All Issue

2024 Vol.57, Issue 12 Preview Page

Research Article

High-resolution soil moisture estimation using Sentinel-1 SAR and Random Forest in the Yeongsan River watershed

영산강 유역에서 Sentinel-1 SAR와 Random Forest 방법론을 활용한 고해상도 토양수분 산정

Kijin Parka
,
Jongmin Parkb*
박 기진a
,
박 종민b*
aMaster's Student, Department of Environmental Engineering, Korea National University of Transportation, Chungju, Korea
bAssistant Professor, Department of Environmental Engineering, Korea National University of Transportation, Chungju, Korea
a국립한국교통대학교 환경공학과 석사과정
b국립한국교통대학교 환경공학전공 조교수
*Corresponding Author
31 December 2024. pp. 1085-1098
PDF XML Citation
Abstract

Soil moisture (SM) is a key variables in understanding the hydrological cycle and interactions between the land surface and the atmosphere. Consequently, research on SM monitoring has been actively conducted both domestically and internationally. In this study, a high-resolution (10m) SM estimation model for the Yeongsan River watershed was developed using Sentinel-1 Synthetic Aperture Radar (SAR) imagery from the European Space Agency and the Random Forest (RF) method. The model was trained and validated with SAR imagery from May 2015 to August 2023 and SM data collected from four ground observation sites. Statistical verification was conducted for the estimated values. Statistical analysis of the Sentinel-1 and RF-based SM model estimates against independent observed data yielded a correlation coefficient (R) of 0.75 and an index of agreement of 0.83, indicating significant statistical performance. For further validation, the high-resolution SM estimates were used to calculate watershed-averaged SM and compared with precipitation data from the European Centre for Medium-Range Weather Forecasts Reanalysis v5-Land and Soil Moisture Active Passive (SMAP)/ Sentinel-1 SM data. The validation results showed an increase in watershed-averaged SM estimates in response to precipitation events (R = 0.30). Additionally, when comparing the watershed-averaged SM estimates derived from the model and those from SMAP/Sentinel-1 with site observed data, the model (R = 0.37) demonstrated higher accuracy than SMAP/Sentinel-1 (R = 0.28). Seasonally, the highest watershed-averaged SM (32.60%) was observed in autumn, while the lowest (30.66%) was observed in winter. This analysis suggests that the model developed in this study is capable of simulating precipitation events and seasonal variations.

Keywords
Soil moisture
Sentinel-1 SAR
Random Forest

토양수분은 수문순환, 그리고 지표와 대기 사이의 상호작용을 이해하는 데 중요한 요소이다. 이에 따라 국∙내외에서는 토양수분 모니터링과 관련된 연구가 활발히 이루어지고 있다. 본 연구에서는 유럽우주국(European Space Agency)의 Sentinel-1 Synthetic Aperture Radar (SAR) 영상과 Random Forest (RF) 방법론을 활용하여 영산강 유역의 고해상도(10m) 토양수분 추정 모델을 개발하였다. 2015년 5월부터 2023년 8월까지의 SAR 영상과 4개의 지상 관측소에서 수집한 토양수분 자료를 훈련 및 검증 자료로 구분하여 모델을 개발하고 추정값에 대한 통계적 검증을 수행하였다. 훈련 과정에 활용하지 않은 검증 자료와 RF 기반 모델을 통해 산정한 토양수분 추정값 사이의 통계적 분석을 수행한 결과, 상관계수(correlation coefficient; R)는 0.75, 일치도(Index of Agreement)는 0.83으로 유의미한 통계치를 도출하였다. 추가적인 검증을 위해 RF 기반 모델을 활용하여 유역 평균 토양수분을 산정하고 European Centre for Medium-Range Weather Forecasts Reanalysis v5-Land 강수 및 Soil Moisture Active Passive (SMAP)/Sentinel-1 토양수분과 비교하였다. 검증 결과, 강수 사상에 따라 유역 평균 토양수분 추정값이 증가하는 경향(R = 0.30)을 나타내었다. 또한, SMAP/Sentinel-1을 활용하여 산정한 유역 평균 토양수분과 RF 기반 모델을 통해 산정한 유역 평균 토양수분을 각각 지점 관측자료와 비교하였을 때, RF 기반 모델(R = 0.37)이 SMAP/Sentinel-1 (R = 0.28)보다 높은 정확도를 나타내었다. 계절적으로는 가을에 가장 높은 유역 평균 토양수분(32.60%)을 나타내었고, 겨울에 가장 낮은 값(30.66%)을 나타내었다. 이러한 분석 과정을 통해, 본 연구에서 개발한 RF 기반 모델이 강수 사상과 계절 변동을 모의할 수 있는 것으로 판단하였다.

키워드
토양수분
Sentinel-1 SAR
Random Forest
References
1

Breiman, L. (2001). "Random forests." Machine Learning, Vol. 45, pp. 5-32.

10.1023/A:1010933404324
2

Chaudhary, S.K., Srivastava, P.K., Gupta, D.K., Kumar, P., Prasad, R., Pandey, D.K., Das, A.K., and Gupta, M. (2022). "Machine learning algorithms for soil moisture estimation using Sentinel-1: Model development and implementation." Advances in Space Research, Vol. 69, No. 4, pp. 1799-1812.

10.1016/j.asr.2021.08.022
3

Cho, S., Jeong, J., Lee, S., and Choi, M. (2021). "Estimation of soil moisture based Sentinel-1 SAR data: Assessment of soil moisture estimation in different vegetation condition." Journal of Korea Water Resources Association, Vol. 54, No. 2, pp. 81-91.

4

Cho, Y. (2024). "Study on the possibility of estimating surface soil moisture using Sentinel-1 SAR satellite imagery based on Google Earth Engine." Korean Journal of Remote Sensing, Vol. 40, No. 2, pp. 229-241.

10.7780/kjrs.2024.40.5.1.18
5

Choi, S., Park, J., Kang, M., Kim, J., Sohn, S., Cho, S., Chun, H., and Jung, K. (2022) "Development of correction formulas for KMA AAOS soil moisture observation data." Korean Journal of Agricultural and Forest Meteorology, Vol. 24, No. 1, pp. 13-34.

6

Chung, J., Lee, Y., Kim, J., Jang, W., and Kim, S. (2023). "Soil moisture estimation using the water cloud model and Sentinel-1 & -2 satellite image-based vegetation indices." Journal of Korea Water Resources Association, Vol. 56, No. 3, pp. 211-224.

7

Das, N., Entekhabi, D., Dunbar, S., Chaubell, J., Colliander, A., Yueh, S., Jagdhuber, T., Chen, F., Crow, W.T., and O'Neill, P.E. et al. (2019). "The SMAP and copernicus Sentinel 1A/B microwave active-passive high resolution surface soil moisture product." Remote Sensing of Environment, Vol. 233, 111380.

10.1016/j.rse.2019.111380
8

Dinesh, D., Kumar, S., and Saran, S. (2024). "Machine learning modelling for soil moisture retrieval from simulated NASA-ISRO SAR (NISAR) L-Band data." Remote Sensing, Vol. 16, No. 18, 3539.

10.3390/rs16183539
9

Dubois, P.C., Van Zyl, J., and Engman, T. (1995). "Measuring soil moisture with imaging radars." IEEE Transactions on Geoscience and Remote Sensing, Vol. 33, No. 4, pp. 915-926.

10.1109/36.406677
10

Entekhabi, D., Njoku, E.G., O'Neill, P.E., Kellogg, K.H., Crow, W.T., Edelstein, W.N., Entin, J.K., Goodman, S.D., Jackson, T.J., and Johnson, J. et al. (2010a). "The Soil Moisture Active Passive (SMAP) mission." Proceedings of the IEEE, Vol. 98, No. 5, pp. 704-716.

11

Entekhabi, D., Reichle, R.H., Koster, R.D., and Crow, W.T. (2010b). "Performance metrics for soil moisture retrievals and application requirements." Journal of Hydrometeorology, Vol. 11, No. 3, pp. 832-840.

10.1175/2010JHM1223.1
12

Filipponi, F. (2019). "Sentinel-1 GRD preprocessing workflow." Proceedings, Vol. 18, No. 1, 11.

10.3390/ECRS-3-06201
13

Hagemann, S., and Stacke, T. (2015). "Impact of the soil hydrology scheme on simulated soil moisture memory." Climate Dynamics, Vol. 44, pp. 1731-1750.

10.1007/s00382-014-2221-6
14

Hajdu, I., Yule, I., and Dehghan-Shear, M.H. (2018). "Modelling of near-surface soil moisture using machine learning and multi- temporal sentinel 1 images in New Zealand." In IGARSS 2018- 2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain, pp. 1422-1425.

10.1109/IGARSS.2018.8518657
15

Hwang, T., Kim, B., Kim, H., and Seoh, B. (2006) "The estimation of soil moisture index by SWAT model and drought monitoring." Journal of the Korean Society of Civil Engineers B, Vol. 26, No. 4B, pp. 345-354.

16

Jeong, J., Cho, S., Jeon, H., Lee, S., and Choi, M. (2022). "Assessment of stand-alone utilization of Sentinel-1 SAR for high resolution soil moisture retrieval using machine learning." Korean Journal of Remote Sensing, Vol. 38, No. 5-1, pp. 571- 585.

17

Jeong, J., Cho, S., Lee, S., Kim, K., Lee, Y., Lee, C., Lee, S., and Choi, M. (2023) "A study on domestic applicability for the Korean cosmic-ray soil moisture observing system." Korean Journal of Remote Sensing, Vol. 39, No. 2, pp. 233-246.

18

Jiang, K., Pan, Z., Pan, F., Wang, J., Han, G., Song, Y., Zhang, Z., Huang, N., Ma, S., and Chen, X. (2022). "Influence patterns of soil moisture change on surface-air temperature difference under different climatic background." Science of The Total Environment, Vol. 822, 153607.

10.1016/j.scitotenv.2022.15360735114238
19

Joseph, A.T., van der Velde, R., O'Neill, P.E., Lang, R.H., and Gish, T. (2008). "Soil moisture retrieval during a corn growth cycle using L-band (1.6 GHz) radar observations." IEEE Transactions on Geoscience and Remote Sensing, Vol. 46, No. 8, pp. 2365- 2374.

10.1109/TGRS.2008.917214
20

Kang, M., Cho, S., Kim, J., Sohn, S., Choi, S., and Park, J. (2020). "A dataset from a test-bed to develop soil moisture estimation technology for upland fields." Korean Journal of Agricultural and Forest Meteorology, Vol. 22, No. 3, pp. 107-116.

21

Karthikeyan, L., Pan, M., Wanders, N., Kumar, D.N., and Wood, E.F. (2017). "Four decades of microwave satellite soil moisture observations: Part 1. A review of retrieval algorithms." Advances in Water Resources, Vol. 109, pp. 106-120.

10.1016/j.advwatres.2017.09.006
22

Kerr, Y.H., Waldteufel, P., Richaume, P., Wigneron, J.P., Ferrazzoli, P., Mahmoodi, A., Al Bitar, A., Cabot, F., Gruhier, C., and Juglea, S.E. et al. (2012). "The SMOS soil moisture retrieval algorithm." IEEE Transactions on Geoscience and Remote Sensing, Vol. 50, No. 5, pp. 1384-1403.

10.1109/TGRS.2012.2184548
23

Kim, H., Parinussa, R., Konings, A.G., Wagner, W., Cosh, M.H., Lakshmi, V., Zohaib, M., and Choi, M. (2018). "Global-scale assessment and combination of SMAP with ASCAT (active) and AMSR2 (passive) soil moisture products." Remote Sensing of Environment, No. 204, pp. 260-275.

10.1016/j.rse.2017.10.026
24

Kim, S., Lee, T., and Shin, Y. (2019). "Estimation of high-resolution soil moisture based on Sentinel-1A/B SAR Sensors" Journal of The Korean Society of Agricultural Engineers, Vol. 61, No. 5, pp.88-89.

25

Kim, Y., Lee, J., Woo, S., and Kim, S. (2020). "Evaluation of stream flow and water quality changes of Yeongsan River basin by inter-basin water transfer using SWAT." Journal of Korea Water Resources Association, Vol. 53, No. 12, pp. 1081-1095.

26

Kornelsen, K.C., and Coulibaly, P. (2013). "Advances in soil moisture retrieval from synthetic aperture radar and hydrological applications." Journal of Hydrology, Vol. 476, pp. 460-489.

10.1016/j.jhydrol.2012.10.044
27

Lee, J., Choi, M., and Kim, D. (2016) "Spatial merging of satellite based soil moisture and in-situ soil moisture using conditional merging technique." Journal of Korea Water Resources Association, Vol. 49, No. 3, pp. 263-273.

10.3741/JKWRA.2016.49.3.263
28

Lee, K., Ryu, Y., and Park, J. (2020). "Investigation of flood damage and cause analysis in the Yeongsan and Seomjin River basins in August 2020." Water for Future, Vol. 53, No. 11, pp. 21-48.

29

Lee, S., Hong, S., Cho, J., and Lee, Y. (2017). "Experimental retrieval of soil moisture for cropland in South Korea using Sentinel-1 SAR data" Korean Journal of Remote Sensing, Vol. 33, No. 6-1, pp. 947-960.

30

Ministry of Environment (ME), and K-Water (2023). Yeongsan and Seomjin River watershed drought paper (2022-2023). No. 2023-WR-GP-270-1694. pp. 28-29.

31

Ministry of Land, Infrastructure and Transport (MOLIT) (2016). Water resources long term master plan (2000-2020) third revised plan. No. 11-1613000-001716-13. p. 15.

32

Muñoz-Sabater, J., Dutra, E., Agustí-Panareda, A., Albergel, C., Arduini, G., Balsamo, G., Boussetta, S., Choulga, M., Harrigan, S., and Hersbach, H. et al. (2021) "ERA5-land: A state-of-the- art global reanalysis dataset for land applications." Earth System Science Data, Vol. 13, No. 9, pp. 4349-4383.

10.5194/essd-13-4349-2021
33

Ok, J., Kim, D., Han, K., Jung, K., Lee, K., Zhang, Y., Cho, H., and Hwang, S. (2019) "Relationship between measured and predicted soil water content using soil moisture monitoring network." Korean Journal of Agricultural and Forest Meteorology, Vol. 21, No. 4, pp. 297-306.

34

Okuyama, A., and Imaoka, K. (2015). " Intercalibration of advanced microwave scanning radiometer-2 (AMSR2) brightness temperature." IEEE Transactions on Geoscience and Remote Sensing, Vol. 53, No. 8, pp. 4568-4577.

10.1109/TGRS.2015.2402204
35

Palomaki, R.T., and Sproles, E.A. (2022). "Quantifying the effect of river ice surface roughness on sentinel-1 SAR backscatter." Remote Sensing, Vol. 14, No. 22, 5644.

10.3390/rs14225644
36

Park, J., and Kim, G. (2011) "Estimation of spatial distribution of soil moisture at Yongdam Dam watershed using artificial neural networks." Journal of the Korean Geographical Society, Vol. 46, No. 3, pp. 319-330.

37

Petropoulos, G.P., Ireland, G., and Barrett, B. (2015). "Surface soil moisture retrievals from remote sensing: Current status, products & future trends." Physics and Chemistry of the Earth, Vol. 83-84, pp. 36-56.

10.1016/j.pce.2015.02.009
38

Sehler, R., Li, J., Reager, J.T., and Ye, H. (2019). "Investigating relationship between soil moisture and precipitation globally using remote sensing observations." Journal of Contemporary Water Research & Education, Vol. 168, No. 1, pp. 106-118.

10.1111/j.1936-704X.2019.03324.x
39

Seneviratne, S.I., Koster, R.D., Guo, Z., Dirmeyer, P.A., Kowalczyk, E., Lawrence, D., Liu, P., Lu, C.H., Mocko, D., and Oleson, K.W. et al. (2006). "Soil moisture memory in AGCM simulations: analysis of global land-atmosphere coupling experiment (GLACE) data." Journal of Hydrometeorology, Vol. 7, No. 5, pp. 1090-1112.

10.1175/JHM533.1
410

Torres, R., Snoeij, P., Geudtner, D., Bibby, D., Davidson, M., Attema, E., Potin, P., Rommen, B., Floury, N., and Brown, M., et al. (2012). "GMES Sentinel-1 mission" Remote Sensing of Environment, Vol. 120, pp. 9-24.

10.1016/j.rse.2011.05.028
41

Ulaby, F.T., Batlivala, P.P., and Dobson, M.C. (1978). "Microwave backscatter dependence on surface roughness, soil moisture, and soil texture: Part I-bare soil." IEEE Transactions on Geoscience Electronics, Vol.16, No. 4, pp. 286-295.

10.1109/TGE.1978.294586
42

Vereecken, H., Huisman, J.A., Bogena, H., Vanderborght, J., Vrugt, J.A., and Hopmans, J. (2008). "On the value of soil moisture measurements in vadose zone hydrology: A review." Water Resources Research, Vol. 44, No. 4, W00D06.

10.1029/2008WR006829
43

Vreugdenhil, M., Wagner, W., Bauer-Marschallinger, B., Pfeil, I., Teubner, I., Rüdiger, C., and Strauss, P. (2018). "Sensitivity of Sentinel-1 backscatter to vegetation dynamics: An Austrian case study."Remote Sensing, Vol. 10, No. 9, 1396.

10.3390/rs10091396
44

Wagner, W., Hahn, S., Kidd, R., Melzer, T., Bartalis, Z., Hasenauer, S., Figa-Saldana, J., de Rosnay, P., Jann, A., and Schneider, S. et al. (2013). "The ASCAT soil moisture product: A review of its specifications, validation results, and emerging applications." Meteorologische Zeitschrift, Vol. 22, No. 1, pp. 5-33.

10.1127/0941-2948/2013/0399
45

Wang, L., and Qu, J.J. (2009). "Satellite remote sensing applications for surface soil moisture monitoring: A review." Frontiers of Earth Science in China, Vol. 3, pp. 237-247.

10.1007/s11707-009-0023-7
46

Yoo, H.Y., Park, N.W., Hong, S., Lee, K., and Kim, Y. (2013). "Feature extraction and classification of multi-temporal SAR data using 3D wavelet transform." Korean Journal of Remote Sensing, Vol. 29, No. 5, pp. 569-579.

10.7780/kjrs.2013.29.5.12
47

Zanaga, D., Van De Kerchove, R., Daems, D., De Keersmaecker, W., Brockmann, C., Kirches, G., Wevers, J., Cartus, O., Santoro, M., and Fritz, S. et al. (2022). ESA WorldCover 10 m 2021 v200, accessed 1 September 2024, <https://doi.org/10.5281/zenodo.7254221>.

Information
  • Publisher :KOREA WATER RESOURECES ASSOCIATION
  • Publisher(Ko) :한국수자원학회
  • Journal Title :Journal of Korea Water Resources Association
  • Journal Title(Ko) :한국수자원학회 논문집
  • Volume : 57
  • No :12
  • Pages :1085-1098
  • Received Date : 2024-09-03
  • Revised Date : 2024-11-26
  • Accepted Date : 2024-11-27
  • DOI :https://doi.org/10.3741/JKWRA.2024.57.12.1085
Journal Informaiton Journal of Korea Water Resources Association Journal of Korea Water Resources Association
Online Submission
Archives
  • scopus
  • KCI-수자원
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close