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

Journal of Imaging

Ronald Daanen¹  HowardE. Epstein²  Kelcy Kent²  ClaireG. Griffin²  MdAbul Ehsan Bhuiyan³  Chandi Witharana³  Amber Agnew³  BenjaminM. Jones⁴  AnnaK. Liljedahl⁵ 

[1] Alaska Department of Natural Resources, Division of Geological & Geophysical Surveys, Fairbanks, AK 99775, USA;Department of Environmental Sciences, University of Virginia, Charlottesville, VA 22904, USA;Department of Natural Resources and the Environment, University of Connecticut, Storrs, CT 06269, USA;Institute of Northern Engineering, University of Alaska Fairbanks, Fairbanks, AK 99775, USA;Woodwell Climate Research Center, Falmouth, MA 02540, USA;

关键词: deep learning;    tundra;    ice-wedge polygons;    Mask R-CNN;    satellite imagery;    permafrost;   

DOI  :  10.3390/jimaging6090097

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown