基于遥感和深度学习的输电线路地表水深预测

doi:10.6046/zrzyyg.2021450

摘要
图/表
参考文献
相关文章
Metrics

全文: PDF(4699 KB)

HTML
输出: BibTeX | EndNote (RIS)

摘要

近年来很多输电线路区域受到洪水灾害的影响,因此,预测输电线区域地表水深对于输电线区域安全至关重要。本研究通过遥感卫星产品、观测气象资料和水文数据来预测地表水深。该研究首先利用长短期记忆网络(long short-term memory,LSTM)、门控循环单元网络(gated recurrent unit,GRU)、编码器和解码器的长短期记忆网络(long short-term memory-seq2seq,LSTM-S2S)和前馈神经网络(feedforward neural network,FFNN)模型针对气象资料和水文数据进行了日和月尺度数据模拟。结果表明,在4个模型中,LSTM-S2S是预测地表水深的最佳模型; 相比之下,FFNN的表现最差; LSTM,GRU和LSTM-S2S模型在日和月尺度数据模拟中均表现良好。在LSTM,GRU和LSTM-S2S模型中,日尺度模拟的决定系数(coefficient of determination,R²)和纳什效率系数(Nash-Sutcliffe efficiency coefficient,NSE)均优于月尺度。因此,本研究中的方法可以用来模拟未来电力传输线地区的日和月尺度的地表水深。

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张可
	张庚生
	王宁
	温静
	李宇
	杨俊

关键词 ：深度学习模型, GRU, LSTM-S2S, LSTM, 地表水深

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.

Key words： deep learning model GRU LSTM-S2S LSTM water table depth

收稿日期: 2021-12-20 出版日期: 2023-03-20

ZTFLH:

TP79

基金资助:国家电网公司总部科技项目“无人区输电线路全景物联网络技术及共享型智慧感知平台研究”(5500-202140127A)

通讯作者: 王宁(1988-),男,高级工程师,主要从事航空物探遥感数据处理及应用研究。Email: ning.-wang@163.com。

作者简介: 张可(1983-),男,高级工程师,主要从事电气自动化及人工智能应用研究。zhangke2@sgepri.sgc。

引用本文:

张可, 张庚生, 王宁, 温静, 李宇, 杨俊. 基于遥感和深度学习的输电线路地表水深预测[J]. 自然资源遥感, 2023, 35(1): 213-221.
ZHANG Ke, ZHANG Gengsheng, WANG Ning, WEN Jing, LI Yu, YANG Jun. A forecasting method for water table depths in areas with power transmission lines based on remote sensing and deep learning models. Remote Sensing for Natural Resources, 2023, 35(1): 213-221.

链接本文:

https://www.gtzyyg.com/CN/10.6046/zrzyyg.2021450 或 https://www.gtzyyg.com/CN/Y2023/V35/I1/213

Fig.1 研究区域

Fig.2 RNN网络

Fig.3 LSTM网络

Fig.4 LSTM-S2S 网络

Fig.5 使用本实验模型对每日测量和模拟的地表水深进行敏感性分析

Fig.6 使用实验模型对日测量和模拟的地表水深进行比较

Tab.1 不同模型中的最佳性能参数表

Fig.7 使用实验模型对月测量和仿真的地表水深进行比较

Tab.2 LSTM、GRU和LSTM-S2S模型中月度数据的性能

[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
[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
[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
[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
[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
[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
[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
[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]	于文, 宫辉力, 陈蓓蓓, 周超凡. 北京东部平原区地面沉降时空演化特征及预测[J]. 自然资源遥感, 2022, 34(4): 183-193.

Viewed

Full text

Abstract

Cited

Shared

Discussed