Modelling daily plant growth response to environmental conditions in Chinese solar greenhouse using Bayesian neural network

Understanding how plants respond to environmental conditions such as temperature, CO2, humidity, and light radiation is essential for plant growth. This paper proposes an Artificial Neural Network (ANN) model to predict plant response to environmental conditions to enhance crop production systems that improve plant performance and resource use efficiency (e.g. light, fertiliser and water) in a Chinese Solar Greenhouse. Comprehensive data collection has been conducted in a greenhouse environment to validate the proposed prediction model. Specifically, the data has been collected from the CSG in warm and cold weather. This paper confirms that CSG's passive insulation and heating system was effective in providing adequate protection during the winter. In particular, the CSG average indoor temperature was 18 C-? higher than the outdoor temperature. The difference in environmental conditions led to a yield of 320.8g per head in the winter after 60 growing days compared to 258.9g in the spring experiment after just 35 days. Three different architectures of Bayesian Neural Networks (BNN) models have been evaluated to predict plant response to environmental conditions. The results show that the BNN network is accurate in modelling and predicting crop performance.

Automated summary

Understanding how plants respond to environmental conditions is crucial for plant growth. This paper proposes using an Artificial Neural Network (ANN) model to predict plant response to environmental conditions in a Chinese Solar Greenhouse to improve crop production systems. Comprehensive data collection has been conducted in a greenhouse environment to validate the proposed prediction model. The results show that the Bayesian Neural Networks (BNN) models accurately predict crop performance.