Developing an Integrated AI Model for Predictive Maintenance in Hydroponics

Hydroponics have gained attention due to their ability to cope with future food needs. However, the farmers face the issue of maintenance: if done frequently, it is expensive, and if done rarely, it risks crop failure. This paper aims to ideate a setup of AI models for maintenance to be predictive, reducing crop failure risk while making maintenance more profitable. The model must be able to predict future readings of various conditions that can indicate a crop failure. For this reason, I found the various measurements that can indicate crop failure, and which sensors can detect them. The factors were yield prediction, component malfunction, nutrition, electrical conductivity, power of hydrogen, and environmental factors (temperature, humidity, and light intensity). Next, I collected various studies done on how different models predict each of these factors. The results showed that for yield prediction, deep neural network; for component malfunction, random forest; nutrition, random forest and support vector regression; for electrical conductivity and power of hydrogen, nonlinear autoregressive with exogeneous inputs; and for environmental factors, extreme gradient boosting were the promising AI models. Also, deep neutral networks can be trained to mimic other model’s decisions, which can lower economic investment of the various AI models.