Exploring Transfer Learning for Anthropogenic Geomorphic Feature Extraction from Land Surface Parameters Using UNet

Semantic segmentation algorithms, such as UNet, that rely on convolutional neural network (CNN)-based architectures, due to their ability to capture local textures and spatial context, have shown promise for anthropogenic geomorphic feature extraction when using land surface parameters (LSPs) derive...

Full description

Saved in:
Bibliographic Details
Main Authors: Aaron E. Maxwell, Sarah Farhadpour, Muhammad Ali
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/24/4670
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846102890019553280
author Aaron E. Maxwell
Sarah Farhadpour
Muhammad Ali
author_facet Aaron E. Maxwell
Sarah Farhadpour
Muhammad Ali
author_sort Aaron E. Maxwell
collection DOAJ
description Semantic segmentation algorithms, such as UNet, that rely on convolutional neural network (CNN)-based architectures, due to their ability to capture local textures and spatial context, have shown promise for anthropogenic geomorphic feature extraction when using land surface parameters (LSPs) derived from digital terrain models (DTMs) as input predictor variables. However, the operationalization of these supervised classification methods is limited by a lack of large volumes of quality training data. This study explores the use of transfer learning, where information learned from another, and often much larger, dataset is used to potentially reduce the need for a large, problem-specific training dataset. Two anthropogenic geomorphic feature extraction problems are explored: the extraction of agricultural terraces and the mapping of surface coal mine reclamation-related valley fill faces. Light detection and ranging (LiDAR)-derived DTMs were used to generate LSPs. We developed custom transfer parameters by attempting to predict geomorphon-based landforms using a large dataset of digital terrain data provided by the United States Geological Survey’s 3D Elevation Program (3DEP). We also explored the use of pre-trained ImageNet parameters and initializing models using parameters learned from the other mapping task investigated. The geomorphon-based transfer learning resulted in the poorest performance while the ImageNet-based parameters generally improved performance in comparison to a random parameter initialization, even when the encoder was frozen or not trained. Transfer learning between the different geomorphic datasets offered minimal benefits. We suggest that pre-trained models developed using large, image-based datasets may be of value for anthropogenic geomorphic feature extraction from LSPs even given the data and task disparities. More specifically, ImageNet-based parameters should be considered as an initialization state for the encoder component of semantic segmentation architectures applied to anthropogenic geomorphic feature extraction even when using non-RGB image-based predictor variables, such as LSPs. The value of transfer learning between the different geomorphic mapping tasks may have been limited due to smaller sample sizes, which highlights the need for continued research in using unsupervised and semi-supervised learning methods, especially given the large volume of digital terrain data available, despite the lack of associated labels.
format Article
id doaj-art-d67d955e84964c28ace81dcccb7ac520
institution Kabale University
issn 2072-4292
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-d67d955e84964c28ace81dcccb7ac5202024-12-27T14:50:51ZengMDPI AGRemote Sensing2072-42922024-12-011624467010.3390/rs16244670Exploring Transfer Learning for Anthropogenic Geomorphic Feature Extraction from Land Surface Parameters Using UNetAaron E. Maxwell0Sarah Farhadpour1Muhammad Ali2Department of Geology and Geography, West Virginia University, 98 Beechurst Avenue Brooks Hall, Morgantown, WV 26506, USADepartment of Geology and Geography, West Virginia University, 98 Beechurst Avenue Brooks Hall, Morgantown, WV 26506, USADepartment of Geology and Geography, West Virginia University, 98 Beechurst Avenue Brooks Hall, Morgantown, WV 26506, USASemantic segmentation algorithms, such as UNet, that rely on convolutional neural network (CNN)-based architectures, due to their ability to capture local textures and spatial context, have shown promise for anthropogenic geomorphic feature extraction when using land surface parameters (LSPs) derived from digital terrain models (DTMs) as input predictor variables. However, the operationalization of these supervised classification methods is limited by a lack of large volumes of quality training data. This study explores the use of transfer learning, where information learned from another, and often much larger, dataset is used to potentially reduce the need for a large, problem-specific training dataset. Two anthropogenic geomorphic feature extraction problems are explored: the extraction of agricultural terraces and the mapping of surface coal mine reclamation-related valley fill faces. Light detection and ranging (LiDAR)-derived DTMs were used to generate LSPs. We developed custom transfer parameters by attempting to predict geomorphon-based landforms using a large dataset of digital terrain data provided by the United States Geological Survey’s 3D Elevation Program (3DEP). We also explored the use of pre-trained ImageNet parameters and initializing models using parameters learned from the other mapping task investigated. The geomorphon-based transfer learning resulted in the poorest performance while the ImageNet-based parameters generally improved performance in comparison to a random parameter initialization, even when the encoder was frozen or not trained. Transfer learning between the different geomorphic datasets offered minimal benefits. We suggest that pre-trained models developed using large, image-based datasets may be of value for anthropogenic geomorphic feature extraction from LSPs even given the data and task disparities. More specifically, ImageNet-based parameters should be considered as an initialization state for the encoder component of semantic segmentation architectures applied to anthropogenic geomorphic feature extraction even when using non-RGB image-based predictor variables, such as LSPs. The value of transfer learning between the different geomorphic mapping tasks may have been limited due to smaller sample sizes, which highlights the need for continued research in using unsupervised and semi-supervised learning methods, especially given the large volume of digital terrain data available, despite the lack of associated labels.https://www.mdpi.com/2072-4292/16/24/4670semantic segmentationUNetconvolutional neural networkanthropogenic geomorphic feature extractiontransfer learningland surface parameters
spellingShingle Aaron E. Maxwell
Sarah Farhadpour
Muhammad Ali
Exploring Transfer Learning for Anthropogenic Geomorphic Feature Extraction from Land Surface Parameters Using UNet
Remote Sensing
semantic segmentation
UNet
convolutional neural network
anthropogenic geomorphic feature extraction
transfer learning
land surface parameters
title Exploring Transfer Learning for Anthropogenic Geomorphic Feature Extraction from Land Surface Parameters Using UNet
title_full Exploring Transfer Learning for Anthropogenic Geomorphic Feature Extraction from Land Surface Parameters Using UNet
title_fullStr Exploring Transfer Learning for Anthropogenic Geomorphic Feature Extraction from Land Surface Parameters Using UNet
title_full_unstemmed Exploring Transfer Learning for Anthropogenic Geomorphic Feature Extraction from Land Surface Parameters Using UNet
title_short Exploring Transfer Learning for Anthropogenic Geomorphic Feature Extraction from Land Surface Parameters Using UNet
title_sort exploring transfer learning for anthropogenic geomorphic feature extraction from land surface parameters using unet
topic semantic segmentation
UNet
convolutional neural network
anthropogenic geomorphic feature extraction
transfer learning
land surface parameters
url https://www.mdpi.com/2072-4292/16/24/4670
work_keys_str_mv AT aaronemaxwell exploringtransferlearningforanthropogenicgeomorphicfeatureextractionfromlandsurfaceparametersusingunet
AT sarahfarhadpour exploringtransferlearningforanthropogenicgeomorphicfeatureextractionfromlandsurfaceparametersusingunet
AT muhammadali exploringtransferlearningforanthropogenicgeomorphicfeatureextractionfromlandsurfaceparametersusingunet