DATA-DRIVEN ANALYSIS AND MAPPING OF THE POTENTIAL DISTRIBUTION OF MOUNTAIN PERMAFROST
In alpine environments, mountain permafrost is defined as a thermal state of the ground and it corresponds to any lithosphere material that is at or below 0°C for at least two years. Its degradation is potentially leading to an increasing rock fall activity and sediment transfer rates. During the la...
Main Author: | |
---|---|
Format: | Doctoral or Postdoctoral Thesis |
Language: | English |
Published: |
Université de Lausanne, Faculté des géosciences et de l'environnement
2018
|
Subjects: | |
Online Access: | https://serval.unil.ch/notice/serval:BIB_F417FD0D4407 https://serval.unil.ch/resource/serval:BIB_F417FD0D4407.P001/REF.pdf http://nbn-resolving.org/urn/resolver.pl?urn=urn:nbn:ch:serval-BIB_F417FD0D44072 |
id |
ftunivlausanne:oai:serval.unil.ch:BIB_F417FD0D4407 |
---|---|
record_format |
openpolar |
spelling |
ftunivlausanne:oai:serval.unil.ch:BIB_F417FD0D4407 2024-02-11T10:07:47+01:00 DATA-DRIVEN ANALYSIS AND MAPPING OF THE POTENTIAL DISTRIBUTION OF MOUNTAIN PERMAFROST Deluigi, Nicola 2018 application/pdf https://serval.unil.ch/notice/serval:BIB_F417FD0D4407 https://serval.unil.ch/resource/serval:BIB_F417FD0D4407.P001/REF.pdf http://nbn-resolving.org/urn/resolver.pl?urn=urn:nbn:ch:serval-BIB_F417FD0D44072 eng eng Université de Lausanne, Faculté des géosciences et de l'environnement info:eu-repo/semantics/altIdentifier/urn/urn:nbn:ch:serval-BIB_F417FD0D44072 https://serval.unil.ch/notice/serval:BIB_F417FD0D4407 https://serval.unil.ch/resource/serval:BIB_F417FD0D4407.P001/REF.pdf http://nbn-resolving.org/urn/resolver.pl?urn=urn:nbn:ch:serval-BIB_F417FD0D44072 info:eu-repo/semantics/openAccess Copying allowed only for non-profit organizations https://serval.unil.ch/disclaimer mountain permafrost mapping environmental modelling machine learning spatial data mining cartographie du permafrost de montagne modélisation environnemen- tale apprentissage automatique exploration de données spatiales cartografia del permafrost di montagna modellizzazione ambientale apprendimento automatico estrazione di dati spaziali info:eu-repo/semantics/doctoralThesis phdthesis 2018 ftunivlausanne 2024-01-22T00:54:55Z In alpine environments, mountain permafrost is defined as a thermal state of the ground and it corresponds to any lithosphere material that is at or below 0°C for at least two years. Its degradation is potentially leading to an increasing rock fall activity and sediment transfer rates. During the last 20 years, knowledge on this phenomenon has significantly improved thanks to many studies and monitoring projects, revealing an extremely discontinuous and complex spatial distribution, especially at the micro scale (scale of a specific landform; tens to several hundreds of metres). The objective of this thesis was the systematic and detailed investigation of the potential of data-driven techniques for mountain permafrost distribution modelling. Machine learning (ML) algorithms are able to consider a greater number of pa- rameters compared to classic approaches. Not only can permafrost distribution be modelled by using topo-climatic parameters as a proxy, but also by taking into ac- count known field permafrost evidences. These latter were collected in a sector of the Western Swiss Alps and they were mapped from field data (thermal and geoelectrical data) and ortho-image interpretations (rock glacier inventorying). A permafrost dataset was built from these evidences and completed with environmental and mor- phological predictors. Data were firstly analysed with feature relevance techniques in order to identify the statistical contribution of each controlling factor and to exclude non-relevant or redundant predictors. Five classification algorithms, belonging to statistics and machine learning, were then applied to the dataset and tested: Logistic regression (LR), linear and non-linear Support Vector Machines (SVM), Multilayer perceptrons (MLP) and Random forests (RF). These techniques inferred a classifica- tion function from labelled training data (pixels of permafrost absence and presence) to predict the permafrost occurrence where this was unknown. Classification performances, assessed with AUROC curves, ranged ... Doctoral or Postdoctoral Thesis permafrost Université de Lausanne (UNIL): Serval - Serveur académique lausannois |
institution |
Open Polar |
collection |
Université de Lausanne (UNIL): Serval - Serveur académique lausannois |
op_collection_id |
ftunivlausanne |
language |
English |
topic |
mountain permafrost mapping environmental modelling machine learning spatial data mining cartographie du permafrost de montagne modélisation environnemen- tale apprentissage automatique exploration de données spatiales cartografia del permafrost di montagna modellizzazione ambientale apprendimento automatico estrazione di dati spaziali |
spellingShingle |
mountain permafrost mapping environmental modelling machine learning spatial data mining cartographie du permafrost de montagne modélisation environnemen- tale apprentissage automatique exploration de données spatiales cartografia del permafrost di montagna modellizzazione ambientale apprendimento automatico estrazione di dati spaziali Deluigi, Nicola DATA-DRIVEN ANALYSIS AND MAPPING OF THE POTENTIAL DISTRIBUTION OF MOUNTAIN PERMAFROST |
topic_facet |
mountain permafrost mapping environmental modelling machine learning spatial data mining cartographie du permafrost de montagne modélisation environnemen- tale apprentissage automatique exploration de données spatiales cartografia del permafrost di montagna modellizzazione ambientale apprendimento automatico estrazione di dati spaziali |
description |
In alpine environments, mountain permafrost is defined as a thermal state of the ground and it corresponds to any lithosphere material that is at or below 0°C for at least two years. Its degradation is potentially leading to an increasing rock fall activity and sediment transfer rates. During the last 20 years, knowledge on this phenomenon has significantly improved thanks to many studies and monitoring projects, revealing an extremely discontinuous and complex spatial distribution, especially at the micro scale (scale of a specific landform; tens to several hundreds of metres). The objective of this thesis was the systematic and detailed investigation of the potential of data-driven techniques for mountain permafrost distribution modelling. Machine learning (ML) algorithms are able to consider a greater number of pa- rameters compared to classic approaches. Not only can permafrost distribution be modelled by using topo-climatic parameters as a proxy, but also by taking into ac- count known field permafrost evidences. These latter were collected in a sector of the Western Swiss Alps and they were mapped from field data (thermal and geoelectrical data) and ortho-image interpretations (rock glacier inventorying). A permafrost dataset was built from these evidences and completed with environmental and mor- phological predictors. Data were firstly analysed with feature relevance techniques in order to identify the statistical contribution of each controlling factor and to exclude non-relevant or redundant predictors. Five classification algorithms, belonging to statistics and machine learning, were then applied to the dataset and tested: Logistic regression (LR), linear and non-linear Support Vector Machines (SVM), Multilayer perceptrons (MLP) and Random forests (RF). These techniques inferred a classifica- tion function from labelled training data (pixels of permafrost absence and presence) to predict the permafrost occurrence where this was unknown. Classification performances, assessed with AUROC curves, ranged ... |
format |
Doctoral or Postdoctoral Thesis |
author |
Deluigi, Nicola |
author_facet |
Deluigi, Nicola |
author_sort |
Deluigi, Nicola |
title |
DATA-DRIVEN ANALYSIS AND MAPPING OF THE POTENTIAL DISTRIBUTION OF MOUNTAIN PERMAFROST |
title_short |
DATA-DRIVEN ANALYSIS AND MAPPING OF THE POTENTIAL DISTRIBUTION OF MOUNTAIN PERMAFROST |
title_full |
DATA-DRIVEN ANALYSIS AND MAPPING OF THE POTENTIAL DISTRIBUTION OF MOUNTAIN PERMAFROST |
title_fullStr |
DATA-DRIVEN ANALYSIS AND MAPPING OF THE POTENTIAL DISTRIBUTION OF MOUNTAIN PERMAFROST |
title_full_unstemmed |
DATA-DRIVEN ANALYSIS AND MAPPING OF THE POTENTIAL DISTRIBUTION OF MOUNTAIN PERMAFROST |
title_sort |
data-driven analysis and mapping of the potential distribution of mountain permafrost |
publisher |
Université de Lausanne, Faculté des géosciences et de l'environnement |
publishDate |
2018 |
url |
https://serval.unil.ch/notice/serval:BIB_F417FD0D4407 https://serval.unil.ch/resource/serval:BIB_F417FD0D4407.P001/REF.pdf http://nbn-resolving.org/urn/resolver.pl?urn=urn:nbn:ch:serval-BIB_F417FD0D44072 |
genre |
permafrost |
genre_facet |
permafrost |
op_relation |
info:eu-repo/semantics/altIdentifier/urn/urn:nbn:ch:serval-BIB_F417FD0D44072 https://serval.unil.ch/notice/serval:BIB_F417FD0D4407 https://serval.unil.ch/resource/serval:BIB_F417FD0D4407.P001/REF.pdf http://nbn-resolving.org/urn/resolver.pl?urn=urn:nbn:ch:serval-BIB_F417FD0D44072 |
op_rights |
info:eu-repo/semantics/openAccess Copying allowed only for non-profit organizations https://serval.unil.ch/disclaimer |
_version_ |
1790606499179921408 |