Journal of Jilin University(Engineering and Technology Edition) ›› 2022, Vol. 52 ›› Issue (3): 675-683.doi: 10.13229/j.cnki.jdxbgxb20210608

Previous Articles    

Spatio⁃temporal model of soil moisture prediction integrated with transfer learning

Xue-zhi WANG1(),Qing-liang LI2,Wen-hui LI1()   

  1. 1.College of Computer Science and Technology,Jilin University,Changchun 130012,China
    2.School of Computer Science and Technology,Changchun Normal University,Changchun 130032,China
  • Received:2021-07-04 Online:2022-03-01 Published:2022-03-08
  • Contact: Wen-hui LI E-mail:wxz14@mails.jlu.edu.cn;liwh@mails.jlu.edu.cn

Abstract:

Using the deep learning methods can solve the model over-fitting caused by less observation data, and improve the prediction accuracy. This paper proposes spatio-temporal model of soil moisture prediction integrated with transfer learning. Firstly, the EAR5-land dataset is used as the source model. Then three-dimensional layer convolution is used to extract the spatial characteristics of the lag time of the soil moisture, and the long short-time memory network is integrated to extract the temporal characteristics. Third, the network model is pre-trained. Finally, the fine-tune method is applied to adjust the network parameters in the SMAP dataset for soil moisture prediction. The experimental results show that the proposed model has the better prediction results than the convolutional neural network, long short-term memory network and PredRNN. Meanwhile the method of transfer learning can improve the prediction accuracy.

Key words: computer application, soil moisture prediction, convolutional neural network, long short-term memory networks, transfer learning

CLC Number: 

  • TP391

Fig.1

Flow chart of spatio-temporal model of soil moisture integrated with transfer learning"

Fig.2

Spatio-temporal deep learning model"

Table 1

Effect of setting different hyper-parameters on our model"

学习率batch size迭代次数R2
0.001128500.873
0.01128500.864
0.0001128500.868
0.00164500.869
0.001256500.862
0.0011281000.865
0.001128250.868

Fig.3

Scatter plot of predicted and observed values"

Fig.4

Performance spatial distribution diagram of predicted and observed values"

Fig.5

Average distribution map of soilmoisture in SMAP"

Fig.6

Scatter plot of predicted and observed valuesafter incorporating transfer learningof 3DCNN-LSTM model"

Fig.7

Change of performance distribution chart of 3DCNN-LSTM model after incorporatingtransfer learning"

Table 2

Testing results of integrating transfer learning into the different models"

模型RMSEMAEMSER2
CNN0.0490.6281.0830.871
LSTM0.0470.6010.9970.890
PredRNN0.0410.4160.6480.902

冻结卷积层

冻结LSTM

0.045

0.047

0.489

0.512

0.695

0.728

0.900

0.898

3DCNN-LSTM0.0390.3930.5820.913
1 Yu Feng, Cui Ning-bo, Hao Wei-ping, et al. Estimation of soil temperature from meteorological data using different machine learning models[J]. Geoderma, 2019, 338: 67-77.
2 Sanikhania H, Deo R C, Yaseen Z M, et al. Non-tuned data intelligent model for soil temperature estimation: a new approach[J]. Geoderma, 2018, 330: 52-64.
3 Yang J M, Busen H, Scherb H, et al. Modeling of radon exhalation from soil influenced by environmental parameters[J]. Science of the Total Environment, 2019, 656: 1304-1311.
4 Bhadani P, Vashisht V. Soil moisture, temperature and humidity measurement using arduino[C]∥2019 9th International Conference on Cloud Computing, Data Science & Engineering, Amity Univ, Noida, India, 2019: 567-571.
5 Hu Guo-jie, Zhao Lin, Wu Xiao-dong, et al. An analytical model for estimating soil temperature profiles on the Qinghai-Tibet plateau of China[J]. Journal of Arid Land, 2016, 8(2): 232-240.
6 Liang L L, Riveros-Iregui D A, Emanuel R E, et al. A simple framework to estimate distributed soil temperature from discrete air temperature measurements in data-scarce regions[J]. Journal of Geophysical Research-Atmospheres, 2014, 119(2): 407-417.
7 Entekhabi D, Njoku E G, O"Neill P E, et al. The soil moisture active passive (SMAP) mission[J]. Proceedings of the IEEE, 2010, 98(5): 704-716.
8 Fang Kuai, Shen Chao-peng, Kifer D, et al. Prolongation of SMAP to spatio-temporally seamless coverage of continental U.S. using a deep learning neural network[J]. Geophysical Research Letters, 2017, 44(21): 11030-11039.
9 Fang Kuai, Shen Chao-peng. Near-real-time forecast of satellite-based soil moisture using long short-term memory with an adaptive data integration kernel[J]. Journal of Hydrometeorology, 2020, 21(3): 399-413.
10 Reichstein M, Camps-Valls G, Stevens B, et al. Deep learning and process understanding for data-driven Earth system science[J]. Nature, 2019, 566(7743): 195-204.
11 Cobaner M, Citakoglu H, Kisi O, et al. Estimation of mean monthly air temperatures in Turkey[J]. Computers and Electronics in Agriculture, 2014, 109: 71-79.
12 Kisi O, Sanikhani H. Modelling long-term monthly temperatures by several data-driven methods using geographical inputs[J]. International Journal of Climatology, 2015, 35(13): 3834-3846.
13 Kisi O, Kim S, Shiri J. Estimation of dew point temperature using neuro-fuzzy and neural network techniques[J]. Theoretical & Applied Climatology, 2013, 114(3/4): 365-373.
14 Kisi O, Sanikhani H. Prediction of long-term monthly precipitation using several soft computing methods without climatic data[J]. International Journal of Climatology, 2015, 35(14): 4139-4150.
15 Mohammadi K, Shamshirband S, Kamsin A, et al. Identifying the most significant input parameters for predicting global solar radiation using an ANFIS selection procedure[J]. Renewable and Sustainable Energy Reviews, 2016, 63: 423-434.
16 Sobayo R, Wu H H, Ray R L, et al. Integration of convolutional neural network and thermal images into soil moisture estimation[C]∥1st International Conference on Data Intelligence and Security, South Padre Island, USA, 2018: 207-210.
17 Pan B X, Hsu K H, Aghakouchak A, et al. Improving precipitation estimation using convolutional neural network[J]. Water Resources Research, 2019, 55(3): 2301-2321.
18 Li Qing-liang, Zhao Yang, Yu Fan-hua. A novel multichannel long short-term memory method with time series for soil temperature modeling[J]. IEEE Access, 2020, 8: 182026-182043.
19 Hu Qing-hua, Zhang Ru-jia, Zhou Yu-can. Transfer learning for short-term wind speed prediction with deep neural networks[J]. Renewable Energy, 2016, 85: 83-95.
20 Chen Yu-wen, Huang Xiao-meng, Yi Li, et al. Improving machine learning-based weather forecast post-processing with clustering and transfer learning[J/OL]. [2021-06-19].
21 Rasp S, Dueben P D, Scher S, et al. WeatherBench: a benchmark dataset for data-driven weather forecasting[J/OL]. [2021-06-21].
22 Cao B, Gruber S, Zheng D H, et al. The ERA5-land soil temperature bias in permafrost regions[J]. Cryosphere, 2020, 14(8): 2581-2595.
23 Wang Yun-bo, Long Ming-sheng, Wang Jian-min, et al. PredRNN: recurrent neural networks for predictive learning using spatiotemporal LSTMs[C]∥31st Annual Conference on Neural Information Processing Systems, Long Bench, CA, 2017:879-888.
[1] Lin MAO,Feng-zhi REN,Da-wei YANG,Ru-bo ZHANG. Two⁃way feature pyramid network for panoptic segmentation [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(3): 657-665.
[2] Xian-tong LI,Wei QUAN,Hua WANG,Peng-cheng SUN,Peng-jin AN,Yong-xing MAN. Route travel time prediction on deep learning model through spatiotemporal features [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(3): 557-563.
[3] Xue WANG,Zhan-shan LI,Ying-da LYU. Medical image segmentation based on multi⁃scale context⁃aware and semantic adaptor [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(3): 640-647.
[4] Ji-hong OUYANG,Ze-qi GUO,Si-guang LIU. Dual⁃branch hybrid attention decision net for diabetic retinopathy classification [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(3): 648-656.
[5] Xiang-jun LI,Jie-ying TU,Zhi-bin ZHAO. Validity classification of melting curve based on multi⁃scale fusion convolutional neural network [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(3): 633-639.
[6] Su-ming KANG,Ye-e ZHANG. Hadoop⁃based local timing link prediction algorithm across social networks [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(3): 626-632.
[7] Long ZHANG,Tian-peng XU,Chao-bing WANG,Jian-yu YI,Can-zhuang ZHEN. Gearbox fault diagnosis baed on convolutional gated recurrent network [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(2): 368-376.
[8] Wen-zhi GAO,Yan-jun WANG,Xin-wei WANG,Pan ZHANG,Yong LI,Yang DONG. Real⁃time diagnosis for misfire fault of diesel engine based on convolutional neural network [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(2): 417-424.
[9] You QU,Wen-hui LI. Single-stage rotated object detection network based on anchor transformation [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(1): 162-173.
[10] Liang DUAN,Chun-yuan SONG,Chao LIU,Wei WEI,Cheng-ji LYU. State recognition in bearing temperature of high-speed train based on machine learning algorithms [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(1): 53-62.
[11] Hong-wei ZHAO,Dong-sheng HUO,Jie WANG,Xiao-ning LI. Image classification of insect pests based on saliency detection [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(6): 2174-2181.
[12] Zhou-zhou LIU,Qian-yun ZHANG,Xin-hua MA,Han PENG. Compressed sensing signal reconstruction based on optimized discrete differential evolution algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(6): 2246-2252.
[13] Yan-lei XU,Run HE,Yu-ting ZHAI,Bin ZHAO,Chen-xiao LI. Weed identification method based on deep transfer learning in field natural environment [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(6): 2304-2312.
[14] Sheng-sheng WANG,Jing-yu CHEN,Yi-nan LU. COVID⁃19 chest CT image segmentation based on federated learning and blockchain [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(6): 2164-2173.
[15] Dong-ming SUN,Liang HU,Yong-heng XING,Feng WANG. Text fusion based internet of things service recommendation for trigger⁃action programming pattern [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(6): 2182-2189.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!