Field experiments are a very important part of agricultural production, and they are important means for agricultural researchers to study the effects of crop varieties, fertilization, irrigation, and other factors on crop growth and development. Every year, researchers conduct a large number of experiments in experimental fields to explore optimal planting plans for different crop varieties and environmental factors. The data obtained from these experiments are objective records of the factors affecting agricultural production and have important guiding significance for improving agricultural production.

However, analyzing field trial data is an extremely tedious and time-consuming task. Traditional data processing methods require steps such as analyzing database data, conducting experimental data statistics, classifying, and filtering, which can lead to problems such as insufficient comparison conditions, data omissions, and errors. In order to improve the efficiency and accuracy of data processing, Nemet began to try ChatGPT, an artificial intelligence, to apply to field experiment data processing by using its own synthetic biology active substance database, combined with massive agricultural databases and information sources around the world.

After experimental verification, the field test data of the biostimulant developed by Namet, analyzed by ChatGPT, showed significant positive differences compared to CK, with an accuracy of nearly 100%.

Next, NMT will train ChatGPT to help researchers better understand and analyze the impact of biostimulants on crop growth, so as to select appropriate agricultural chemicals, improve the utilization rate of agricultural means of production, and provide relevant environmental governance programs.