TESFAYE Regasa ADUGNA

Dr. TESFAYE Regasa ADUGNA

Yangtze Delta Region Institute (Huzhou), University of Electronic Science and Technology of China,, Huzhou, Zhejiang, China
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 January 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
TESFAYE Regasa ADUGNATESFAYE Regasa ADUGNA
TESFAYE Regasa ADUGNA
WXWenbo Xu
Wenbo Xu
JFJinlong Fan
Jinlong Fan
The type of algorithm employed to classify remote sensing imageries plays a great role in affecting the accuracy. In recent decades, machine learning (ML) has received great attention due to its robustness in remote sensing image classification. In this regard, random forest (RF) and support vector machine (SVM) are two of the most widely used ML algorithms to generate land cover (LC) maps from satellite imageries. Although several comparisons have been conducted between these two algorithms, the findings are contradicting. Moreover, the comparisons were made on local-scale LC map generation either from high or medium resolution images using various software, but not Python. In this paper, we compared the performance of these two algorithms for large area LC mapping of parts of Africa using coarse resolution imageries in the Python platform by the employing Scikit-Learn (sklearn) library. We employed a big dataset, 297 metrics, comprised of systematically selected 9-month composite FegnYun-3C (FY-3C) satellite images with 1 km resolution. Several experiments were performed using a range of values to determine the best values for the two most important parameters of each classifier, the number of trees and the number of variables, for RF, and penalty value and gamma for SVM, and to obtain the best model of each algorithm. Our results showed that RF outperformed SVM yielding 0.86 (OA) and 0.83 (k), which are 1–2% and 3% higher than the best SVM model, respectively. In addition, RF performed better in mixed class classification; however, it performed almost the same when classifying relatively pure classes with distinct spectral variation, i.e., consisting of less mixed pixels. Furthermore, RF is more efficient in handling large input datasets where the SVM fails. Hence, RF is a more robust ML algorithm especially for heterogeneous large area mapping using coarse resolution images. Finally, default parameter values in the sklearn library work well for satellite image classification with minor/or no adjustment for these algorithms.

6 November 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
TESFAYE Regasa ADUGNATESFAYE Regasa ADUGNA
TESFAYE Regasa ADUGNA
WXWenbo Xu
Wenbo Xu
JFJinlong Fan
Jinlong Fan
Regional or continental-scale land cover mapping requires various amounts of months of multi-temporal satellite data to pick phenological variation in vegetation, enhancing differentiability among surface cover types and improving accuracy. However, little has been addressed about the number of months/multi-temporal images needed to obtain the best result and the impact of using different amounts of these data on the accuracy of individual classes. This work aimed to analyze these effects by utilizing the various amounts of months of time series FengYun-3C (FY-3C) data within one year for land cover mapping of parts of Africa using a random forest classifier. The study area covers roughly one-third of Africa, including eastern, central, and northern parts of the continent. One-year FY-3C ten-day composite images consisting of eleven-band each with 1-km spatial resolution were divided into seven input datasets that comprise stacked images of 1-month, 3-month, 6-month, consecutive 9-month, 12-month, selected images from 12 months using band/feature importance, and selected 9-month. Comparisons of these datasets on independent test samples revealed that overall accuracy, kappa coefficient, and the accuracy of the individual classes generally increase significantly with increasing the number of data/months. However, the highest accuracy and kappa coefficient, 0.86 and 0.83, were obtained by processing selected 9-month imageries. The second maximum accuracy and kappa (0.85 and 0.82,) were found by manipulating 12-month scenes which are the same as the results obtained by applying feature reduction. Although 4% and 5% higher accuracy were achieved by manipulating 3-month and 6-month data relative to 1-month imageries, no variation of accuracy was observed between six- and nine-months of consecutive data, both yielding equal accuracy and kappa value (0.84 and 0.81) indicating redundancy of information. Overall, the high accuracy results show the feasibility of FY-3C data for land cover mapping of Africa.

1 October 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
TESFAYE Regasa ADUGNATESFAYE Regasa ADUGNA
TESFAYE Regasa ADUGNA
WXWenbo Xu
Wenbo Xu
JFJinlong Fan
Jinlong Fan
XLXin Luo
Xin Luo
HJHaitao Jia
Haitao Jia
Cloud is a serious problem that affects the quality of remote-sensing (RS) images. Existing cloud removal techniques suffer from notable limitations, such as being specific to certain data types, cloud conditions, and spatial extents, as well as requiring auxiliary data, which hampers their generalizability and flexibility. To address the issue, we propose a maximum-value compositing approach by generating cloud masks. We acquired 432 daily MOD09GA L2 MODIS imageries covering a vast region with persistent cloud cover and various climates and land-cover types. Labeled datasets for cloud, land, and no-data were collected from selected daily imageries. Subsequently, we trained and evaluated RF, SVM, and U-Net models to choose the best models. Accordingly, SVM and U-Net were chosen and employed to classify all the daily imageries. Then, the classified imageries were converted to two sets of mask layers to mask clouds and no-data pixels in the corresponding daily images by setting the masked pixels’ values to −0.999999. After masking, we employed the maximum-value technique to generate two sets of 16-day composite products, MaxComp-1 and MaxComp-2, corresponding to SVM and U-Net-derived cloud masks, respectively. Finally, we assessed the quality of our composite products by comparing them with the reference MOD13A1 16-day composite product. Based on the land-cover classification accuracy, our products yielded a significantly higher accuracy (5–28%) than the reference MODIS product across three classifiers (RF, SVM, and U-Net), indicating the quality of our products and the effectiveness of our techniques. In particular, MaxComp-1 yielded the best results, which further implies the superiority of SVM for cloud masking. In addition, our products appear to be more radiometrically and spectrally consistent and less noisy than MOD13A1, implying that our approach is more efficient in removing shadows and noises/artifacts. Our method yields high-quality products that are vital for investigating large regions with persistent clouds and studies requiring time-series data. Moreover, the proposed techniques can be adopted for higher-resolution RS imageries, regardless of the spatial extent, data volume, and type of clouds.

27 September 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
TESFAYE Regasa ADUGNATESFAYE Regasa ADUGNA
TESFAYE Regasa ADUGNA
WXWenbo Xu
Wenbo Xu
JFJinlong Fan
Jinlong Fan
HJHaitao Jia
Haitao Jia
XLXin Luo
Xin Luo
Based on studies using high-medium resolution images, convolutional neural networks (CNNs) and semantic segmentation have shown superiority over classical machine learning (ML), particularly in small-scale mapping. However, few/no studies have assessed the techniques on coarse resolution image classification for extensive area land cover mapping. In this study, we evaluated the performance and feasibility of three CNN models (1D CNN, 2D CNN, and 3D CNN), and U-net for coarse-resolution satellite image classification and compared them to a random forest (RF) classifier. We utilized time-series, coarse resolution (1 km) composite imageries acquired by FY-3C VIRR. Labeled datasets were collected as shapefiles and split into three independent datasets: training, validation, and test datasets, and preprocessed to meet each model's input format requirements. We conducted several experiments to optimize models and select the best models. Then, the best models were evaluated on an unseen dataset. Among the DL models, 1D CNN achieved the highest overall accuracy (OA) 0. 87 and kappa (k) 0.84, 2% higher than the best results attained by 2D CNN, 3D CNN, and U-net models. However, 1D CNN is outperformed by RF which achieved 0.89 (OA) and 0.87 (k). Achieving the best and the second-best results using RF and 1D CNN models, respectively, indicates the superiority of the pixel-based method and the insignificance of spatial information in coarse-resolution image classification. Furthermore, although the DL models can yield high accuracy, especially 1D CNN, they are less feasible than RF classifiers for coarse-resolution satellite image classification in extensive area land cover mapping.

17 July 2022
Verified
Conference Paper
Closed access
TESFAYE Regasa ADUGNATESFAYE Regasa ADUGNA
TESFAYE Regasa ADUGNA
WXWenbo Xu
Wenbo Xu
JHJia Haitao
Jia Haitao
JFJinlong Fan
Jinlong Fan
This paper compared multi-temporal composite products of FY-3C VIRR and MODIS for regional land cover (LC) mapping of a part of Africa. LC classification was conducted using a random forest algorithm in the Scikit-Learn library of Python after the model was trained using reference data that were collected by combining three techniques and employed simultaneously i.e. Landsat 8 image interpretation, referring exiting maps, and crosschecking on Google Earth pro/ maps. Based on the overall accuracy (OA) and kappa value (k) the two instruments showed insignificant performance variation although FY-3C VIRR achieved slightly higher OA (.82) and k (.79) which are 1 % higher than MODIS. However, the two instruments exhibited notable performance differences in discerning individual classes. The FY-3C data are generally better for vegetation classification; MODIS, whereas, classified built-up, bare/sparse-vegetation, and water bodies with better accuracy. Moreover, the incorporation of FY-3C thermal bands improved its accuracy significantly, by 3%.

7 July 2024
Verified
Conference Paper
Closed access
TESFAYE Regasa ADUGNATESFAYE Regasa ADUGNA
TESFAYE Regasa ADUGNA
WXWenbo Xu
Wenbo Xu
JFJinlong Fan
Jinlong Fan
Convolutional Neural Networks (CNNs) have been applied effectively to classify high to medium-resolution imageries, especially for local scale land cover mapping, and attained high accuracy by outperforming the conventional machine learning techniques as the models incorporate spatial information as well as spectral reflectance values to differentiate objects.However, few studies have explored the effectiveness of CNN models for coarse-resolution satellite image classification. In this work, therefore, we applied 1D CNN and 3D CNN for time-series, coarse resolution (1km) FY-3C image classification in extensive area land cover mapping of a part of Eastern and North-East Africa.The result indicates both 1D CNN and 3D CNN models achieved high overall accuracy (OA >=85), although the former outperformed the latter significantly by 2-4%, indicating the superiority of pixel-based classification in time-series coarse resolution image classification.