Quantification of hydrocarbon abundance in soils using deep learning with dropout and hyperspectral data
- Submitting institution
-
Kingston University
- Unit of assessment
- 12 - Engineering
- Output identifier
- 12-029-1585
- Type
- D - Journal article
- DOI
-
10.3390/rs11161938
- Title of journal
- Remote Sensing
- Article number
- -
- First page
- 1938
- Volume
- 11
- Issue
- -
- ISSN
- 2072-4292
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
-
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper presents an original use of deep learning combined with spectral unmixing for the quantification of hydrocarbon spills in soils. This is significant because the methodology allows not just to detect but also to quantify the level of soil contamination as a consequence of industrial accidents or natural disasters and also because the methodology can be applied to a wide range of applications, including mapping and measuring soil characteristics of moisture, nitrogen, phosphorus, potassium, organic carbon, and hydrocarbons.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -