Browse > Article
http://dx.doi.org/10.5389/KSAE.2019.61.6.123

RNN-LSTM Based Soil Moisture Estimation Using Terra MODIS NDVI and LST  

Jang, Wonjin (Department of Civil, Environmental, and Plant Engineering, Konkuk University)
Lee, Yonggwan (Department of Civil, Environmental, and Plant Engineering, Konkuk University)
Lee, Jiwan (Department of Civil, Environmental, and Plant Engineering, Konkuk University)
Kim, Seongjoon (School of Civil, Environmental, and Plant Engineering, Konkuk University)
Publication Information
Journal of The Korean Society of Agricultural Engineers / v.61, no.6, 2019 , pp. 123-132 More about this Journal
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 ($R^2$), 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;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 Lee, Y. G., C. G. Jung, Y. H. Jo, and S. J. Kim, 2017. Estimation of soil moisture using multiple linear regression model and COMS land surface temperature data. Journal of the Korean Society of Agricultural Engineers 59(1): 11-20(in Korean). doi:10.5389/KSAE.2017.59.1.011.   DOI
2 Narasimhan, B., R. Srinivasan, J. G. Arnold, and M. Di Luzio, 2005. Estimation of long-term soil moisture using a distributed parameter hydrologic model and verification using remotely sensed data. Transactions of the ASAE 48(3): 1101-1113. doi:10.13031/2013.18520.   DOI
3 Park, J. A., and G. S. Kim, 2011. Estimation of spatial distribution of soil moisture at Yongdam Dam watershed using artificial neural networks. Journal of the Korean Geographical Society 46(3): 319-330 (in Korean).
4 Park S. Y., 2003. Evaluation of MODIS land surface temperature as an indicator of the climatic water budget in the central great plains. The Geographical Journal of Korea 37(3): 257-271 (in Korean).
5 Qiu, Y., B. Fu, J. Wang, and L. Chen, 2003. Spatiotemporal prediction of soil moisture content using multiple-linear regression in a small catchment of the Loess Plateau, China. CATENA 54(1-2): 173-195. doi:10.1016/S0341-8162(03)00064-X.   DOI
6 Hutchinson, J. S., T. J. Vought, and S. L. Hutchinson, 2006. Continuous soil moisture mapping using MODIS NDVI and LST products. Papers and Proceedings of Applied Geography Conferences 29: 140.
7 Joo, J. Y., M. H. Choi, S. W. Jung, and S. O. Lee, 2010. Prediction of soil moisture using hydrometeorological data in selmacheon. Journal of the Korean Society of Civil Engineers 30(5B): 437-444 (in Korean).
8 Jung, C. G., Y. G. Lee, Y. H. Cho, and S. J. Kim, 2017. A study of spatial soil moisture estimation using a multiple linear regression model and MODIS Land surface temperature data corrected by conditional merging. Remote Sensing 9(8): 870. doi:10.3390/rs9080870.   DOI
9 Kim, B. S., and B. K. Jung, 2016. Flood simulation using the gauge-adjusted radar rainfall and physics-based distributed hydrologic model. Hydrological Processes 22(22): 4400-4414. doi:10.1002/hyp.7043.   DOI
10 Kim, D. S., 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, 2017a. Downscaling advanced microwave scanning radiometer 2 (AMSR2) soil moisture data using regression-kriging. Journal of the Korean Cartographic Association 17(2): 99-110 (in Korean). doi:10.4172/2169-0049.1000139.   DOI
11 Kim, G. S., and J. P. Kim, 2011. Correlation analysis between soil moisture retrieved from satellite images and ground network measurements. Journal of the Korean Association of Geographic Information Studies 14(2): 69-81 (in Korean). doi:10.11108/kagis.2011.14.2.069.   DOI
12 Kim, J. Y., and T. S. Hogue, 2011. Improving spatial soil moisture representation through integration of AMSR-E and MODIS products. IEEE Transactions on Geoscience and Remote Sensing 50(2): 446-460. doi:10.1109/TGRS.2011.2161318.   DOI
13 Wan, Z., P. Wang, and X. Li, 2004. Using MODIS land surface temperature and normalized difference vegetation index products for monitoring drought in the southern Great Plains. International Journal of Remote Sensing 25(1): 61-72. doi:10.1080/0143116031000115328.   DOI
14 Shin, D. H., K. H. Choi, and C. B. Kim, 2017. Deep learning model for prediction rate improvement of stock price using RNN and LSTM. Journal of Korean Institute of Information Technology 15(10): 9-16 (in Korean). doi:10.14801/jkiit.2017.15.10.9.   DOI
15 Su, S. L., D. N. Singh, and M. S. Baghini, 2014. A critical review of soil moisture measurement. Measurement 54: 92-105. doi:10.1016/j.measurement.2014.04.007.   DOI
16 Wang, L., J. Wen, T. Zhang, Y. Zhao, H. Tian, X. Wang, R. Liu, J. Zhang, and S. Lu, 2009. Surface soil moisture estimates from AMSR-E observations over an arid area. Hydrology and Earth System Sciences Discussions 6(1): 1055-1087.   DOI
17 Wang, Z. M., 1999. MODIS land-surface temperature algorithm theoretical basis document (LST ATBD). Institute for Computational Earth System Science, Santa Barbara, 75.
18 Wan, Z., and J. Dozier, 1996. A generalized split-window algorithm for retrieving land-surface temperature from space. IEEE Transactions on Geoscience and Remote Sensing 34(4): 892-905. doi:10.1109/36.508406.   DOI
19 Zribi, M., N. Baghdadi, N. Holah, and O. Fafin, 2005. New nethodology for soil surface moisture estimation and its application to ENVISAT-ASAR multi-incidence data inversion. Remote Sensing of Environment 96(3-4): 485-496. doi:10.1016/j.rse.2005.04.005.   DOI
20 Aubert, D., C. Loumagne, and L. Oudin, 2003. Sequential assimilation of soil moisture and streamflow data in a conceptual rainfall-runoff model. Journal of Hydrology 280(1-4): 145-161. doi:10.1016/S0022-1694(03)00229-4.   DOI
21 Barling, R. D., I. D. Moore, and R. B. Grayson, 1994. A quasi-dynamic wetness index for characterizing the spatial distribution of zones of surface saturation and soil water content. Water Resources Research 30(4): 1029-1044. doi:10.1029/93WR03346.   DOI
22 Dai, A., K. E. Trenberth, and T. Qian, 2004. A global dataset of Palmer Drought Severity Index for 1870-2002: Relationship with soil moisture and effects of surface warming. Journal of Hydrometeorology 5(6): 1117-1130. doi:10.1175/JHM-386.1.   DOI
23 Farrar, T. J., S. E. Nicholson, and A. R. Lare, 1994. The influence of soil type on the relationships between NDVI, rainfall, and soil moisture in semiarid Botswana. II. NDVI response to soil moisture. Remote Sensing of Environment 50(2): 121-133. doi:10.1016/0034-4257(94)90039-6.   DOI
24 Gers, F. A., N. N. Schraudolph, and J. Schmidhuber, 2002. Learning precise timing with LSTM recurrent networks. Journal of Machine Learning Research 3(Aug): 115-143.
25 Gillies, R. R., W. P. Kustas, and K. S. Humes, 1997. 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. International Journal of Remote Sensing 18(15): 3145-3166. doi:10.1080/014311697217026.   DOI
26 Huete, A. R., C. Justice, and W. J. D. van Leeuwen, 1999. MODIS Vegetation Index (MOD13) Algorithm Theoretical Basis Document Version 3.
27 Kim, Y. H., G. J. Kim, S. J. LEE, J. W. Kim, and Y. W. Lee, 2017b. Deep learning-based retrieval of daily 500-m soil moisture for south korea. Journal of The Korean Cartographic Association 17(3): 109-121 (in Korean). doi:10.16879/jkca.2017.17.3.109.   DOI