.; Indriani, D. Spatial and temporal analysis of land surface temperature change on new britain island. Int. J. Remote Sens. Earth Sci. (IJReSES) 2020, 17, 45. [Google Scholar] [CrossRef]
- Nezhad, M.M.; Groppi, D.; Marzialetti, P.; Fusilli, L.; Laneve, G.; Cumo, F.; Garcia, D.A. Wind energy potential analysis using Sentinel−1 satellite: A review and a case study on Mediterranean islands. Renew. Sustain. Energy Rev. 2019, 109, 499–513. [Google Scholar] [CrossRef]
- Kim, S. Jeju Island climate modeling using multiple linear regression analysis. J. Anal. Appl. Math. 2019, 13, 118–136. [Google Scholar]
- Muksin, D.; Simbolon, D.; Wiyono, E.S.; Sondita, M.F.A. Effect of global climate (ENSO) on regional climate (rainfall and air temperature) in the Morotai Island region. Adv. Environ. Sci. 2020, 12, 97–109. [Google Scholar]
- Ke, G.; Meng, Q.; Finley, T.; Wang, T.; Chen, W.; Ma, W.; Liu, T.Y. LightGBM: A highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. 2017, 30, 3146–3154. [Google Scholar]
- Friedman, J.H. Greedy Function Approximation: A Gradient Boosting Machine. Ann. Stat. 2001, 29, 1189–1232. [Google Scholar] [CrossRef]
- Zhong, J.; Zhang, X.; Gui, K.; Wang, Y.; Che, H.; Shen, X.; Zhang, W. Robust prediction of hourly PM2.5 from meteorological data using LightGBM. Natl. Sci. Rev. 2021. [Google Scholar] [CrossRef] [PubMed]
- Mousavi, S.M.; Beroza, G.C. Bayesian-deep-learning estimation of earthquake location from single-station observations. arXiv 2019, arXiv:1912.01144. [Google Scholar] [CrossRef]
Data Types | Predictors | Abbreviations |
---|---|---|
Predictors at the surface | 10-m U-wind component | 10 U |
10-m V-wind component | 10 V | |
2-m dewpoint temperature | 2 D | |
2-m temperature | 2 T | |
Convective available potential energy | CAPE | |
Mean sea level pressure | MSL | |
Low cloud cover | LCC | |
Predictors at different pressure levels (200 kpa, 400 kpa, 500 kpa, 700 kpa, 850 kpa, 925 kpa, 950 kpa) | Geopotential height | GH |
Relative humidity | RH | |
Temperature | T | |
U component of wind | U | |
V component of wind | V | |
Vertical velocity | W | |
Geopotential height | GH |
Element | Abbreviation | Element | Abbreviation |
---|---|---|---|
2-m wind direction | Wd2 m | Minimum temperature | Tmin |
2-m wind speed | Ws2 m | Relative humidity | RH |
Temperature | TT | Station pressure | Pp |
Maximum temperature | Tmax | Hourly precipitation | R1 H |
Proposed Model | Original LightGBM | Random Forest | GBDT | |
---|---|---|---|---|
Cost Time (s) | 19.0 | 8.5 | 1772.5 | 605.3 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Tang, R.; Ning, Y.; Li, C.; Feng, W.; Chen, Y.; Xie, X. Numerical Forecast Correction of Temperature and Wind Using a Single-Station Single-Time Spatial LightGBM Method. Sensors 2022, 22, 193. https://doi.org/10.3390/s22010193
Tang R, Ning Y, Li C, Feng W, Chen Y, Xie X. Numerical Forecast Correction of Temperature and Wind Using a Single-Station Single-Time Spatial LightGBM Method. Sensors. 2022; 22(1):193. https://doi.org/10.3390/s22010193
Chicago/Turabian StyleTang, Rongnian, Yuke Ning, Chuang Li, Wen Feng, Youlong Chen, and Xiaofeng Xie. 2022. "Numerical Forecast Correction of Temperature and Wind Using a Single-Station Single-Time Spatial LightGBM Method" Sensors 22, no. 1: 193. https://doi.org/10.3390/s22010193
APA StyleTang, R., Ning, Y., Li, C., Feng, W., Chen, Y., & Xie, X. (2022). Numerical Forecast Correction of Temperature and Wind Using a Single-Station Single-Time Spatial LightGBM Method. Sensors, 22(1), 193. https://doi.org/10.3390/s22010193