4.7 Article

Using high-resolution imagery and deep learning to classify land-use following deforestation: a case study in Ethiopia

Journal

GISCIENCE & REMOTE SENSING
Volume 59, Issue 1, Pages 1446-1472

Publisher

TAYLOR & FRANCIS LTD
DOI: 10.1080/15481603.2022.2115619

Keywords

Attention U-Net; deep learning; Planet-NICFI; Land-use following deforestation; deforestation drivers; remote sensing

Funding

  1. International Climate Initiative (IKI) of the German Federal Ministry for the Environment, Nature Conservation, Building, and Nuclear Safety (BMUB) [20_III_108]
  2. Norwegian Agency for Development Cooperation (Norad) [1500551]
  3. CGIAR Research Program on Forests, Trees, and Agroforestry (CRPFTA)
  4. CGIAR
  5. European Commission Horizon Europe project Open-Earth-Monitor [101059548]
  6. CGIAR initiative MITIGATE+

Ask authors/readers for more resources

This research assesses the potential of different satellite data modalities for classifying post-deforestation land-use in Ethiopia. The study finds that choosing the right satellite imagery type is crucial and that detailed spatial or temporal patterns are necessary for achieving high classification accuracy.
National-scale assessments of post-deforestation land-use are crucial for decreasing deforestation and forest degradation-related emissions. In this research, we assess the potential of different satellite data modalities (single-date, multi-date, multi-resolution, and an ensemble of multi-sensor images) for classifying land-use following deforestation in Ethiopia using the U-Net deep neural network architecture enhanced with attention. We performed the analysis on satellite image data retrieved across Ethiopia from freely available Landsat-8, Sentinel-2 and Planet-NICFI satellite data. The experiments aimed at an analysis of (a) single-date images from individual sensors to account for the differences in spatial resolution between image sensors in detecting land-uses, (b) ensembles of multiple images from different sensors (Planet-NICFI/Sentinel-2/Landsat-8) with different spatial resolutions, (c) the use of multi-date data to account for the contribution of temporal information in detecting land-uses, and, finally, (d) the identification of regional differences in terms of land-use following deforestation in Ethiopia. We hypothesize that choosing the right satellite imagery (sensor) type is crucial for the task. Based on a comprehensive visually interpreted reference dataset of 11 types of post-deforestation land-uses, we find that either detailed spatial patterns (single-date Planet-NICFI) or detailed temporal patterns (multi-date Sentinel-2, Landsat-8) are required for identifying land-use following deforestation, while medium-resolution single-date imagery is not sufficient to achieve high classification accuracy. We also find that adding soft-attention to the standard U-Net improved the classification accuracy, especially for small-scale land-uses. The models and products presented in this work can be used as a powerful data resource for governmental and forest monitoring agencies to design and monitor deforestation mitigation measures and data-driven land-use policy.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available