A Machine Learning approach for automatic land cover mapping from DSLR images over the Maltese Islands

2018 ◽  
Vol 99 ◽  
pp. 1-10 ◽  
Author(s):  
A. Gauci ◽  
J. Abela ◽  
M. Austad ◽  
L.F. Cassar ◽  
K. Zarb Adami
Keyword(s):  
Machine Learning ◽  
Land Cover ◽  
Land Cover Mapping ◽  
Learning Approach ◽  
Maltese Islands ◽  
Machine Learning Approach

scholarly journals JUNGLE-NET: USING EXPLAINABLE MACHINE LEARNING TO GAIN NEW INSIGHTS INTO THE APPEARANCE OF WILDERNESS IN SATELLITE IMAGERY

2021 ◽  
Vol V-3-2021 ◽  
pp. 317-324
Author(s):  
T. Stomberg ◽  
I. Weber ◽  
M. Schmitt ◽  
R. Roscher
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Land Cover ◽  
Observational Data ◽  
Satellite Imagery ◽  
Learning Approach ◽  
Scene Classification ◽  
Machine Learning Approach ◽  
New Knowledge

Abstract. Explainable machine learning has recently gained attention due to its contribution to understanding how a model works and why certain decisions are made. A so far less targeted goal, especially in remote sensing, is the derivation of new knowledge and scientific insights from observational data. In our paper, we propose an explainable machine learning approach to address the challenge that certain land cover classes such as wilderness are not well-defined in satellite imagery and can only be used with vague labels for mapping. Our approach consists of a combined U-Net and ResNet-18 that can perform scene classification while providing at the same time interpretable information with which we can derive new insights about classes. We show that our methodology allows us to deepen our understanding of what makes nature wild by automatically identifying simple concepts such as wasteland that semantically describes wilderness. It further quantifies a class’s sensitivity with respect to a concept and uses it as an indicator for how well a concept describes the class.

scholarly journals Fusion of Radar and Optical Data for Land Cover Classification Using Machine Learning Approach

2020 ◽  
Vol 20 (1) ◽  
pp. 39-45
Author(s):  
David Nhemaphuki ◽  
Kiran Thapa Chetri ◽  
Sanjeevan Shrestha
Keyword(s):  
Land Cover ◽  
Land Cover Classification ◽  
Radar Data ◽  
Optical Data ◽  
Land Cover Mapping ◽  
Learning Approach ◽  
Random Forest Algorithm ◽  
Machine Learning Approach ◽  
Radar Imagery ◽  
Optical Radar

This study evaluates the advantages of combining traditional space borne optical data with longer wavelengths of radar for land cover mapping. Land cover classification was carried out using Optical, radar data and combination of both for the Bardiya district using Random Forest algorithm. The fusion of optical and radar shows better land cover discrimination with 96.98% overall accuracy in compared to using radar data and optical data separately with overall accuracy of 69.2% and 95.89% respectively. Additionally, the qualitative result demonstrates that the combined utilization of optical and radar imagery yields useful land cover information over those obtained using either type of image on its own.

Sign in / Sign up

Export Citation Format

Share Document