The integration of artificial intelligence (AI) and big data in agriculture is set to transform the industry, and North Carolina State University (NC State) is at the forefront of this revolution. The recent appointment of Debjani Sihi as an assistant professor in the Departments of Plant and Microbial Biology and Crop and Soil Sciences marks a significant step forward. Sihi’s expertise in biogeochemistry and her innovative approach to applying AI in agricultural practices promise to drive substantial advancements in the field. As the first AI-focused cluster hire in the College of Agriculture and Life Sciences, she symbolizes the critical role of interdisciplinary work that bridges advanced data science with practical agricultural applications, positioning NC State to lead AI-driven sustainability solutions.
A Unique Expertise in Biogeochemistry
Debjani Sihi brings a wealth of knowledge and experience to NC State. Prior to her appointment, she was a faculty member at Emory University, where she led research on soil carbon dynamics and mentored students in environmental sciences. Sihi earned her Ph.D. in soil and water science from the University of Florida, focusing on soil organic matter dynamics and greenhouse gas emissions in subtropical wetlands. Her postdoctoral work at the University of Maryland Center for Environmental Science and Oak Ridge National Laboratory involved biogeochemical modeling and soil greenhouse gas emissions.
Sihi’s fascination with the minor interactions in soil that significantly impact ecosystems and agriculture has driven her career. She believes that integrating AI into this field presents once unimaginable opportunities. Her appointment highlights the importance of her interdisciplinary work, bringing together biogeochemistry and AI to transform agricultural practices. At Emory University, Sihi was known for her innovative research and mentorship. Her diverse background and experience in biogeochemical modeling provide a unique perspective to address complex agricultural challenges with AI-driven solutions.
Integrating Advanced Technologies
To achieve her research objectives, Debjani Sihi plans to utilize a range of advanced technologies, including sensors, imaging, and molecular tools to gather comprehensive data on soil and ecosystem processes. This data is essential for understanding how different elements within the agricultural environment interact and impact each other. By employing machine learning and process-based models, Sihi aims to predict productivity, greenhouse gas emissions, and carbon and nutrient cycling under various environmental conditions and land management scenarios. This predictive capability is crucial for developing effective agricultural practices and policies that address environmental sustainability and food security.
Sihi’s research will focus on the intricate interactions within the plant-soil-microbe-atmosphere continuum, aiming to integrate advanced technologies, employ modeling approaches, and address scalable solutions. The use of AI in agriculture transcends solitary studies, requiring a data-driven approach to decipher the mechanisms and build comprehensive models. By leveraging these technologies, Sihi’s work will contribute to understanding the complexity of agricultural environments and provide actionable insights for sustainable practices.
Addressing Scalable Solutions
One of Sihi’s primary research focuses will be on scalable solutions related to climate change mitigation, food security, and environmental sustainability. Through data-supported agricultural practices, she seeks to recommend practices like cover cropping, reduced tillage, soil amendments, or combinations of these to reduce the environmental footprint of agricultural systems. However, Sihi emphasizes the importance of having concrete evidence to support these recommendations. She aims to answer critical questions such as whether these practices increase growers’ profitability or provide other benefits, and whether the impacts, such as carbon sequestration and reduced greenhouse gases, are permanent or temporary.
This evidence is essential for building sound decision-making and policymaking. By addressing scalability, Sihi’s work ensures that agricultural innovations can be implemented on a broad scale, benefiting numerous stakeholders. Her focus on data-supported practices emphasizes the importance of evidence-based recommendations. This approach will foster trust among growers and policymakers, leading to informed decisions and long-term sustainability in agriculture.
The Data Challenge in Agriculture
The proliferation of agricultural data instruments on farms and research facilities has created a significant yet scattered data field, posing a challenge in coordinating and combining data from various locations and scales effectively. While the availability of data is no longer a limitation, data sharing and ethical issues present significant challenges. Sihi acknowledges these challenges and emphasizes the importance of communicating the value of public/private partnerships, such as the land grant system, to stakeholders.
These partnerships could accelerate understanding and advancements in agricultural practices. Sihi envisions forming collaborations within her cluster area, the North Carolina Plant Sciences Initiative (N.C. PSI), and other colleges within the university to create action-oriented work. She aims to evaluate management practices through multi-scale measurements that could have broad and immediate applications. By addressing the data challenge, Sihi’s work will contribute to creating a cohesive data ecosystem that enhances the effectiveness of AI-driven agricultural practices.
Building on Existing Foundations
Sihi is particularly excited about the opportunity to build on the groundwork already laid by her colleagues and through platforms like the N.C. PSI and the Center for Environmental Farming Systems (CEFS). She sees great potential to improve understanding and mapping of plant and soil properties or ecosystem services in heterogeneous landscapes. This can be achieved through a bottom-up approach starting at the microbe and soil cores at the field level and a top-down approach from satellite data to drone measurements.
By growing datasets in both directions, a comprehensive pool of data can be created, ultimately benefiting farmers by providing actionable insights. Sihi foresees a future where algorithms can guide real-time decision-making, helping reduce agriculture’s environmental footprint while maintaining yield. This involves assessing variables like time, amendments, fertility, and resources such as irrigation to provide the greatest benefit at the moment. By leveraging existing foundations and expanding data collection, Sihi’s work aims to create a robust framework for actionable insights in agriculture.
Opportunities for Students and Future Research
To achieve her research goals, Debjani Sihi intends to leverage advanced technologies like sensors, imaging, and molecular tools to collect extensive data on soil and ecosystem processes. This information is crucial for understanding interactions in the agricultural environment and their impacts. Sihi plans to use machine learning and process-based models to predict productivity, greenhouse gas emissions, and carbon and nutrient cycling under various environmental conditions and land management scenarios. This predictive power is vital for creating effective agricultural practices and policies that promote environmental sustainability and food security.
Sihi’s research will delve into the complex interactions within the plant-soil-microbe-atmosphere continuum. She aims to combine advanced technologies with modeling approaches to develop scalable solutions. AI’s use in agriculture goes beyond isolated studies, needing a data-centric approach to understand mechanisms and develop comprehensive models. By utilizing these technologies, Sihi’s research will enhance our grasp of agricultural environments’ complexity and offer actionable insights for sustainable practices.
