All Issue

2020 Vol.62, Issue 5 Preview Page
Estimation of DNN-based Soil Moisture at Mountainous Regions

DNN 회귀모형을 이용한 산악 지형 토양수분 산정

Beomseok Chuna
,
Taehwa Leeb
,
Sangwoo Kimc
,
Jonggun Kimd
,
Keunchang Jange
,
Junghwa Chunf
,
Won Seok Jangg
,
Yongchul Shinh†
천 범석a
,
이 태화b
,
김 상우c
,
김 종건d
,
장 근창e
,
천 정화f
,
장 원석g
,
신 용철h†
aMS Student, Major in Agricultural Civil Engineering, School of Agricultural Civil & Bio-Industrial Engineering, Kyungpook National University
bPh.D. Student, Major in Agricultural Civil Engineering, School of Agricultural Civil & Bio-Industrial Engineering, Kyungpook National University
cPh.D. Student, Major in Agricultural Civil Engineering, School of Agricultural Civil & Bio-Industrial Engineering, Kyungpook National University
dAssistant Professor, Department of Regional Infrastructure Engineering, Kangwon National University
eResearch Scientist, Division of Forest Ecology and Climate Change, National Institute of Forest Science
fSenior Researcher, Division of Forest Ecology and Climate Change, National Institute of Forest Science
gResearch Fellow, Division of Public Infrastructure Assessment, Environmental Assessment Group, Korea Environment Institute
hAssistant Professor, Major in Agricultural Civil Engineering, School of Agricultural Civil & Bio-Industrial Engineering, Kyungpook National University
a석사, 경 포 국립 대학 농업 토 목 및 생물 공업 공학 대학 농업 토 목 공학 과
b경포 국립 대 농업 토 목 과 생물 공업 공학 부 농업 토 목 공학 과 박사
c경포 국립 대 농업 토 목 과 생물 공업 공학 부 농업 토 목 공학 과 박사
d강원 국립 대 지역 인 프 라 공학 과 조교수
e국가 산림 과학 연구원 산림 생태 와 기후 변화 연구실 연구원
f국가 산림 과학 연구원 산림 생태 와 기후 변화 연구실 고급 연구원
g한국 환경 연구소 환경 평가 팀 공공 인 프 라 시설 평가 부 연구원
h경 포 국립 대 농업 토 목 및 생물 공업 공정 대학 농업 토 목 공학 과 조교수
† Corresponding author Tel.: +82-53-950-5730 Fax.: +82-53-950-6752 E-mail: ycshin@knu.ac.kr
2020. pp. 93-103
PDF XML Citation
Abstract

In this study, we estimated soil moisture values using the Deep Neural Network(DNN) scheme at the mountainous regions. In order to test the sensitive analysis of DNN scheme, we collected the measured(at the soil depths of 10 cm and 30 cm) soil moisture and DNN input(weather and land surface) data at the Pyeongchang-gun(relatively flat) and Geochang-gun(steep slope) sites. Our findings indicated that the soil moisture estimates were sensitive to the weather variables(5 days-averaged rainfall, 5 days precedent rainfall, accumlated rainfall) and DEM. These findings showed that the DEM and weather variables play the key role in the processes of soil water flow at the mountainous regions. We estimated the soil moisture values at the soil depths of 10 cm and 30 cm using DNN at two study sites under different climate-landsurface conditions. The estimated soil moisture(R: 0.890 and RMSE: 0.041) values at the soil depth of 10 cm were comparable with the measured data in Pyeongchang-gun site while the soil moisture estimates(R: 0.843 and RMSE: 0.048) at the soil depth of 30 cm were relatively biased. The DNN-based soil moisture values(R: 0.997/0.995 and RMSE: 0.014/0.006) at the soil depth of 10 cm/30 cm matched well with the measured data in Geochang-gun site. Although uncertainties exist in the results, our findings indicated that the DNN-based soil moisture estimation scheme demonstrated the good performance in estimating soil moisture values using weather and land surface information at the monitoring sites. Our proposed scheme can be useful for efficient land surface management in various areas such as agriculture, forest hydrology, etc.

Keywords
Deep neural network
soil moisture
weather
land surface
mountainous regions
References

REFERENCES

1
Y. Cai, W. Zheng, X. Zhang, L. Zhangzhong and X. Xue, Plos one,, Research on soil moisture prediction model based on deep learning., 14(4), e0214508. (2019)10.1371/journal.pone.0214508
2
E. T. Engman, Remote Sensing of Environment, Applications of microwave remote sensing of soil moisture for water resources and agriculture., 35(2-3); 213-226 (1991)10.1016/0034-4257(91)90013-v
3
D. Entekhabi, E. G. Njoku, P. E. O’Neill, K. H. Kellogg, W. T. Crow, W. N. Edelstein, J. K. Entin, S. D. Goodman, T. J. Jackson, J. Johnson, J. Kimball, J. R. Piepmeier, R. D. Koster, N. Martin, K. C. McDonald, M. Moghaddam, S. Moran, R. Reichle, J. C. Shi, M. W. Spencer, S. W. Thurman, L. Tsang and J. Van Zyl, Proceedings of the IEEE,, The soil moisture active passive (SMAP) mission., 98(5); 704-716 (2010)10.1109/jproc.2010.2043918
4
D. Entekhabi, G. R. Asrar, A. K. Betts, K. J. Beven, R. L. Bras and C. J. Duffy, Bulletin of the American Meteorological Society, An agenda for land surface hydrology research and a call for the second international hydrological decade., 80(10); 2043-2058, 10.1175/1520-0477(1999)080<2043:aaflsh>2.0.co;2 (1999)
5
A. V. M. Ines, B. P. Mohanty and Y. Shin, Water Resource Research, An un-mixing algorithm for remotely sensed soil moisture., 49(1); 408-425 (2013)10.1029/2012wr012379
6
Y. H. Kerr, P. Waldteufel, J. P. Wigneron, J. A. M. J. Martinuzzi, J. Font and M. Berger, IEEE Transactions on Geoscience and Remote Sensing, Soil moisture retrieval from space: The soil moisture and ocean salinity (SMOS) mission., 39(8); 1729-1735 (2001)10.1109/36.942551
7
Y. H. Kim, K. J. Kim, S. J. Lee, L. W. Kim and Y. W. Yang, 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). (2017)10.16879/jkca.2017.17.3.109
8
D. P. Kingma and J. Ba, In Proc. 3rd International Conference for Learning Representations, , Adam: A method for stochastic optimization., arXiv:1412.6980. (2014)
9
C. S. Lee, E. Sohn, J. D. Park and J. D. Jang, GIScience & Remote Sensing, Estimation of soil moisture using deep learning based on satellite data: A case study of South Korea., 56(1); 43-67 (2018)10.1080/15481603.2018.1489943
10
W. S. McCulloch and W. Pitts, The Bulletin of Mathematical Biophysics, A logical calculus of the ideas immanent in nervous activity., 5(4); 115-133 (1943)10.1007/bf02478259
11
National Research Council,, Reducing losses from landsliding in the United States., Washington, DC:. The National Academies Press.. (1985)10.17226/19286
12
NGII (National Geographic Information Institute),, The geography of Korea., (in Korean)., The Ministry of Land, Transport and Maritime affairs, National Geographic Information Institute. (2008)
13
Y. Shin and B. P. Mohanty, Water Resource Research, Development of a deterministic downscaling algorithm for remote sensing soil moisture footprint using soil and vegetation classifications., 49(10); 6208-6228 (2013)10.1002/wrcr.20495
14
X. Song, G. Zhang, F. Liu, D. Li, Y. Zhao and J. Yang, Journal of Arid Land,, Modeling spatio-temporal distribution of soil moisture by deep learning-based cellular automata model., 8(5); 734-748 (2016)10.1007/s40333-016-0049-0
15
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever and R. Salakhutdinov, The Journal of Machine Learning Research, Dropout: A simple way to prevent neural networks from overfitting., 15(56); 1929-1959 (2014)
16
I. T. Yang, K. S. Chun, J. K. Park and S. Y. Lee, Journal of Korean Society for Geospatial Information System, An estimation to landslide vulnerable area of rainfall condition using GIS., 15(1); 39-46 (2007)
17
H. Zhang, L. Liao, K. M. Saravanan, P. Yin and Y. Wei, PeerJ, DeepBindRG: A deep learning based method for estimating effective protein-ligand affinity., 7: e7362. (2019)10.7717/peerj.7362
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 : 62
  • No :5
  • Pages :93-103
  • Received Date : 2020-08-21
  • Revised Date : 2020-09-22
  • Accepted Date : 2020-09-22
  • DOI :https://doi.org/10.5389/KSAE.2020.62.5.093
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