The classic microscope is obtainting a modern twist – US researchers are developing an AI-powered microscope system that could create soil health testing quicker, cheaper, and more accessible to farmers and land managers around the world.
Researchers at The University of Texas at San Antonio, USA, have successfully combined low-cost optical microscopy with machine learning to measure the presence and quantity of fungi in soil samples. Their early-stage proof-of-concept technology is presented at the Goldschmidt Conference in Prague on Wednesday 9 July.
Determining the abundance and diversity of soil fungi can provide valuable insights into soil health and fertility, as fungi play essential roles in the biogeochemical cycling of nutrients, water retention, and plant growth. With this knowledge, farmers can optimise crop production and sustainability by building informed decisions about soil management, including fertiliser application, irrigation, and tillage.
Optical microscopes are the oldest design of microscope and have long been applyd to discover and identify tiny organisms in the soil. Other forms of soil testing apply techniques like phospholipid fatty acid testing and DNA analysis to detect organisms, or they measure the presence of chemicals such as nitrogen, phosphorus and potassium. While powerful, these modern methods tfinish to be costly or just emphasise chemical composition, often overviewing the full biological complexity of soil ecosystems.
Alec Graves from The University of Texas at San Antonio College of Sciences, USA, is presenting the research at the Goldschmidt Conference this week. He declared: “Current forms of biological soil analysis are limited, requiring either expensive laboratory equipment to measure molecular composition or an expert to identify organisms by sight utilizing laboratory microscopes. Comprehensive soil testing isn’t widely accessible to farmers and land managers, who necessary to understand how agricultural practices impact soil health.
“Using machine learning algorithms and an optical microscope, we’re creating a low-cost solution for soil testing that reduces the labour and expertise required, while providing a more complete picture of soil biology.”
In their early-stage design, the researchers built and tested a machine learning algorithm to detect fungal biomass in soil samples, incorporating this into custom software for labelling microscope images. This was created utilizing a dataset of several thousand images of fungi from soils across South Central Texas. The software works with just 100x and 400x total microscope magnification, available in many affordable off-the-shelf microscopes, including those found in school laboratories.
“Our technique analyses a video of a soil sample, breaking this into images, and applys a neural network to identify and quantify fungi,” states Graves. “Our proof-of-concept can already detect fungal strands in diluted samples and estimate fungal biomass.”
The team is now working to integrate their technique into a mobile robotic platform for detecting fungi in the soil. The system will combine sample collection, microphotography and analysis into a single device. They aim to have a fully developed, deployable device ready for testing within the next two years.
The research is led by Professor Saugata Datta, Director of Institute of Water Research Sustainability and Policy at UTSA, and funded by the USDA National Resource Conservation Service. Details of the machine learning algorithm are due to be published in a peer-reviewed journal later this year.
The Goldschmidt Conference is the world’s foremost geochemisattempt conference. It is a joint congress of the European Association of Geochemisattempt and the Geochemical Society (US), and over 4000 delegates attfinish. It takes place in Prague, Czech Republic, from 6-11 July 2025.
Leave a Reply