Understanding the Effects of Optimal Combination of Spectral Bands on Deep Learning Model Predictions: A Case Study Based on Permafrost Tundra Landform Mapping Using High Resolution Multispectral Satellite Imagery
Deep learning (DL) convolutional neural networks (CNNs) have been rapidly adapted in very high spatial resolution (VHSR) satellite image analysis. DLCNN-based computer visions (CV) applications primarily aim for everyday object detection from standard red, green, blue (RGB) imagery, while earth scie...
Published in: | Journal of Imaging |
---|---|
Main Authors: | , , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2020
|
Subjects: | |
Online Access: | https://doi.org/10.3390/jimaging6090097 https://doaj.org/article/b3ce386536544247943fc405954a03ba |
id |
ftdoajarticles:oai:doaj.org/article:b3ce386536544247943fc405954a03ba |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:b3ce386536544247943fc405954a03ba 2023-05-15T15:18:39+02:00 Understanding the Effects of Optimal Combination of Spectral Bands on Deep Learning Model Predictions: A Case Study Based on Permafrost Tundra Landform Mapping Using High Resolution Multispectral Satellite Imagery Md Abul Ehsan Bhuiyan Chandi Witharana Anna K. Liljedahl Benjamin M. Jones Ronald Daanen Howard E. Epstein Kelcy Kent Claire G. Griffin Amber Agnew 2020-09-01T00:00:00Z https://doi.org/10.3390/jimaging6090097 https://doaj.org/article/b3ce386536544247943fc405954a03ba EN eng MDPI AG https://www.mdpi.com/2313-433X/6/9/97 https://doaj.org/toc/2313-433X doi:10.3390/jimaging6090097 2313-433X https://doaj.org/article/b3ce386536544247943fc405954a03ba Journal of Imaging, Vol 6, Iss 97, p 97 (2020) deep learning tundra ice-wedge polygons Mask R-CNN satellite imagery permafrost Photography TR1-1050 Computer applications to medicine. Medical informatics R858-859.7 Electronic computers. Computer science QA75.5-76.95 article 2020 ftdoajarticles https://doi.org/10.3390/jimaging6090097 2023-01-08T01:39:41Z Deep learning (DL) convolutional neural networks (CNNs) have been rapidly adapted in very high spatial resolution (VHSR) satellite image analysis. DLCNN-based computer visions (CV) applications primarily aim for everyday object detection from standard red, green, blue (RGB) imagery, while earth science remote sensing applications focus on geo object detection and classification from multispectral (MS) imagery. MS imagery includes RGB and narrow spectral channels from near- and/or middle-infrared regions of reflectance spectra. The central objective of this exploratory study is to understand to what degree MS band statistics govern DLCNN model predictions. We scaffold our analysis on a case study that uses Arctic tundra permafrost landform features called ice-wedge polygons (IWPs) as candidate geo objects. We choose Mask RCNN as the DLCNN architecture to detect IWPs from eight-band Worldview-02 VHSR satellite imagery. A systematic experiment was designed to understand the impact on choosing the optimal three-band combination in model prediction. We tasked five cohorts of three-band combinations coupled with statistical measures to gauge the spectral variability of input MS bands. The candidate scenes produced high model detection accuracies for the F1 score, ranging between 0.89 to 0.95, for two different band combinations (coastal blue, blue, green (1,2,3) and green, yellow, red (3,4,5)). The mapping workflow discerned the IWPs by exhibiting low random and systematic error in the order of 0.17–0.19 and 0.20–0.21, respectively, for band combinations (1,2,3). Results suggest that the prediction accuracy of the Mask-RCNN model is significantly influenced by the input MS bands. Overall, our findings accentuate the importance of considering the image statistics of input MS bands and careful selection of optimal bands for DLCNN predictions when DLCNN architectures are restricted to three spectral channels. Article in Journal/Newspaper Arctic Ice permafrost Tundra wedge* Directory of Open Access Journals: DOAJ Articles Arctic Journal of Imaging 6 9 97 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
deep learning tundra ice-wedge polygons Mask R-CNN satellite imagery permafrost Photography TR1-1050 Computer applications to medicine. Medical informatics R858-859.7 Electronic computers. Computer science QA75.5-76.95 |
spellingShingle |
deep learning tundra ice-wedge polygons Mask R-CNN satellite imagery permafrost Photography TR1-1050 Computer applications to medicine. Medical informatics R858-859.7 Electronic computers. Computer science QA75.5-76.95 Md Abul Ehsan Bhuiyan Chandi Witharana Anna K. Liljedahl Benjamin M. Jones Ronald Daanen Howard E. Epstein Kelcy Kent Claire G. Griffin Amber Agnew Understanding the Effects of Optimal Combination of Spectral Bands on Deep Learning Model Predictions: A Case Study Based on Permafrost Tundra Landform Mapping Using High Resolution Multispectral Satellite Imagery |
topic_facet |
deep learning tundra ice-wedge polygons Mask R-CNN satellite imagery permafrost Photography TR1-1050 Computer applications to medicine. Medical informatics R858-859.7 Electronic computers. Computer science QA75.5-76.95 |
description |
Deep learning (DL) convolutional neural networks (CNNs) have been rapidly adapted in very high spatial resolution (VHSR) satellite image analysis. DLCNN-based computer visions (CV) applications primarily aim for everyday object detection from standard red, green, blue (RGB) imagery, while earth science remote sensing applications focus on geo object detection and classification from multispectral (MS) imagery. MS imagery includes RGB and narrow spectral channels from near- and/or middle-infrared regions of reflectance spectra. The central objective of this exploratory study is to understand to what degree MS band statistics govern DLCNN model predictions. We scaffold our analysis on a case study that uses Arctic tundra permafrost landform features called ice-wedge polygons (IWPs) as candidate geo objects. We choose Mask RCNN as the DLCNN architecture to detect IWPs from eight-band Worldview-02 VHSR satellite imagery. A systematic experiment was designed to understand the impact on choosing the optimal three-band combination in model prediction. We tasked five cohorts of three-band combinations coupled with statistical measures to gauge the spectral variability of input MS bands. The candidate scenes produced high model detection accuracies for the F1 score, ranging between 0.89 to 0.95, for two different band combinations (coastal blue, blue, green (1,2,3) and green, yellow, red (3,4,5)). The mapping workflow discerned the IWPs by exhibiting low random and systematic error in the order of 0.17–0.19 and 0.20–0.21, respectively, for band combinations (1,2,3). Results suggest that the prediction accuracy of the Mask-RCNN model is significantly influenced by the input MS bands. Overall, our findings accentuate the importance of considering the image statistics of input MS bands and careful selection of optimal bands for DLCNN predictions when DLCNN architectures are restricted to three spectral channels. |
format |
Article in Journal/Newspaper |
author |
Md Abul Ehsan Bhuiyan Chandi Witharana Anna K. Liljedahl Benjamin M. Jones Ronald Daanen Howard E. Epstein Kelcy Kent Claire G. Griffin Amber Agnew |
author_facet |
Md Abul Ehsan Bhuiyan Chandi Witharana Anna K. Liljedahl Benjamin M. Jones Ronald Daanen Howard E. Epstein Kelcy Kent Claire G. Griffin Amber Agnew |
author_sort |
Md Abul Ehsan Bhuiyan |
title |
Understanding the Effects of Optimal Combination of Spectral Bands on Deep Learning Model Predictions: A Case Study Based on Permafrost Tundra Landform Mapping Using High Resolution Multispectral Satellite Imagery |
title_short |
Understanding the Effects of Optimal Combination of Spectral Bands on Deep Learning Model Predictions: A Case Study Based on Permafrost Tundra Landform Mapping Using High Resolution Multispectral Satellite Imagery |
title_full |
Understanding the Effects of Optimal Combination of Spectral Bands on Deep Learning Model Predictions: A Case Study Based on Permafrost Tundra Landform Mapping Using High Resolution Multispectral Satellite Imagery |
title_fullStr |
Understanding the Effects of Optimal Combination of Spectral Bands on Deep Learning Model Predictions: A Case Study Based on Permafrost Tundra Landform Mapping Using High Resolution Multispectral Satellite Imagery |
title_full_unstemmed |
Understanding the Effects of Optimal Combination of Spectral Bands on Deep Learning Model Predictions: A Case Study Based on Permafrost Tundra Landform Mapping Using High Resolution Multispectral Satellite Imagery |
title_sort |
understanding the effects of optimal combination of spectral bands on deep learning model predictions: a case study based on permafrost tundra landform mapping using high resolution multispectral satellite imagery |
publisher |
MDPI AG |
publishDate |
2020 |
url |
https://doi.org/10.3390/jimaging6090097 https://doaj.org/article/b3ce386536544247943fc405954a03ba |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Ice permafrost Tundra wedge* |
genre_facet |
Arctic Ice permafrost Tundra wedge* |
op_source |
Journal of Imaging, Vol 6, Iss 97, p 97 (2020) |
op_relation |
https://www.mdpi.com/2313-433X/6/9/97 https://doaj.org/toc/2313-433X doi:10.3390/jimaging6090097 2313-433X https://doaj.org/article/b3ce386536544247943fc405954a03ba |
op_doi |
https://doi.org/10.3390/jimaging6090097 |
container_title |
Journal of Imaging |
container_volume |
6 |
container_issue |
9 |
container_start_page |
97 |
_version_ |
1766348838281412608 |