Dongxue Zhao
Postgraduate Research Student

Dongxue Zhao

Postgraduate Research Student
School of Biological, Earth and Environmental Sciences

#UNSWSoilScienceCentral2019: My Top 3

1. The encouragement and support from each other which shows we are a real team

2. The “clear, concise and consistent” rule makes complicated things easy to follow.

3. JT keeping his door open and being patient to us.

Establishing a vis-NIR spectral library for predicting clay in cotton growing soil using machine learning algorithm and various sample sizes

The cotton growing areas of south-eastern Australia are highly productive. To maintain profitability, information pertaining to nutrient management and water use efficiency are needed. In this regard, information about clay content is required. This is a time-consuming and expensive laboratory analysis to undertake. An alternative is the use of visible near infra-red (Vis-NIR) spectroscopy, which has shown great potential on the field and global scales. However, the established spectral libraries are site-specific and not readily available for predicting properties in different areas. In this study, we explore some of these issues to demonstrate these problems by considering clay content prediction using a machine learning algorithm (i.e. Cubist) from Vis-NIR data acquired from topsoil (0-0.3 m) and subsurface (0.3-0.6 m) samples in seven cotton growing areas. The first aim is to assess the ability of soil samples collected from each area to predict clay content independent of the other 6 areas. The second aim is to determine the ability of the soil samples of 6 areas to predict clay content in an area which is withheld from the calibration. The third aim is to explore the potential to improve the prediction model using a spectra-based sampling approach. We also investigate the effects of combining soil samples from different depths on model performance.

Supervisor: Associate Professor John Triantafilis




Qu, J. L., Zhao, D. X., & Li, B. B. (2015). Effect of Random Inclusion of Palm Fibers on Strength Characteristics of Shanghai Cohesive Soil. In Advanced Materials Research (Vol. 1096, pp. 572-581). Trans Tech Publications.


Zhao, D. X., He, B. J., Johnson, C., & Mou, B. (2015). Social problems of green buildings: From the humanistic needs to social acceptance. Renewable and Sustainable Energy Reviews, 51, 1594-1609.


Zhao, D. X., He, B. J., & Meng, F. Q. (2015). The green school project: A means of speeding up sustainable development?. Geoforum, 65, 310-313.


Qu, J. L., & Zhao, D. X. (2016). Comparative research on tillable properties of diatomite-improved soils in the Yangtze River Delta region, China. Science of the Total Environment, 568, 480-488.


Qu, J., & Zhao, D. (2016). Stabilising the cohesive soil with palm fibre sheath strip. Road Materials and Pavement Design, 17(1), 87-103.


Zhao, D. X., & He, B. J. (2017). Effects of architectural shapes on surface wind pressure distribution: case studies of oval-shaped tall buildings. Journal of Building Engineering, 12, 219-228.


Mou, B., He, B. J., Zhao, D. X., & Chau, K. W. (2017). Numerical simulation of the effects of building dimensional variation on wind pressure distribution. Engineering Applications of Computational Fluid Mechanics, 11(1), 293-309.


Meng, F. Q., He, B. J., Zhu, J., Zhao, D. X., Darko, A., & Zhao, Z. Q. (2018). Sensitivity analysis of wind pressure coefficients on CAARC standard tall buildings in CFD simulations. Journal of Building Engineering, 16, 146-158.


He, B. J., Zhao, D. X., Zhu, J., Darko, A., & Gou, Z. H. (2018). Promoting and implementing urban sustainability in China: An integration of sustainable initiatives at different urban scales. Habitat International, 82, 83-93.


Zhao, D., Zhao, X., Khongnawang, T., Arshad, M., & Triantafilis, J. (2018). A Vis-NIR spectral library to predict clay in Australian cotton growing soil. Soil Science Society of America Journal.


Room 107Samuels Building (F25)UNSW, Kensington 2052