Using high-resolution imagery and deep learning to classify land-use following deforestation: a case study in Ethiopia
CGSpace
View Archive InfoField | Value | |
Title |
Using high-resolution imagery and deep learning to classify land-use following deforestation: a case study in Ethiopia
|
|
Creator |
Masolele, R.N.
De Sy, V. Marcos, D. Verbesselt, J. Gieseke, F. Mulatu, K.A. Moges, Y. Sebrala, H. Martius, C. Herold, M. |
|
Subject |
remote sensing
deforestation climate change satellite imagery |
|
Description |
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.
|
|
Date |
2022-12-31
2023-01-25T04:47:08Z 2023-01-25T04:47:08Z |
|
Type |
Journal Article
|
|
Identifier |
Masolele, Robert N.; De Sy, Veronique; Marcos, Diego; Verbesselt, Jan; Gieseke, Fabian; Mulatu, Kalkidan Ayele; Moges, Yitebitu; Sebrala, Heiru; Martius, Christopher; Herold, Martin. 2022. Using high-resolution imagery and deep learning to classify land-use following deforestation: a case study in Ethiopia. GIScience & Remote Sensing. 58(1): 1446-1472. https://doi.org/10.1080/15481603.2022.2115619
1548-1603 https://hdl.handle.net/10568/128140 https://doi.org/10.1080/15481603.2022.2115619 |
|
Language |
en
|
|
Rights |
CC-BY-4.0
Open Access |
|
Format |
1446-1472
|
|
Publisher |
Informa UK Limited
|
|
Source |
GIScience & Remote Sensing
|
|