Harnessing technology to solve complex problems

Growing up in Rajshahi, Bangladesh, Dristi Datta was surrounded by a rich agricultural heritage and a vibrant community life. A fascination with technology and its potential to solve real-world problems led Dristi to pursue tertiary studies in electrical and electronic engineering. But it was his desire to apply these skills to agriculture that brought him to Australia.

“I moved to Australia in 2022 to further my studies in computer science with a focus on agricultural remote sensing, and I’m excited to be pursuing a PhD in this field with the Soil CRC and Charles Sturt University,” he said.

Dristi’s research aims to develop an imagery-based decision support system for soil assessment. The goal is to be able to predict soil properties in vegetation-covered areas by establishing the relationship between vegetation health patterns and soil contents.

“Combining principles from remote sensing, learning-based models, and soil science enables me to explore novel approaches for soil assessment that bridge the gap between traditional laboratory methods and large-scale field applications,” Dristi said.

“The prospect of developing practical tools that address the needs of agricultural stakeholders motivates me to push the boundaries of current knowledge in this field,” he enthused. “This drive to innovate and create impactful solutions is what led me to pursue my PhD studies.”

Dristi explained that prediction of different soil properties, such as soil moisture, carbon, and nitrogen, is a significant field of study due to their direct impact on plant health and food production.

“Traditional methods for estimating these properties, like oven-drying and chemical analysis, are time-consuming and resource-intensive, and can only be applied to small land areas,” he said.

“With the development of remote sensing technologies, including satellite sensors and multi/hyperspectral imaging, it is now possible to predict different soil contents in a non-invasive and cost-effective manner for large areas of bare soil.

“However, farmers and other stakeholders often need to predict soil content for vegetation-covered soil areas to make immediate decisions, such as applying fertilisers or estimating yields during the growing season,” he said.

Dristi’s research is evaluating the performance of different learning-based models to predict a number of soil properties using lab-based hyperspectral data, achieving the highest possible performance with this technology.

“We’re exploring the possibilities of predicting soil properties from satellite data for mixed areas (both bare and vegetation-covered soil) to determine if satellite images can provide accuracy comparable to lab-based hyperspectral datasets,” he said.

“My research aims to provide farmers and stakeholders with a powerful decision support system that utilises remote sensing imagery to accurately predict soil properties in both bare and vegetation-covered areas.

“By offering non-invasive and cost-effective soil assessment tools, my research can empower agricultural practitioners to make informed decisions about crop management practices, such as fertiliser application and yield estimations. This, in turn, leads to improved productivity and sustainable land use.”

Dristi is relishing the opportunity to harness cutting-edge technologies to tackle real-world challenges in agriculture.

“I am passionate about developing innovative solutions that have the potential to revolutionise how we assess and manage soil health, ultimately contributing to global food security and environmental sustainability,” he said.

Through his research, Dristi has already contributed to thedevelopment of a novel Hybrid Bayesian Attention Model (HBAM) and ‘ReflecGAN’ for estimating soil organic carbon from satellite data. The HBAM can adequately estimate soil carbon from bare soil, while the proposed ‘ReflecGAN’ can estimate soil carbon from vegetation-covered fields.

“These achievements represent significant advancements in this field and have the potential to make a real impact on sustainable agriculture and soil management practices,” he said.

“Working with my Charles Sturt University supervisors, Dr Paul, Dr Murshed, Dr Teng and Dr Schmidtke, has been extremely rewarding. I’m eager to share our findings with the broader research community through our upcoming publications and conference presentations.”

Dristi is also passionate about interdisciplinary collaboration, and its importance in addressing complex challenges in agriculture and environmental conservation. He advocates for combining insights from various fields to help develop more comprehensive and effective solutions.

“I am committed to mentoring the next generation of researchers and professionals, sharing my knowledge and experiences to inspire and guide them in their pursuits. Through continuous learning and innovation, I hope to make a lasting impact on sustainable agriculture and global food security,” he said.

When Dristi isn’t working to solve complex problems, you’ll find him capturing the beauty of our natural landscapes and agricultural fields with his digital camera.

“I have a keen interest in photography, which I developed during my travels and fieldwork for research,” he said. “It allows me to appreciate the intricate details of nature and share them with others, which provides a creative outlet and also deepens my connection to the very subjects I study in my research.”

Dristi is on track to submit his PhD thesis later this year and is keen to continue working at the intersection of agriculture, technology, and environmental conservation.

“Whether in academia, industry, or government, I aim to apply my expertise to develop practical solutions that address pressing challenges in sustainable agriculture and land management,” he said.

“My goal is to contribute to global efforts towards creating a more resilient and food-secure future.”

You can hear more about Dristi’s research at the 2024 Soil CRC Participants Conference in August. Register now to join us.

Find out more

Read Dristi’s publications:

• Datta, D., Paul, M., Murshed, M., Teng, S. W., & Schmidtke, L. (2022). Soil Moisture, Organic Carbon, and Nitrogen Content Prediction with Hyperspectral Data Using Regression Models. Sensors, 22(20), 7998. https://doi.org/10.3390/s22207998
• Datta, D., Paul, M., Murshed, M., Teng, S. W., & Schmidtke, L. (2023). Comparative Analysis of Machine and Deep Learning Models for Soil Properties Prediction from Hyperspectral Visual Band. Environments, 10(5), 77. https://doi.org/10.3390/environments10050077
• Datta, D., Paul, M., Murshed, M., Teng, S. W., & Schmidtke, L. M. (2023). Novel Dry Soil and Vegetation Indices to Predict Soil Contents from Landsat 8 Satellite Data. In 2023 International Conference on Digital Image Computing: Techniques and Applications (DICTA) (pp. 152-159). IEEE. https://doi.org/10.1109/DICTA60407.2023.00029

Connect with Dristi online:

• Soil CRC student profile
• LinkedIn
• ResearchGate
• Google Scholar
• Scopus
• University profile