By Scout Nelson
Artificial intelligence is playing an increasing role in agriculture, but questions remain about how farmers can trust the recommendations made by these systems. To address this, University of Nebraska–Lincoln professor Sruti Das Choudhury is leading innovative research on explainable AI.
Her projects, including Explainable AI for Precision Agriculture: A Data-Driven Approach to Crop Recommendation and Explainable Artificial Intelligence for Phenotype-Genotype Mapping Using Time-Series Data Analytics, are designed to make AI’s decision-making process more transparent.
“We will have an answer, an explanation of the output of the model, and we can verify that explanation with the existing knowledge of the farmers,” Das Choudhury said.
Explainable AI allows users to see which factors—such as soil pH, rainfall, or temperature—most influenced the recommendation. This not only builds trust but also ensures that predictions are aligned with farmers’ real-world understanding. “That's the idea, like deeper insight into the predictions that AI model is making, and if we can do that, that will make the model more transparent, interpretable and trustworthy and will adhere to the ethical aspects of AI,” she explained.
Working alongside her are undergraduate students Sanjan Baitalik and Rajashik Datta from India, who have applied AI interpretability techniques such as LIME, SHAP, and machine learning models like K-means and neural networks. Together, they have produced rapid results, even submitting a research paper by August 2025.
The team is currently working without funding, but Das Choudhury hopes early results will strengthen applications for grants. She has also proposed a semester-long course on AI, computer vision, and data analytics for agriculture to further train students.
“It would help farmers understand why an AI system makes certain predictions or decisions rather than having to just accept the decisions blindly," she said.
By combining advanced data science with practical agriculture, this work could set a new standard for trustworthy AI applications in farming.
Photo Credit:istock-primeimages
Categories: Nebraska, Crops