Abstract
Obtaining continuous and high-quality soil moisture (SM) data is important in scientific research and applications, especially for agriculture, meteorology, and environmental monitoring. With the continuously increasing number of artificial satellites in China, the acquisition of SM data from remote sensing images has received increasing attention. In this study, we constructed an SM inversion model by using a deep belief network (DBN) to extract SM data from Fengyun-3D (FY-3D) Medium Resolution Spectral Imager-II (MERSI-II) imagery; we named this model SM-DBN. The SM-DBN consists of two subnetworks: one for temperature and the other for SM. In the temperature subnetwork, bands 1, 2, 3, 4, 24, and 25 of the FY-3D MERSI-II imagery, which are relevant to temperature, were used as inputs while land surface temperatures (LST) obtained from ground stations were used as the expected output value when training the model. In the SM subnetwork, the input data included LSTs generated from the temperature subnetwork, normalized difference vegetation index (NDVI), and enhanced vegetation index (EVI); and the SM data obtained from ground stations were used as the expected outputs. We selected the Ningxia Hui Autonomous Region of China as the study area and used selected MERSI-II images and in-situ observation station data from 2018 to 2019 to develop our dataset. The results of the SM-DBN were validated by using in-situ SM data as a reference, and its performance was also compared with those of the linear regression (LR) and back propagation (BP) neural network models. The overall accuracy of these models was measured by using the root mean square error (RMSE) of the differences between the model results and in-situ SM observation data. The RMSE of the LR, BP neural network, and SM-DBN models were 0.101, 0.083, and 0.032, respectively. These results suggest that the SM-DBN model significantly outperformed the other two models.
Similar content being viewed by others
References
Abu-Hamdeh, N. H., 2003: Thermal properties of soils as affected by density and water content. Biosyst. Eng., 86, 97–102, doi: https://doi.org/10.1016/S1537-5110(03)00112-0.
Adegoke, J. O., and A. M. Carleton, 2002: Relations between soil moisture and satellite vegetation indices in the U.S. Corn Belt. J. Hydrometeor., 3, 395–405, doi: https://doi.org/10.1175/1525-7541(2002)003<0395:RBSMAS>2.0.CO;2.
Brusca, R. C., 2002: Desert ecology: An introduction to life in the arid southwest, by John Sowell. Nat. Resour. J., 42, 685–687.
Carlson, T. N., R. R. Gillies, and E. M. Perry, 1994: A method to make use of thermal infrared temperature and NDVI measurements to infer surface soil water content and fractional vegetation cover. Remote Sens. Rev., 9, 161–173, doi: https://doi.org/10.1080/02757259409532220.
Carlson, T. N., R. R. Gillies, and T. J. Schmugge, 1995: An interpretation of methodologies for indirect measurement of soil water content. Agric. For. Meteor., 77, 191–205, doi: https://doi.org/10.1016/0168-1923(95)02261-u.
Chen, G. C., A. Tsoi, and X. Hua, 2018: Predict effective drug combination by deep belief network and ontology fingerprints. J. Biomed. Inform., 85, 149–154, doi: https://doi.org/10.1016/j.jbi.2018.07.024.
Chen, J., C. Z. Wang, H. Jiang, et al., 2011: Estimating soil moisture using temperature-vegetation dryness index (TVDI) in the Huang-Huai-Hai (HHH) plain. Int. J. Remote Sens., 32, 1165–1177, doi: https://doi.org/10.1080/01431160903527421.
Chen, W. Y., Q. G. Xiao, and Y. W. Sheng, 1994: Application of the anomaly vegetation index to monitoring heavy drought in 1992. Remote Sens. of Environ. China, (2), 106–112, doi: https://doi.org/10.1007/BF02007173. (in Chinese)
Didan, K., and A. Huete, 2004: Analysis of the global vegetation dynamic metrics using MODIS vegetation index and land cover products. Proceedings of 2004 IEEE International Geoscience and Remote Sensing Symposium, IEEE, Anchorage, AK, USA, 2058–2061.
Feng, Q., G. L. Tian, A. S. Wang, et al., 2004: Remote sensing monitoring of soil humidity using vegetation condition index. J. Nat. Dis., 13, 81–88, doi: https://doi.org/10.3969/j.issn.1004-4574.2004.03.015. (in Chinese)
Feng, Q. L., N. S. Zheng, C. Liu, et al., 2018: BP neural network assisted soil moisture retrieval using GNSS satellite reflected signal. Sci. Surv. Mapp., 43, 157–162, doi: https://doi.org/10.16251/j.cnki.1009-2307.2018.08.026. (in Chinese)
Ghulam, A., Q. M. Qin, T. Teyip, et al., 2007: Modified perpendicular drought index (MPDI): A real-time drought monitoring method. ISPRS J. Photogramm. Remote Sens., 22, 150–164, doi: https://doi.org/10.1016/j.isprsjprs.2007.03.002.
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 e. Int. J. Remote Sens., 18, 3145–3166, doi: https://doi.org/10.1080/014311697217026.
Goetz, S. J., 1997: Multi-sensor analysis of NDVI, surface temperature and biophysical variables at a mixed grassland site. Int. J. Remote Sens., 18, 71–94, doi: https://doi.org/10.1080/014311697219286.
Jackson, R. D., P. N. Slater, and P. J. Pinter Jr, 1983: Discrimination of growth and water stress in wheat by various vegetation indices through clear and turbid atmospheres. Remote Sens. Environ., 13, 187–208, doi: https://doi.org/10.1016/0034-4257(83)90039-1.
Kogan, F. N., 1990: Remote sensing of weather impacts on vegetation in non-homogeneous areas. Int. J. Remote Sens., 11, 1405–1419, doi: https://doi.org/10.1080/01431169008955102.
Kogan, F. N., 1998: Global drought and flood-watch from NOAA polar-orbitting satellites. Adv. Space Res., 21, 477–480, doi: https://doi.org/10.1016/S0273-1177(97)00883-1.
Kondo, A., A. Higuchi, S. Kishi, et al., 1998: The use of multitemporal NOAA/AVHRR data to monitor surface moisture status in the Huaihe River Basin, China. Adv. Space Res., 22, 645–654, doi: https://doi.org/10.1016/s0273-1177(97)01126-5.
Larochelle, H., and Y. Bengio, 2008: Classification using discriminative restricted Boltzmann machines. Proceedings of the 25th International Conference on Machine Learning, ACM, Helsinki, Finland, 536–543, doi: https://doi.org/10.1145/1390156.1390224.
Larochelle, H., M. Mandel, R. Pascanu, et al., 2012: Learning algorithms for the classification restricted boltzmann machine. J. Mach. Learn. Res., 13, 643–669.
Li, P., G. X. Zhao, M. X. Gao, et al., 2015: Hyperspectral estimation and remote sensing retrieval of soil water regime in the Yellow River Delta. Acta Pedol. Sinica, 52, 1262–1272, doi: https://doi.org/10.11766/trxb201408270429. (in Chinese)
Li, Z. G., Y. L. Wang, Q. B. Zhou, et al., 2008: Spatiotemporal variability of land surface moisture based on vegetation and temperature characteristics in northern Shaanxi Loess Plateau, China. J. Arid Environ., 72, 974–985, doi: https://doi.org/10.1016/j.jaridenv.2007.11.014.
Liu, H., R. G. Liu, and S. Y. Liu, 2012: Review of drought monitoring by remote sensing. J. Geo-Inf. Sci., 14, 232–239, doi: https://doi.org/10.3724/SP.J.1047.2012.00232. (in Chinese)
Liu, H. Q., and A. Huete, 1995: A feedback based modification of the NDVI to minimize canopy background and atmospheric noise. IEEE Trans. Geosci. Remote Sens., 33, 457–165, doi: https://doi.org/10.1109/TGRS.1995.8746027.
Liu, P. J., L. Zhang, A. Kurban, et al., 1997: A method for monitoring soil water contents using satellite remote sensing. J. Remote Sens., 1, 135–138. (in Chinese)
Liu, S., Q. G. Jiang, H. Zhu, et al., 2018: Reconstruction of Landsat NDVI time series of Xianghai natural deserve based on a hybrid filtering algorithm Hyb-F. J. Jilin Univ. (Eng. Technol. Ed.), 48, 957–967, doi: https://doi.org/10.13229/j.cnki.jdxbgxb20170865. (in Chinese)
Liu, S. S., D. A. Roberts, O. A. Chadwick, et al., 2012: Spectral responses to plant available soil moisture in a Californian grassland. Int. J. Appl. Earth Obs. Geoinf., 99, 31–14, doi: https://doi.org/10.1016/j.jag.2012.04.008.
Liu, Y. M., H. F. Zhou, F. Tsung, et al., 2019: Real-time quality monitoring and diagnosis for manufacturing process profiles based on deep belief networks. Comput. Ind. Eng., 36, 494–503, doi: https://doi.org/10.1016/j.cie.2019.07.042.
Liu, Y. Y., R. M. Parinussa, W. A. Dorigo, et al., 2011: Developing an improved soil moisture dataset by blending passive and active microwave satellite-based retrievals. Hydrol. Earth Syst. Sci., 15, 425–436, doi: https://doi.org/10.5194/hess-15-425-2011.
Liu, Y. Y., W. A Dorigo, R. M. Parinussa, et al., 2012: Trend-preserving blending of passive and active microwave soil moisture retrievals. Remote Sens. Environ., 123, 280–297, doi: https://doi.org/10.1016/j.rse.2012.03.014.
Mallick, K., B. K. Bhattacharya, and N. K. Patel, 2009: Estimating volumetric surface moisture content for cropped soils using a soil wetness index based on surface temperature and NDVI. Agr. For. Meteorol., 149, 1327–1342, doi: https://doi.org/10.1016/j.agrformet.2009.03.004.
Mao, K. B., H. J. Tang, Q. B. Zhou, et al., 2007: A survey of soil moisture retrieval by passive microwave remote sensing. Remote Sens. Technol. Appl., 22, 466–470, doi: https://doi.org/10.3969/j.issn.1004-0323.2007.03.028. (in Chinese)
Moran, M. S., T. R. Clarke, Y. Inoue, et al., 1994: Estimating crop water deficit using the relation between surface-air temperature and spectral vegetation index. Remote Sens. Environ., 49, 246–263, doi: https://doi.org/10.1016/0034-4257(94)90020-5.
Nemani, R., and S. Running, 1997: Land cover characterization using multitemporal red, near-IR, and thermal-IR data from NOAA/AVHRR. Ecol. Appl, 7, 79–90, doi: https://doi.org/10.1890/1051-0761(1997)007[0079:LCCUMR]2.0.CO;2.
Paloscia, S., S. Pettinato, E. Santi, et al., 2013: Soil moisture mapping using sentinel-1 images: Algorithm and preliminary validation. Remote Sens. Environ., 134, 234–248, doi: https://doi.org/10.1016/j.rse.2013.02.027.
Patel, N. R., R. Anapashsha, S. Kumar, et al., 2009: Assessing potential of MODIS derived temperature/vegetation condition index (TVDI) to infer soil moisture status. Int. J. Remote Sens., 30, 23–39, doi: https://doi.org/10.1080/01431160802108497.
Patel, N. R., A. Mukund, and B. R. Parida, 2019: Satellite-derived vegetation temperature condition index to infer root zone soil moisture in semi-arid province of Rajasthan, India. Geocarto Int., doi: https://doi.org/10.1080/10106049.2019.1704074.
Peng, K. X., R. H. Jiao, J. Dong, et al., 2019: A deep belief network based health indicator construction and remaining useful life prediction using improved particle filter. Neurocomputing, 361, 19–28, doi: https://doi.org/10.1016/j.neucom.2019.07.075.
Price, J. C., 1990: Using spatial context in satellite data to infer regional scale evapotranspiration. IEEE Trans. Geosci. Remote Sens., 28, 940–948, doi: https://doi.org/10.1109/36.58983.
Qi, S. H., C. Y. Wang, and Z. Niu, 2003: Evaluating soil moisture status in China using the temperature/vegetation dryness index (TVDI). J. Remote Sens., 7, 420–427, doi: https://doi.org/10.11834/jrs.20030513. (in Chinese)
Qi, S. H., G. C. Li, C. Y. Wang, et al., 2005: Study on monitoring drought in China with MODIS product. Adv. Water Sci., 16, 56–61, doi: https://doi.org/10.14042/j.cnki.32.1309.2005.01.012. (in Chinese)
Ratana, P., A. R. Huete, Y. Yin, et al., 2005: Interrelationship among among MODIS vegetation products across an Amazon Eco-climatic gradient. Proceedings of 2005 IEEE International Geoscience and Remote Sensing Symposium, IEEE, Seoul, South Korea, 3009–3012, doi: https://doi.org/10.1109/IGARSS.2005.1525703.
Sandholt, I., K. Rasmussen, and J. Andersen, 2002: A simple interpretation of the surface temperature/vegetation index space for assessment of surface moisture status. Remote Sens. Environ., 79, 213–224, doi: https://doi.org/10.1016/s0034-4257(01)00274-7.
Song, Y., S. B Fang, H. Y. Liang, et al., 2017: Comparison and application of agricultural drought indexes based on MODIS data. Remote Sens. Land Resour., 29, 215–220, doi: https://doi.org/10.6046/gtzyyg.2017.02.31. (in Chinese)
Sun, J. Y., M. Z. Li, N. Tang, et al., 2007: Spectral characteristics and their correlation with soil parameters of black soil in Northeast China. Spectrosc. Spect. Anal., 27, 1502–1505. (in Chinese)
Tian, G. L., Q. H. Liu, and L. F. Chen, 2014: Thermal Remote Sensing. 2nd Ed., Publishing House of Electronics Industry, Beijing, 584 pp. (in Chinese)
Wang, J. X., Y. Z. Pang, X. F. Zhu, et al., 2019: A review of researches on inversion of eigenvariance of soil water. Acta Pedol. Sinica, 56, 23–35, doi: https://doi.org/10.11766/trxb201803090579. (in Chinese)
Wang, Z. X., C. Liu, and A. Huete, 2003: From AVHRR-NDVI to MODIS-EVI: Advances in vegetation index research. Acta Ecol. Sinica, 23, 979–987, doi: https://doi.org/10.3321/j.issn:1000-0933.2003.05.020. (in Chinese)
Yan, H. B., and G. Q. Zhou, 2017: Surface soil moisture retrieval from optical remote sensing: Current status and perspectives. J. Subtrop. Resour. Environ., 12, 82–89, 95, doi: https://doi.org/10.19687/j.cnki.1673-7105.2017.02.011. (in Chinese)
Yang, J., N. Guo, and J. H. Jia, 2007: Comparison between MODIS/NDVI and MODIS/EVI in northwest China. Arid Meteor., 25, 38–43, doi: https://doi.org/10.3969/j.issn:1006-7699.2007.01.007. (in Chinese)
Yang, T., H. L. Gong, X. J. Li, et al., 2010: Progress of soil moisture monitoring by remote sensing. Acta Ecol. Sinica, 30, 6264–6277. (in Chinese)
Yao, C. S., Z. X. Zhang, and X. Wang, 2004: Evaluating soil moisture status in Xinjiang using the temperature vegetation dryness index (TVDI). Remote Sens. Technol. Appl., 19, 473–478, doi: https://doi.org/10.3969/j.issn.1004-0323.2004.06.008. (in Chinese)
Yin, W. J., D. W. Zhang, J. H. Yan, et al., 2015: Deep learning based air pollutant forecasting with big data. Chinese J. Environ. Manag., 7, 46–52, doi: https://doi.org/10.3969/j.issn.1674-6252.2015.06.011. (in Chinese)
Yu, F., and Y. S. Zhao, 2011: A new semi-empirical model for soil moisture content retrieval by ASAR and TM data in vegetation-covered areas. Sci. China Earth Sci., 54, 1955–1964, doi: https://doi.org/10.1007/s11430-011-4204-3. (in Chinese)
Yu, F., Y. S. Zhao, and H. T. Li, 2012: Soil moisture retrieval based on GA-BP neural networks algorithm. J. Infrared Millim. Waves, 31, 283–288, doi: https://doi.org/10.3724/SP.J.1010.2012.00283. (in Chinese)
Zhang, J., Z. M. Zhou, F. M. Yao, et al., 2015: Validating the modified perpendicular drought index in the North China region using in-situ soil moisture measurement. IEEE Geosci. Remote Sens. Lett., 12, 542–546, doi: https://doi.org/10.1109/LGRS.2014.2349957.
Zhang, L., and H. Sun, 2009: Research on the relationships between soil moisture and reflectance spectrum in Loess Plateau area. Chinese J. Soil Sci., 40, 1255–1258, doi: https://doi.org/10.19336/j.cnki.trtb.2009.06.005. (in Chinese)
Zhang, Y., H. B. Wang, Y. F. Wang, et al., 2016: Soil moisture inversion in pasture of northern Tibet based on vegetation index. Trans. Chinese Soc. Agric. Eng., 32, 149–154, doi: https://doi.org/10.11975/j.issn.1002-6819.2016.06.020. (in Chinese)
Zhao, J. Y., J. H. Peng, Q. Song, et al., 2019: Modeling method of non-stationary NDVI time series data using artificial neural network. Remote Sens. Inf., 34, 12–17, doi: https://doi.org/10.3969/j.issn.1000-3177.2019.06.003.
Zhao, S. H., Q. M. Qin, X. Y. Shen, et al., 2010: Review of microwave remote sensing on soil moisture monitoring. J. Microw., 26, 90–96, doi: https://doi.org/10.14183/j.cnki.1005-6122.2010.02.023. (in Chinese)
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by the Science Foundation of Shandong (ZR2017MD018); Key Research and Development Program of Ningxia (2019BEH03008); Open Research Project of the Key Laboratory for Meteorological Disaster Monitoring, Early Warning and Risk Management of Characteristic Agriculture in Arid Regions (CAMF-201701 and CAMF-201803); Arid Meteorological Science Research Fund Project by the Key Open Laboratory of Arid Climate Change and Disaster Reduction of China Metrological Administration (IAM201801); and Science Foundation of Ningxia (NZ12278).
Rights and permissions
About this article
Cite this article
Wang, W., Zhang, C., Li, F. et al. Extracting Soil Moisture from Fengyun-3D Medium Resolution Spectral Imager-II Imagery by Using a Deep Belief Network. J Meteorol Res 34, 748–759 (2020). https://doi.org/10.1007/s13351-020-9191-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13351-020-9191-x