Researchers have leveraged Climate Data and Satellite Technology for developing the predictive model

CHANDIGARH, India , June 27, 2026 /PRNewswire/ -- In a significant advancement for smart agriculture and precision farming, researchers at Chandigarh University have developed an Artificial Intelligence (AI)-powered Transformer Model that is capable of accurately predicting crop yields using satellite imagery, climate data and historical agricultural records.

The innovation would be instrumental in empowering farmers, policymakers and agricultural agencies to make informed decisions while strengthening food security and advancing resilient farm management.

The research, led by Kusum Lata, Assistant Professor Department of Computer Science Engineering, Chandigarh University, Dr Navneet Kaur Professor Department of CSE and Dr Simrandeep Singh Professor from University Centre of Research and Development at Chandigarh University that focuses on improving crop yield forecasting in Punjab's agricultural heartland. The study, recently presented at the 2026 International Conference on Signal Processing and Electronics Design (ICSPED) at Chandigarh College of Engineering and Technology, Chandigarh that introduces a lightweight transformer-based system that leverages multi-source data to estimate crop production before harvest with greater accuracy and lower computational costs.

Notably, the accurate crop yield prediction has become increasingly important as farmers face growing challenges from climate variability, changing weather patterns and rising food demand. Traditional field surveys are often time-consuming, labour-intensive and limited in scale. The Chandigarh University researchers sought to overcome these limitations by integrating advanced AI techniques with real-time Earth observation data.

Kusum Lata, Assistant Professor Department of Computer Science Engineering at CU said, "The transformer model utilizes data from Sentinel-1 and Sentinel-2 satellites which are advanced Earth observation satellites operated by the European Space Agency (ESA) to continuously monitor agricultural fields and provide information on crop growth, vegetation health, soil moisture and field conditions. The satellite observations are combined with climatic variables such as rainfall, temperature and soil moisture, along with historical crop production records, creating a comprehensive picture of crop performance throughout the growing season."

Kusum added, "Unlike conventional machine learning models, the newly developed lightweight transformer can identify critical crop growth stages and learn complex temporal patterns that influence final yields. We have designed the model to deliver high predictive performance that require fewer computational resources, making it suitable for practical deployment in large-scale agricultural monitoring systems."

"The model was evaluated on four major crops cultivated in Ludhiana district, namely paddy, maize, moong and sugarcane, using data collected between 2019 and 2023. Experimental results demonstrated that the transformer model outperformed widely used approaches such as Random Forest and Long Short-Term Memory (LSTM) models, indicating stronger agreement between predicted and actual yields. The framework also recorded lower prediction errors and improved computational efficiency.

Kusum has worked as a Junior Research Fellow in the Agriculture and Crop Monitoring Division at Punjab Remote Sensing Centre (PRSC), PAU Ludhiana, contributed to geospatial research projects, including crop residue burning analysis using remote sensing and geospatial mapping techniques.

The study further revealed that the lightweight architecture requires nearly 40 percent fewer parameters than conventional transformer models while delivering faster and accurate predictions. This level of efficiency makes this automatic framework suitable for near real-time agricultural applications, including regional crop monitoring, production forecasting and early warning systems.

According to the researchers, the ability to accurately forecast crop yields before harvest can have significant implications for farmers and governments alike. Reliable forecasts can support agricultural planning, optimize resource allocation, strengthen crop insurance mechanisms and improve market management strategies. In a state like Punjab, where agriculture plays a central role in the economy, such technologies can contribute to more resilient and sustainable farming systems.

The researchers also shared that one of the key strengths of the model lies in its ability to combine multiple sources of information into a single predictive model. By integrating satellite-derived observations with climatic and historical datasets, the system captures the complex interactions that influence crop productivity and provides a more robust understanding of agricultural outcomes.

The future developments will also focus on enabling near real-time forecasting through cloud-based platforms, paving the way for broader adoption of AI-driven decision support systems in agriculture, added the Chandigarh University researchers.

About Chandigarh University

Chandigarh University is a NAAC A+ Grade University and QS World Ranked University. This autonomous educational institution is approved by UGC and is located near Chandigarh in the state of Punjab. It is the youngest university in India and the only private university in Punjab to be honoured with A+ Grade by NAAC (National Assessment and Accreditation Council). CU offers more than 109 UG and PG programs in the field of engineering, management, pharmacy, law, architecture, journalism, animation, hotel management, commerce, and others. It has been awarded as The University with Best Placements by WCRC.

Website address: https://www.cuchd.in/

Photo: https://mma.prnewswire.com/media/3001456/Chandigarh_University_AI_Crop_Yield.jpg

“This is a company press release that is not part of editorial content. No journalist of The Hindu was involved in the publication of this release.”