All Issue

2019 Vol.61, Issue 6 Preview Page
RNN-LSTM Based Soil Moisture Estimation Using Terra MODIS NDVI and LST

Terra MODIS NDVI 및 LST 자료와 RNN-LSTM을 활용한 토양수분 산정

Wonjin Janga
,
Yonggwan Leeb
,
Jiwan Leec†
,
Seongjoon Kimd
장 원진a
,
이 용관b
,
이 지완c†
,
김 성준d
aGraduate Student, Department of Civil, Environmental, and Plant Engineering, Konkuk University
bDoctoral Student, Department of Civil, Environmental, and Plant Engineering, Konkuk University
cPhD Candidate, Department of Civil, Environmental, and Plant Engineering, Konkuk University
dProfessor, School of Civil, Environmental, and Plant Engineering, Konkuk University
a건국 대학교 토목 환경 환경 공학과 졸업생
b건국 대학교 토목 환경 공학부 박사 과정생
c건국 대학교 토목 환경 공학과 cPhD 후보
d건국 대학교 토목 환경 환경 공학부 교수
† Corresponding author Tel.: +82-2-444-0186 Fax: +82-2-444-0186 E-mail: closer01@konkuk.ac.kr
2019. pp. 123-132
PDF XML Citation
Abstract

This study is to estimate the spatial soil moisture using Terra MODIS (Moderate Resolution Imaging Spectroradiometer) satellite data and machine learning technique. Using the 3 years (2015~2017) data of MODIS 16 days composite NDVI (Normalized Difference Vegetation Index) and daily Land Surface Temperature (LST), ground measured precipitation and sunshine hour of KMA (Korea Meteorological Administration), the RDA (Rural Development Administration) 10 cm~30 cm average TDR (Time Domain Reflectometry) measured soil moisture at 78 locations was tested. For daily analysis, the missing values of MODIS LST by clouds were interpolated by conditional merging method using KMA surface temperature observation data, and the 16 days NDVI was linearly interpolated to 1 day interval. By applying the RNN-LSTM (Recurrent Neural Network-Long Short Term Memory) artificial neural network model, 70% of the total period was trained and the rest 30% period was verified. The results showed that the coefficient of determination (R2), Root Mean Square Error (RMSE), and Nash-Sutcliffe Efficiency were 0.78, 2.76%, and 0.75 respectively. In average, the clay soil moisture was estimated well comparing with the other soil types of silt, loam, and sand. This is because the clay has the intrinsic physical property for having narrow range of soil moisture variation between field capacity and wilting point.

Keywords
RNN-LSTM
MODIS
NDVI
LST
soil moisture
tensorflow
References

REFERENCES

1
D. Aubert, C. Loumagne and L. Oudin, Journal of Hydrology, Sequential assimilation of soil moisture and streamflow data in a conceptual rainfall-runoff model., 280(1-4); 145-161 (2003)10.1016/s0022-1694(03)00229-4
2
R. D. Barling, I. D. Moore and R. B. Grayson, Water Resources ResearchA quasi-dynamic wetness index for characterizing the spatial distribution of zones of surface saturation and soil water content., 30(4); 1029-1044 (1994)10.1029/93wr03346
3
A. Dai, K. E. Trenberth and T. Qian, Journal of Hydrometeorology, A global dataset of Palmer Drought Severity Index for 1870-2002: Relationship with soil moisture and effects of surface warming., 5(6); 1117-1130 (2004)10.1175/jhm-386.1
4
T. J. Farrar, S. E. Nicholson and A. R. Lare, Remote Sensing of Environment , The influence of soil type on the relationships between NDVI, rainfall, and soil moisture in semiarid Botswana. II. NDVI response to soil moisture., 50(2); 121-133 (1994)10.1016/0034-4257(94)90039-6
5
F. A. Gers, N. N. Schraudolph and J. Schmidhuber, Journal of Machine Learning Research, Learning precise timing with LSTM recurrent networks., 3(8); 115-143 (2002)
6
R. R. Gillies, W. P. Kustas and K. S. Humes, International Journal of Remote Sensing, A verification of the ‘triangle’ method for obtaining surface soil water content and energy fluxes from remote measurements of the Normalized Difference Vegetation Index (NDVI) and surface., 18(15); 3145-3166 (1997)10.1080/014311697217026
7
A. R. Huete, C. Justice and W. J. D. van Leeuwen, MODIS Vegetation Index (MOD13) Algorithm Theoretical Basis Document Version 3. (1999)
8
J. S. Hutchinson, T. J. Vought and S. L. Hutchinson, Papers and Proceedings of Applied Geography ConferencesContinuous soil moisture mapping using MODIS NDVI and LST products., 29; 140 (2006)
9
J. Y. Joo, M. H. Choi, S. W. Jung and S. O. Lee, Journal of the Korean Society of Civil Engineers, Prediction of soil moisture using hydrometeorological data in selmacheon., 30(5B); 437-444, (in Korean). (2010)
10
C. G. Jung, Y. G. Lee, Y. H. Cho and S. J. Kim, Remote Sensing, A study of spatial soil moisture estimation using a multiple linear regression model and MODIS Land surface temperature data corrected by conditional merging., 9(8); 870 (2017)10.3390/rs9080870
11
B. S. Kim and B. K. Jung, Hydrological ProcessesFlood simulation using the gauge-adjusted radar rainfall and physics-based distributed hydrologic model., 22(22); 4400-4414 (2016)10.1002/hyp.704325855820
12
D. S. Kim, N. W. Park, N. Kim, K. J. Kim, S. J. Lee, Y. H. Kim, J. W. Kim, D. Y. Shin, Y. H. Cho and Y. W. Lee, Journal of the Korean Cartographic Association, Downscaling advanced microwave scanning radiometer 2 (AMSR2) soil moisture data using regression-kriging., 17(2); 99-110, (in Korean). (2017a)10.4172/2169- 0049.1000139
13
G. S. Kim and J. P. Kim, Journal of the Korean Association of Geographic Information Studies, Correlation analysis between soil moisture retrieved from satellite images and ground network measurements., 14(2); 69-81, (in Korean). (2011)10.11108/kagis.2011.14.2.069
14
J. Y. Kim and T. S. Hogue, IEEE Transactions on Geoscience and Remote Sensing, Improving spatial soil moisture representation through integration of AMSR-E and MODIS products., 50(2); 446-460 (2011)10.1109/tgrs.2011.216131827295638
15
Y. H. Kim, G. J. Kim, S. J. LEE, J. W. Kim and Y. W. Lee, Journal of The Korean Cartographic Association, Deep learning-based retrieval of daily 500-m soil moisture for south korea., 17(3); 109-121, (in Korean). (2017b)10.16879/jkca.2017.17.3.109
16
Y. G. Lee, C. G. Jung, Y. H. Jo and S. J. Kim, Journal of the Korean Society of Agricultural Engineers, Estimation of soil moisture using multiple linear regression model and COMS land surface temperature data., 59(1); 11-20, (in Korean). (2017)10.5389/ksae.2017.59.1.011
17
B. Narasimhan, R. Srinivasan, J. G. Arnold and M. Di Luzio, Transactions of the ASAEEstimation of long-term soil moisture using a distributed parameter hydrologic model and verification using remotely sensed data., 48(3); 1101-1113 (2005)10.13031/2013.18520
18
J. A. Park and G. S. Kim, Journal of the Korean Geographical Society, Estimation of spatial distribution of soil moisture at Yongdam Dam watershed using artificial neural networks., 46(3); 319-330, (in Korean). (2011)
19
S. Y. Park, The Geographical Journal of KoreaEvaluation of MODIS land surface temperature as an indicator of the climatic water budget in the central great plains., 37(3); 257-271, (in Korean). (2003)
20
Y. Qiu, B. Fu, J. Wang and L. Chen, CATENASpatiotemporal prediction of soil moisture content using multiple-linear regression in a small catchment of the Loess Plateau, China., 54(1-2); 173-195 (2003)10.1016/s0341-8162(03)00064-x
21
D. H. Shin, K. H. Choi and C. B. Kim, Journal of Korean Institute of Information Technology , Deep learning model for prediction rate improvement of stock price using RNN and LSTM., 15(10); 9-16, (in Korean). (2017)10.14801/jkiit.2017.15.10.9
22
S. L. Su, D. N. Singh and M. S. Baghini, MeasurementA critical review of soil moisture measurement., 54; 92-105 (2014)10.1016/j.measurement.2014.04.007
23
L. Wang, J. Wen, T. Zhang, Y. Zhao, H. Tian, X. Wang, R. Liu, J. Zhang and S. Lu, Hydrology and Earth System Sciences Discussions Surface soil moisture estimates from AMSR-E observations over an arid area., 6(1); 1055-1087 (2009)10.5194/hessd-6-1055-2009
24
Z. M. Wang, Institute for Computational Earth System Science, Santa BarbaraMODIS land-surface temperature algorithm theoretical basis document (LST ATBD)., 75 (1999)
25
Z. Wan and J. Dozier, IEEE Transactions on Geoscience and Remote SensingA generalized split-window algorithm for retrieving land-surface temperature from space., 34(4); 892-905 (1996)10.1109/36.50840627295638
26
Z. Wan, P. Wang and X. Li, International Journal of Remote Sensing, Using MODIS land surface temperature and normalized difference vegetation index products for monitoring drought in the southern Great Plains., 25(1); 61-72 (2004)10.1080/0143116031000115328
27
M. Zribi, N. Baghdadi, N. Holah and O. Fafin, Remote Sensing of EnvironmentNew nethodology for soil surface moisture estimation and its application to ENVISAT-ASAR multi-incidence data inversion., 96(3-4); 485-496 (2005)10.1016/j.rse.2005.04.005
Information
  • Publisher :The Korean Society of Agricultural Engineers
  • Publisher(Ko) :한국농공학회
  • Journal Title :Journal of Korean Society of Agricultural Engineers
  • Journal Title(Ko) :한국농공학회논문집
  • Volume : 61
  • No :6
  • Pages :123-132
  • Received Date : 2019-10-31
  • Revised Date : 2019-11-21
  • Accepted Date : 2019-11-22
  • DOI :https://doi.org/10.5389/KSAE.2019.61.6.123
Journal Informaiton Journal of Korean Society of Agricultural Engineers Journal of Korean Society of Agricultural Engineers
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crossref funder-registry
  • crosscheck
  • orcid
  • open access
Journal Informaiton Journal Informaiton - close