Exploration of Convolutional Neural Network Architectures for Large Region Map Automation

TL;DR

This study evaluates 28 CNN architectures for automating large-scale land cover mapping using Landsat data, achieving over 92% accuracy with improved models and demonstrating the benefits of higher resolution satellite imagery.

Contribution

It introduces optimized CNN architectures for large region land cover mapping, surpassing previous accuracy benchmarks and analyzing the impact of satellite data resolution.

Findings

VGGNet with output stride 4 and modified U-Net performed best.

Achieved 92.4% accuracy for 13 LULC classes, a 15.8% improvement.

Higher radiometric resolution Landsat 8 data improved accuracy by 11.44%.

Abstract

Deep learning semantic segmentation algorithms have provided improved frameworks for the automated production of Land-Use and Land-Cover (LULC) maps, which significantly increases the frequency of map generation as well as consistency of production quality. In this research, a total of 28 different model variations were examined to improve the accuracy of LULC maps. The experiments were carried out using Landsat 5/7 or Landsat 8 satellite images with the North American Land Change Monitoring System labels. The performance of various CNNs and extension combinations were assessed, where VGGNet with an output stride of 4, and modified U-Net architecture provided the best results. Additional expanded analysis of the generated LULC maps was also provided. Using a deep neural network, this work achieved 92.4% accuracy for 13 LULC classes within southern Manitoba representing a 15.8% improvement over published results for the NALCMS. Based on the large regions of interest, higher radiometric resolution of Landsat 8 data resulted in better overall accuracies (88.04%) compare to Landsat 5/7 (80.66%) for 16 LULC classes. This represents an 11.44% and 4.06% increase in overall accuracy compared to previously published NALCMS results, including larger land area and higher number of LULC classes incorporated into the models compared to other published LULC map automation methods.