Automated Irrigation and Fogging System with Temperature predictive Capability for Greenhouse Farming

Abstract Farmers in sub-Saharan Africa are plagued with the challenges of climate change, farmers-headers clash, resulting in low production. Greenhouse farming is seen as a way out due to small space required and ability to control microclimate. Tropical Greenhouses are usually very hot in the afternoon resulting in water and heat stress. This work develops an automated system that monitors microclimate in real-time, regulate temperature and provides prediction of future water needs to aid future management. A data acquisition system using Atmega 382 microcontroller and a DHT22 was used for monitoring and control while Raspberry Pi was used for future temperature prediction. At a threshold temperature of 30 ℃, the microcontroller activates a fogging pump to release mist into the greenhouse to cool the heat-stressed leaves thus enhancing photosynthesis. Irrigation is also activated using drip system. Raspberry Pi combined with DHT22 is used to collect temperature and humidity measurement which were used to train a machine learning algorithm and stored Google sheets in the cloud. The experimental result reveals the ability of the system to perform greenhouse automation, monitoring, and control of fogging and irrigation remotely as well as temperature prediction. Machine learning models: linear regression (LR), support vector regression (SVR) and random forest regression (RFR) were trained with acquired data and the results were compared. The results revealed accuracy (RFR: 98.43%, SVR: 98.54%, LR: 98.57%), and MAE (RFR: 0.47, SVR: 0.44, LR: 0.43). The developed system will enhance greenhouse agriculture and boost food production, especially in the tropics.