English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This study explored the possibility of estimating nitrogen content in a pasture grass using thermal images and artificial neural networks (ANN), based on the premise that plant herbage with a higher N content would be absorbing more light energy for active photosynthesis, therefore emitting excess energy as heat. This is the first reported study to use thermal infrared images and ANN to estimate pasture nitrogen content under different conditions of nitrogen (N) fertiliser. The research was conducted in a controlledclimate environment to isolate the effect of a key environmental parameter, available soil N, on pasture grass herbage temperatures. The project was the first step towards developing a smart fertiliser spreader to manage N applications based on plant temperature. A small glasshouse pot experiment was conducted to determine the degree of the correlations between leaf N content and the surface temperatures of perennial ryegrass (Lolium perenne) herbage. Using a thermal imaging camera, periodic measurements of the herbage surface temperatures were made in conjunction with herbage cuts and analysis of grass dry matter for % N content. At the same time, other environmental factors, such as air temperature and humidity, were also measured. As data constituted the core of the study, the database should be flexible, accessible and simple, for both data entry and data analysis. Subsequently, an ANN model was developed to predict N content based on herbage temperatures and the other factors measured. The final ANN model was developed based on three input variables: plant temperature, number of days after planting, and number of days after the last nitrogen application, with an error margin of ± 0.93 and ± 0.87 %N for the training and validation data, respectively. Comparing actual and predicted data showed that the ANN model could be fitted to pasture nitrogen content and accounted for around 84% and 92% of the variance in the training and validation data, respectively. The outcome of this study will aid the development of technology for estimating nitrogen content of perennial ryegrass (Lolium perenne) under field conditions which was seen as critical in the design of an advanced fertiliser spreader to manage nitrogen application on farms.

Predicting pasture nitrogen content using ANN Models and thermal images