New soil moisture monitor powered by a standard digital camera and AI

LinkedIn +

With World Water Day only a week away, a new easy-to-use and affordable method of monitoring soil moisture has been announced by researchers working at the University of South Australia (UniSA) and Baghdad’s Middle Technical University. The solution they have developed uses a standard RGB digital camera to accurately monitor soil moisture under a wide range of conditions.

With buried sensors susceptible to salts in the substrate, current methods for sensing soil moisture are often problematic – requiring specialised hardware for connections. Thermal imaging cameras can be compromised by climatic conditions such as sunlight intensity, fog, and clouds. Associated costs often put such technology out of reach for many farmers in less affluent parts of the world.

The team of engineers behind this new monitoring solution includes Dr Ali Al-Naji and Professor Javaan Chahl who are already world leaders in the use of computer vision to monitor heart and respiratory rates. Originally from Iraq, Dr Al-Naji has a Ph.D. in Electrical & Information Engineering and is an associate professor in the Department of Medical Instrumentation Techniques Engineering at UniSA. Professor Chahl has a Ph.D. in Neuroscience & Robotics and is DST Group Joint Chair of Sensor Systems at UniSA.

Affordable and reliable soil moisture monitoring

The system we trialled is simple, robust and affordable, making it promising technology to support precision agriculture,” Dr Al-Naji says. “It is based on a standard video camera which analyses the differences in soil colour to determine moisture content. We tested it at different distances, times and illumination levels, and the system was very accurate.”

Data were collected during four weeks in an agricultural nursery located in Baghdad, Iraq. A single digital camera (Nikon D5300) was mounted on a tripod at a height of 1.5 m to acquire images of the loam soils throughout the day. The camera was connected to an artificial neural network (ANN) a form of machine learning software that the researchers trained to recognise different soil moisture levels under different sky conditions.

Data collection of the loam soil under four scenarios (a) S1: sunny-dry, (b) S2: sunny-wet, (c) S3: shadow-dry, and (d) S4: shadow-wet.

Data collection of the loam soil under four scenarios (a) S1: sunny-dry, (b) S2: sunny-wet, (c) S3: shadow-dry, and (d) S4: shadow-wet. [Image source: Heliyon]

Using this ANN, the monitoring system could potentially be trained to recognise the specific soil conditions of any location, allowing it to be customised for each user and updated for changing climatic circumstances, ensuing 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,” Prof Chahl says. “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.

The ever increasing importance of water management in farming

With 70% of global fresh water used in agriculture the United Nations predicts that by 2050 many areas of the planet may not have enough water to meet the demands of agriculture based on current patterns of use. One solution to this global dilemma is the development of more efficient irrigation, central to which is precision monitoring of soil moisture, allowing sensors to guide ‘smart’ irrigation systems to ensure water is applied at the optimum time and rate.

Full details of this research project, published in the Open Access journal ‘Heliyon’, are available: Soil color analysis based on a RGB camera and an artificial neural network towards smart irrigation: A pilot study

Share this story:

About Author

mm

Matt has worked in digital publishing for twenty years, holding management positions at Nature (nature.com) and William Reed Business Media (foodmanufacture.co.uk etc.). He has also worked with BBC Worldwide, Centaur Media, UKi Media and Mark Allen Group. Since 2010 Matt has been a digital consultant working with B2B media companies in the agricultural, automotive, aviation, robotics and technology sectors. As Chairman of his local allotment association Matt grows his own food whilst chasing the dream of a one tonne giant pumpkin. He is a member of the British Garden Media Guild and was a finalist in the Garden Media Guild Awards 'blog of the year' category in 2018 and 2019.

Comments are closed.