Current research interests: My current research interest lies in UAV Thermal image processing and machine/deep learning approaches to improve understanding of water use of wheat genotypes and yield forecasting, particularly in sodic soil under water-limited environments to help identify cultivars tolerant to sodic soil constraints. Demand for food and other agricultural products is projected to increase by 50% globally by 2050. This increasing food demand places growing pressure on agricultural production at a time where there is little scope to expand agricultural lands. In addition, other constraining factors, such as soil and environmental constraints negatively impact productivity at global scale. To help ensure future food security, we must improve soil-crop management practices to achieve optimum yield. One major area where productivity could be improved is for crops grown on dispersive sodic soils, which currently affect over 581 million ha worldwide. One strategy is to identify crops and/or cultivars that are more stress tolerant on sodic soil and can improve agricultural productivity. The advancement of remote sensing techniques and a variety of earth observation data provide useful insights into seasonal and in-field soil-crop variability that can be used for crop yield simulations to understand the drivers, mechanisms, and impact of crop yield variability. With the emergence of big data, machine learning, high-performance computing, and precision agriculture, new challenges require new solutions. In recent years, unmanned aerial vehicle (UAV)-based thermal imaging techniques has become popular in precision agriculture for detecting crop diseases and stresses, and this technique has significant potential to also assess crop performance on sodic soils. My research provides improved understanding of how UAV thermal imaging techniques can be used as a viable technological solution to monitor crop temperature and quantify abiotic stresses (sodicity, water stress, physiological drought, etc.), which is one of the major causes for yield loss of the major rain-fed field crops, particularly wheat. Being able to identify plant abiotic stress is a primary requirement to identify more or less tolerant species or cultivars within a species grown on sodic soil under rain-fed conditions. Solutions to real-world agricultural problems typically require a thorough understanding of crops’ physiological processes and how they respond to soil and environmental stresses. Agricultural management issues are typically multidimensional and exist at multiple spatial and temporal scales. Dealing with such complex, multidimensional problems often invoke the use of quantitative and integrated approaches. Hence my research is focused on integrating UAV remote sensing and machine learning techniques to improve understanding of wheat genotypes adaptation on sodic soils. The overall goal of my research program is to provide farmers, breeders, and agricultural policy makers with useful information and tools that will enable them to make better management decisions towards sustainable food security in the face of limited land resources and other increasing soil and climatic constraints. References: 1. Armstrong, RD, Eagle, C & Flood, R 2015, 'Improving grain yields on a sodic clay soil in a temperate, medium-rainfall cropping environment', Crop and Pasture Science, vol. 66, no. 5, pp. 492–505 2. Dang, Y, Dalal, R, Routley, R, Schwenke, G & Daniells, I 2006, 'Subsoil constraints to grain production in the cropping soils of the northeastern region of Australia', Australian Journal of Experimental Agriculture, vol. 46, pp. 19-35 3. Deery, DM, Rebetzke, GJ, Jimenez-Berni, JA, James, RA, Condon, AG, Bovill, WD, Hutchinson, P, Scarrow, J, Davy, R & Furbank, RT 2016, 'Methodology for High-Throughput Field Phenotyping of Canopy Temperature Using Airborne Thermography', Frontiers in Plant Science, vol. 7, p. 1808


Funding: 1. The University of Queensland 'International RTP scholarship' - Sumanta Das, The Australian Grains Research and Development Corporation (GRDC) project funding - Dr. Yash Dang (principal advisor)

Project members

Sumanta Das

PHD candidate
School of Agriculture and Food Science