About the Project
The use of ML to interpret soil profile characteristics from profile imagery has been successful in estimating specific properties such as organic matter and carbon content , pH  and texture . The proposed work will develop a tool through machine learning techniques and model development approaches (e.g. least absolute shrinkage and selection operator (LASSO)), to identify and predict properties and functions of soil within a profile. The project will focus on (1) the recognition of specific diagnostic soil properties, (2) integration of diagnostic properties into an overall soil profile assessment, and (3) estimation of soil characterisation and ecosystem service provision.
Libraries of soil profile imagery exist at national and global scales, and many are freely available. The student will develop a database of soil profile images with associated properties and features and will attribute those properties and features to specific locations within the images. Statistical techniques will be used to recognise these properties and features within the profile images and integrating them into a whole-profile assessment and characterisation. A further level of machine learning algorithms will be developed and trained through assimilation of these data. The trained system will be tested and demonstrated using soil profile pits in the field, using a smartphone app developed as part of the project and using chemical/physical analysis of soil samples to provide validation/comparison of soil property estimates. In addition, the student will use it to participate as an entrant in soil chemical analyses as an additional way of promoting the work and demonstrating the effectiveness of this approach.
More project details are available here: https://www.quadrat.ac.uk/projects/automated-soil-profiling-identification-of-soil-characteristics-using-machine-learning-and-image-analysis/
How to apply: https://www.quadrat.ac.uk/how-to-apply/
Before applying please check full funding and eligibility information: https://www.quadrat.ac.uk/funding-and-eligibility/
Matt Aitkenhead, David Donnelly, Malcolm Coull, Richard Gwatkin, 2016. Estimating soil fertility indicators with a mobile phone. Chapter 7 of 'Digital Soil Morphometrics'; Book series "Progress in Soil Science" by Springer (http://www.amazon.co.uk/Digital-Soil-Morphometrics-Progress-Science-ebook/dp/B01DXI295Y).
Aitkenhead, M.J., Coull, M.C., Gwatkin, R., Donnelly, D., 2016. Automated soil physical parameter assessment using smartphone and digital camera imagery. Journal of Imaging 2(4), 35; DOI 10.3390/jimaging2040035.
Based on your current searches we recommend the following search filters.
Based on your current search criteria we thought you might be interested in these.
(BBSRC DTP) Wine-making berry and grapevine condition monitoring using multi-band electromagnetic transmission characteristics: Feasibility analysis and post-harvest application
The University of Manchester