Predicting sandy soil moisture content with hyperspectral imaging

Qi Haijun, Jin Xiu, Zhao Liu, DEDO Irene Maxime, Li Shaowen

Abstract


In this study, a rapid and non-invasive technology for predicting soil moisture content (SMC) was presented based on hyperspectral imaging (HSI). Firstly, a set of HSI system was developed to collect both spectral (400-1000 nm) and spatial (1620×841 pixels) information from sandy soil samples with variable SMC levels in the laboratory. Principal component analysis (PCA) transformation, K-means clustering, and several other image processing methods were performed to obtain a region of interest (ROI) of soil sample from the original HSI data. Then, 256 optimal spectral wavelengths were selected from the average reflectance of the ROI, and 28 textural features were extracted using a gray-level co-occurrence matrix (GLCM). Data dimensionality reduction was conducted on both the spectral information and textural information by using a partial least square algorithm. Six latent variables (LVs) extracted from the spectral information, four LVs extracted from the textural information and fused data were used to build regression models with a three-layer BPNN, respectively. The results showed that all of the three calibration models achieved high prediction accuracy, particularly when using spectral information with R2C=0.9532 and RMSEC=0.0086. However, validation models demonstrate that predicting SMC using fused data is more effective than using spectral reflectance and textural features separately, with a R2P=0.9350 and RMSEP=0.0141, thus proving that the HSI technique is capable of detecting SMC.
Keywords: hyperspectral imaging, soil moisture content, image processing, prediction model, fused data, BPNN, regression
DOI: 10.25165/j.ijabe.20171006.2614

Citation: Qi H J, Jin X, Zhao L, DEDO I M, Li S W. Predicting sandy soil moisture content with hyperspectral imaging. Int J Agric & Biol Eng, 2017; 10(6): 175–183.

Keywords


hyperspectral imaging, soil moisture content, image processing, prediction model, fused data, BPNN, regression

Full Text:

PDF

References


Whiting M L, Li L, Ustin S L. Predicting water content using Gaussian model on soil spectra. Remote Sensing of Environment, 2004; 89(4): 535–552.

Lesaignoux A, Fabre S, Briottet X. Influence of soil moisture content on spectral reflectance of bare soils in the 0.4-14 μm domain. International Journal of Remote Sensing, 2013; 34(7): 2268–2285.

Jiang P A. Measuring soil water content by using near infrared spectral characteristics of soil. Spectroscopy and Spectral Analysis, 2012; 32(8): 2117–2121. (in Chinese)

Wu D, Fan W, Cui Y, Yan B, Xu X. Review of monitoring soil water content using hyperspectral remote sensing. Spectroscopy and Spectral Analysis, 2010; 30(11): 3067–3071. (in Chinese)

Yao Y, Wei N, Tang P, Li Z, Yu Q, Xu X, et al. Hyper-spectral characteristics and modeling of black soil moisture content. Transactions of the CSAE, 2011; 27(8): 95–100. (in Chinese)

Peng J, Shen H, He S W, Wu J S. Soil moisture retrieving using hyperspectral data with the application of wavelet analysis. Environmental Earth Sciences, 2013; 69(1): 279–288.

Oltra-Carrió R, Baup F, Fabre S, Fieuzal R, Briottet X. Improvement of soil moisture retrieval from hyperspectral VNIR-SWIR data using clay content information: From laboratory to field experiments. Remote Sensing, 2015; 7(3): 3184–3205.

Park B, Lu R. Hyperspectral imaging technology in food and agriculture. Springer New York, 2015.

Rourke S M O, Holden N M. Optical sensing and chemometric analysis of soil organic carbon – a cost effective alternative to conventional laboratory methods? Soil Use and Management, 2011; 27(2): 143–155.

Zhang H. Soil nutrition content and type measurement based on NIR spectrum and hyper spectra image technology and design portable instrument. Hangzhou: Zhejiang University, 2015. (in Chinese)

O'Rourke S M, Holden N M. Determination of soil organic matter and carbon fractions in forest top soils using spectral data acquired from visible–near infrared hyperspectral images. Soil Science Society of America Journal, 2012; 76(2): 586–596.

Burud I, Moni C, Flo A, Futsaether C, Steffens M, Rasse D P. Qualitative and quantitative mapping of biochar in a soil profile using hyperspectral imaging. Soil and Tillage Research, 2016; 155: 523–531.

Pessoa L G M, Dos Santos Freire M B G, Wilcox B P, Rossi C G, Souza A M D O, Galvíncio J D. Spectral reflectance characteristics of laboratory-grown salt crusts on silty clay and sandy soils. Communications in Soil Science and Plant Analysis, 2015; 46(15): 1895–1904.

Gomez C, Drost A P A, Roger J M. Analysis of the uncertainties affecting predictions of clay contents from VNIR/SWIR hyperspectral data. Remote Sensing of Environment, 2015; 156: 58–70.

Li S, Wang S, Shi Z. Prediction of vertical distribution of soil nitrogen content in soil profile using spectral imaging technique. Acta Pedologica Sinica, 2015; 52(5): 1014–1023. (in Chinese)

GB/T. Method for determination of soil water content. PRC National Standard, 1987. (in Chinese)

Dong G, Guo J, Wang C, Chen Z L, Zheng L, Zhu D Z. The classification of wheat varieties based on near infrared hyperspectral imaging and information fusion. Spectroscopy and Spectral Analysis, 2015; 35(12): 3369–3374. (in Chinese)

Steffens M, Buddenbaum H. Laboratory imaging spectroscopy of a stagnic Luvisol profile-High resolution soil characterisation, classification and mapping of elemental concentrations. Geoderma, 2013; 195: 122–132.

Cen H, Lu R, Zhu Q, Mendoza F. Nondestructive detection of chilling injury in cucumber fruit using hyperspectral imaging with feature selection and supervised classification. Postharvest Biology and Technology, 2016; 111: 352–361.

Rourke S M O, Holden N H. Determination of soil organic matter and carbon fractions in forest top soils using spectral data acquired from visible–near infrared hyperspectral images. Soil Science Society of America Journal, 2012; 76: 586.

Savitzky A, Golay M J E. Smoothing and differentiation of data by simplified least squares procedures. Analytical Chemistry, 1964; 36: 1627–1639.

Li H W, Li H, He Jin, Li S W. Measuring system for residue cover rate in field based on BP neural network. Transactions of the CSAM, 2009; 40(6): 58–62. (in Chinese)

Janik L, Cozzolino D, Dambergs R, Cynkar W, Gishen M. The prediction of total anthocyanin concentration in red-grape homogenates using visible-near-infrared spectroscopy and artificial neural networks. Analytica Chimica Acta, 2007; 594(1): 107–118.

Ji W J, Li X, Li C X, Zhou Y, Shi Z. Using different data mining algorithms to predict soil organic matter based on visible-near infrared spectroscopy. Spectroscopy Spectral Analysis, 2012; 32: 2393–2398. (in Chinese)

Mouazen A M, Kuang B, de Baerdemaeker J, Ramon H. Comparison among principal component, partial least squares and back propagation neural network analyses for accuracy of measurement of selected soil properties with visible and near infrared spectroscopy. Geoderma, 2010; 158: 23–31.

Widyanto M R, Nobuhara H, Kawamoto K, Hirota K, Kusumoputro B. Improving recognition and generalization capability of back-propagation NN using a self-organized network inspired by immune algorithm (SONIA). Applied Soft Computing Journal, 2005; 6: 72–84.

Janik L J, Merry R H, Skjemstad J. Can mid infrared diffuse reflectance analysis replace soil extractions? Animal Production Science, 1998; 38(7): 681–696.

Ji W J, Adamchuk V I, Biswas A, Dhawale N M, Sudarsan B, Zhang Y K, et al. Assessment of soil properties in situ using a prototype portable MIR spectrometer in two agricultural fields. Biosystems Engineering, 2016; 152: 14–27.

Baret F, Jacquemoud S, Hanocq J. The soil line concept in remote sensing. Remote Sensing Reviews, 1993; 7(1): 65–82.

Peng J, Xiang H Y, Zhou Q, Zhang Y Z. Influence of soil iron oxide on VNIR diffuse reflectance spectroscopy. Spectroscopy and Spectral Analysis, 2013; 33(2): 502–506. (in Chinese)

Stenberg B, Rossel R A V, Mouazen A M, Wetterlind J. Chapter five-visible and near infrared spectroscopy in soil science. Advances in agronomy, 2010; 107: 163–215.

Galvão L S, Vitorello Í. Variability of laboratory measured soil lines of soils from southeastern Brazil. Remote Sensing of Environment, 1998; 63(2): 166–181.




Copyright (c)



2023-2026 Copyright IJABE Editing and Publishing Office