3 minute read
F aculty Spotlight
Song Cui
Associate Professor, School of Agriculture
MTSU’s 2019 Distinguished Research Award Winner
Song Cui is a broadly trained agronomist with expertise in big data algorithms, crop physiology, forage production, simulation modeling, soil and boundary layer flux (CO 2 , water vapor, and greenhouse gases) measurements, and large-scale agroecosystem studies addressing issues such as water sustainability and climate change. Cui landed a three-year $714,000 grant, the largest ever to MTSU by the U.S. Department of Agriculture (USDA), for collaborative research with Texas A&M and Sam Houston State universities to discover novel ways of land management and solve important ecological problems. He earned his Ph.D. in Crop Science from Texas Tech University and a B.S. in Agricultural Science from Lanzhou University (China).
You were the project leader on the 2016 USDA grant. Where has that agroecological research project taken you? Historically, this kind of cross-state, multi-institutional agroecological project would typically take place at land-grant institutions. With the support from the USDA’s National Institute of Food and Agriculture, a group of researchers at MTSU was actually leading the team this
time. We have quantified carbon footprint and hydrological dynamics from two major forage pasture ecosystems on the MTSU farm, we have evaluated the possibility of using unmanned aircraft systems (UAS) as a way of estimating forage yield and nutritive value, and several students in the School of Agriculture gained invaluable research experience and eventually went to graduate school. As a researcher, I used the large quantity of carbon flux data collected from this project and derived new methods and data analytical routines for processing carbon flux data, which extends the impacts of the project to the entire agroecological society.
How do you see machine-learning technologies and precision agriculture techniques changing the future of agriculture around the world? Precision agriculture (PA), a farming technology proposed in the early 1980s, utilizes high-resolution, remotesensing techniques to study crop and soil variations and to apply farm inputs at the right place, at the right time, and in the right amounts. Most recently, the PA concept has evolved into digital agriculture, which integrates the use of traditional PA approaches to collect, integrate, and transmit data into cloud-based decision-making
Song Cui (r) with Agriculture students
tools that give farmers real-time guidance and feedback on their farming operation. So the key issue is how to bridge the gap between big data collected from various agricultural domains and translate them into decisionmaking processes. Machine learning fits naturally in the groove because it can offer extremely powerful algorithms for classification, which could be used for processes like decision-making or regression, which could be used for estimation or prediction. I see the strong desire from the employer sector for talents with machine-learning skills and good understanding in agriculture. I think forging a strong educational program training a digital agriculture workforce is imperative.
How might these technologies be used to fight climate change? Again, the ability of using data to facilitate fast decisionmaking processes itself can help enhance the overall sustainability of agronomic production. For example, applying the right amount of nitrogen fertilizer at the right place at the right time and manner can help not only cost-saving, but also could minimize losses caused by denitrification and volatilization, both of which can release extremely potent greenhouse gases that cause global warming. Additionally, using technology and big data analytical algorithms to enhance the efficiency of any farming operation could greatly reduce fossil fuel combustion and directly reduce CO 2 emission from a managerial operation perspective. So, the examples could be limitless.
What would you like to share with the MTSU alumni community about the direction of University programs and research involving your area of expertise? Our School of Agriculture program has grown a lot in the past 5–10 years. We have new leaders, new faculty members, new facilities, and new majors. I think we are doing an excellent job in terms of offering hands-on learning opportunities for our students. We would like to keep doing it. Meanwhile, as a precision/digital agriculture scientist, I would like to implement a strong educational program which could better train students on modern technology, data science, and research/development skills at the same time. We have established several collaborative opportunities with stakeholders from the private, state, and even the federal sectors; I am confident we will get there eventually.