Overview

On June 27, 2026, researchers at Chandigarh University announced the development of an Artificial Intelligence‑powered lightweight transformer model designed to predict crop yields with high accuracy. The model leverages multi‑source data—including Sentinel‑1 and Sentinel‑2 satellite imagery from the European Space Agency, climatic variables such as rainfall, temperature and soil moisture, and historical crop production records spanning 2019 to 2023—to generate pre‑harvest yield forecasts for four major crops cultivated in Punjab’s Ludhiana district: paddy, maize, moong and sugarcane.

Research Team and Presentation

The research was led by Assistant Professor Kusum Lata of the Department of Computer Science Engineering, together with Professors Navneet Kaur and Simrandeep Singh from the University Centre of Research and Development. The findings were presented at the 2026 International Conference on Signal Processing and Electronics Design (ICSPED) held at Chandigarh College of Engineering and Technology.

Model Characteristics and Advantages

The transformer architecture is described as lightweight, requiring nearly 40 percent fewer parameters than conventional transformer models while delivering faster and more accurate predictions. Unlike traditional machine‑learning approaches, the model can identify critical crop growth stages and learn complex temporal patterns, making it suitable for deployment in large‑scale agricultural monitoring systems with lower computational costs.

Performance Evaluation

Experimental evaluation on the four target crops demonstrated that the transformer model outperformed widely used Random Forest and Long Short‑Term Memory (LSTM) models. It showed stronger agreement between predicted and actual yields, lower prediction errors, and improved computational efficiency.

Practical Implications

Accurate pre‑harvest forecasts are positioned to support farmers, policymakers and agricultural agencies by enabling better agricultural planning, optimized resource allocation, strengthened crop‑insurance mechanisms and more effective market‑management strategies. In a state where agriculture is central to the economy, such technology is expected to contribute to more resilient and sustainable farming systems.

Future Development

The research team indicated plans to enable near real‑time forecasting through cloud‑based platforms, facilitating broader adoption of AI‑driven decision‑support systems across the agricultural sector.

About Chandigarh University

Chandigarh University is a NAAC A+‑graded, QS‑world‑ranked autonomous institution approved by the UGC and located near Chandigarh, Punjab. It is the youngest university in India and the only private university in Punjab to receive an A+ grade from NAAC. The university offers more than 109 undergraduate and postgraduate programmes across engineering, management, pharmacy, law, architecture, journalism, animation, hotel management, commerce and other fields, and has been recognised as the University with Best Placements by the World Corporate Roundtable (WCRC).

---