Neural network and digital camera can detect soil moisture - International Burch University
IoT: Swarm Takes LoRa Technology Sky-High
April 1, 2021
Header Britton Haysom Creative Review NFT Wide
April 5, 2021

Neural network and digital camera can detect soil moisture

Researchers have developed a system for monitoring soil moisture, using just a standard digital camera paired with an artificial neural network.

Neural network

The planet may not have enough fresh water to meet the demands of agriculture by 2050. That is prediction of the United Nations, so more efficient soil irrigation could help to alleviate this upcoming problem.

The University of South Australia team found that current methods for sensing soil moisture are problematic. Because, buried sensors are susceptible to salts in the substrate and require specialized hardware for connections. Meanwhile, thermal imaging cameras are expensive and can be compromised by climatic conditions such as sunlight intensity, fog, and clouds.

“The system we trialed is simple, robust and affordable, making it promising technology to support precision agriculture,” said Dr Ali Al-Naji. Dr Ali Al-Naji is researcher that provide this machine learning solution. “It is based on a standard video camera which analyses the differences in soil color to determine moisture content. We tested it at different distances, times and illumination levels, and the system was very accurate.”

The camera was connected to trained artificial neural network. It is trained by the researchers to recognize different soil moisture levels under different sky conditions. Using this network, the monitoring system could potentially be trained to recognize the specific soil conditions of any location. This allowed it to be customized for each user and updated for changing climatic circumstances, ensuring maximum accuracy.

“Once the network has been trained it should be possible to achieve controlled irrigation by maintaining the appearance of the soil at the desired state,” Professor Javaan Chahl said. “Now that we know the monitoring method is accurate, we are planning to design a cost-effective smart-irrigation system based on our algorithm using a microcontroller, USB camera and water pump that can work with different types of soils.

“This system holds promise as a tool for improved irrigation technologies in agriculture in terms of cost, availability and accuracy under changing climatic conditions.”


Department of Electrical and Electronics Engineering