Please wait a minute...
 
Remote Sensing for Natural Resources    2023, Vol. 35 Issue (1) : 213-221     DOI: 10.6046/zrzyyg.2021450
|
A forecasting method for water table depths in areas with power transmission lines based on remote sensing and deep learning models
ZHANG Ke1,2,3(), ZHANG Gengsheng1,2, WANG Ning4(), WEN Jing4, LI Yu1,2, YANG Jun5
1. State Grid Electric Power Research Institute, Hefei 230088, China
2. Anhui NARI Jiyuan Electric Power System Tech Co., Ltd, Hefei 230088, China
3. University of Science and Technology of China, Hefei 230088, China
4. China Aero Geophysical Survey and Remote Sensing Center for Natural Resources, Beijing 100083, China
5. State Grid Hangzhou Power Supply Company, Zhejiang Electric Power Co.,Ltd.,Hangzhou 310000, China
Download: PDF(4699 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

Areas with power transmission lines have been frequently struck by flood disasters in recent years. Therefore, forecasting the water table depths in these areas is critical to the safety of these areas. This study forecasted the water table depth using remote sensing satellite products and observed meteorological and hydrological data. Based on the meteorological and hydrological data, this study forecast the daily and monthly water table depths using the long short-term memory (LSTM), gated recurrent unit (GRU), long short-term memory-seq2seq (LSTM-S2S), and feedforward neural network (FFNN) models. The results indicate that the LSTM-S2S and FFNN models delivered the best and the worst performances, respectively. Meanwhile, the LSTM, GRU, and LSTM-S2S models performed well in forecasting both daily and monthly water table depths, with their forecasts of daily water table depths having a higher coefficient of determination (R2) and a Nash-Sutcliffe efficiency coefficient (NSE) than those of monthly water table depths. Therefore, the method presented in this study can be used to forecast the future daily and monthly water table depths in areas with power transmission lines.
Keywords deep learning model      GRU      LSTM-S2S      LSTM      water table depth     
ZTFLH:  TP79  
Issue Date: 20 March 2023
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Ke ZHANG
Gengsheng ZHANG
Ning WANG
Jing WEN
Yu LI
Jun YANG
Cite this article:   
Ke ZHANG,Gengsheng ZHANG,Ning WANG, et al. A forecasting method for water table depths in areas with power transmission lines based on remote sensing and deep learning models[J]. Remote Sensing for Natural Resources, 2023, 35(1): 213-221.
URL:  
https://www.gtzyyg.com/EN/10.6046/zrzyyg.2021450     OR     https://www.gtzyyg.com/EN/Y2023/V35/I1/213
Fig.1  Study area
Fig.2  RNN network
Fig.3  LSTM network
Fig.4  LSTM-S2S network
Fig.5  Sensitive analysis on daily measured and simulated water table depth using the proposed models: FFNN, LSTM,GRU, LSTM-S2S
Fig.6  Comparison of daily measured and simulated water table depth using the proposed models
模型 迭代
次数		 丢弃率 学习率 均方根
误差		 决定
系数		 效率
系数		 损失
LSTM-S2S 14 000 0.3 0.001 0.03 0.92 0.92 16.07
LSTM 18 000 0.3 0.001 0.05 0.89 0.85 16.80
GRU 1 800 0.5 0.01 0.05 0.85 0.84 19.34
FFNN 10 000 0.5 0.001 0.11 0.94 0.14 128.33
Tab.1  Best performance statistics in different models
Fig.7  Comparison of monthly measured and simulated water table depth using the proposed models
模型 均方根误差 决定系数 效率系数 损失
LSTM 1.04 0.65 0.60 15.21
GRU 0.83 0.75 0.74 23.58
LSTM-S2S 0.89 0.71 0.71 4.70
Tab.2  Performance statistics of monthly data in LSTM, GRU, and LSTM-S2S models
[1] Wang J, Shi P, Jiang P, et al. Application of BP neural network algorithm in traditional hydrological model for flood forecasting[J]. Water, 2017, 9:48.
doi: 10.3390/w9010048 url: http://www.mdpi.com/2073-4441/9/1/48
[2] Batelaan O, De Smedt F, Triest L, et al. Regional groundwater discharge:Phreatophyte mapping,groundwater modelling and impact analysis of land-use change[J]. Journal of Hydrology, 2003, 275:86-108.
doi: 10.1016/S0022-1694(03)00018-0 url: https://linkinghub.elsevier.com/retrieve/pii/S0022169403000180
[3] Bhattacharjee N V, Tollner E W, et al. Improving management of windrow composting systems by modeling runoff water quality dynamics using recurrent neural network[J]. Ecological Modelling, 2016, 339:68-76.
doi: 10.1016/j.ecolmodel.2016.08.011 url: https://linkinghub.elsevier.com/retrieve/pii/S0304380016303106
[4] Kratzert F, Klotz D, Brenner C, et al. Rainfall-runoff modelling using Long Short-Term Memory (LSTM) networks[J]. Hydrology and Earth System Sciences, 2018, 22:6005-6022.
doi: 10.5194/hess-22-6005-2018 url: https://hess.copernicus.org/articles/22/6005/2018/
[5] Schmidhuber J. Deep learning in neural networks:An overview[J]. Neural Networks, 2015, 61:85-117.
pmid: 25462637
[6] Halevy A, Norvig P, Pereira F. The unreasonable effective-ness of data[J]. IEEE Intelligent Systems, 2009, 24(2):8-12.
[7] Zhang J, Zhu Y, Zhang X, et al. Developing a long short-term memory (LSTM) based model for predicting water table depth in agricultural areas[J]. Journal of Hydrology, 2018, 561:918-929.
doi: 10.1016/j.jhydrol.2018.04.065 url: https://linkinghub.elsevier.com/retrieve/pii/S0022169418303184
[8] Kao I, Zhou Y, Chang L, et al. Exploring a long short-term memory based encoder-decoder framework for multi-step-ahead flood forecasting[J]. Journal of Hydrology, 2020, 583:124631.
doi: 10.1016/j.jhydrol.2020.124631 url: https://linkinghub.elsevier.com/retrieve/pii/S0022169420300913
[9] Xiang Z, Yan J, Demir I, et al. A rainfall runoff model With LSTM based sequence to sequence learning[J]. Water Resources Research, 2020, 56:1-17.
[10] Shen Y, Xiong A Y, Wang Y, et al. Performance of high-resolution satellite precipitation products over China[J]. Journal of Geophysical Research, 2010, 115:1-17.
[11] Rumelhart D E, Hinton G E, Williams R J, et al. Learning representations by back-propagating errors[J]. Nature, 1986, 323:533-536.
doi: 10.1038/323533a0
[12] Hochreiter S. The vanishing gradient problem during learning recurrent neural nets and problem solutions[J]. International Journal of Uncertainty Fuzziness and Knowledge-based Systems, 1998, 6:107-116.
doi: 10.1142/S0218488598000094 url: https://www.worldscientific.com/doi/abs/10.1142/S0218488598000094
[13] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9 (8):1735-1780.
doi: 10.1162/neco.1997.9.8.1735 pmid: 9377276
[14] GersF A, Schmidhuber J, Cummins F, et al. Learning to forget:Continual prediction with LSTM[J]. Neural Computation, 2000, 12:2451-2471.
pmid: 11032042
[15] Cho K, van Merrienboer B, Bahdanau D, et al. On the properties of neural machine translation:Encoder-decoder approaches[J]. In Proceedings of SSST-8,Eighth Workshop on Syntax,Semantics and Structure in Statistical Translation, 2014,103-111.
[16] Gao S, Huang Y, Zhang S, et al. Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation[J]. Journal of Hydrology, 2020:125188,doi:https://doi.org/10.1016/j.jhydrol.2020.125188.
doi: https://doi.org/10.1016/j.jhydrol.2020.125188
[1] YU Wen, GONG Huili, CHEN Beibei, ZHOU Chaofan. Spatial-temporal evolution characteristics and prediction of land subsidence in the eastern plain of Beijing[J]. Remote Sensing for Natural Resources, 2022, 34(4): 183-193.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
京ICP备05055290号-2
Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech