Találati lista | Tudóstér

001-es BibID:	BIBFORM095974
035-os BibID:	(cikkazonosító)2980 (WOS)000682299100001 (Scopus)85112129721
Első szerző:	Phinzi, Kwanele
Cím:	Classification Efficacy Using K-Fold Cross-Validation and Bootstrapping Resampling Techniques on the Example of Mapping Complex Gully Systems / Kwanele Phinzi, Dávid Abriha, Szilárd Szabó
Dátum:	2021
ISSN:	2072-4292
Megjegyzések:	The availability of aerial and satellite imageries has greatly reduced the costs and time associated with gully mapping, especially in remote locations. Regardless, accurate identification of gullies from satellite images remains an open issue despite the amount of literature addressing this problem. The main objective of this work was to investigate the performance of support vector machines (SVM) and random forest (RF) algorithms in extracting gullies based on two resampling methods: bootstrapping and k-fold cross-validation (CV). In order to achieve this objective, we used PlanetScope data, acquired during the wet and dry seasons. Using the Normalized Difference Vegetation Index (NDVI) and multispectral bands, we also explored the potential of the PlanetScope image in discriminating gullies from the surrounding land cover. Results revealed that gullies had significantly different (p < 0.001) spectral profiles from any other land cover class regarding all bands of the PlanetScope image, both in the wet and dry seasons. However, NDVI was not efficient in gully discrimination. Based on the overall accuracies, RF's performance was better with CV, particularly in the dry season, where its performance was up to 4% better than the SVM's. Nevertheless, class level metrics (omission error: 11.8%; commission error: 19%) showed that SVM combined with CV was more successful in gully extraction in the wet season. On the contrary, RF combined with bootstrapping had relatively low omission (16.4%) and commission errors (10.4%), making it the most efficient algorithm in the dry season. The estimated gully area was 88 ? 14.4 ha in the dry season and 57.2 - 18.8 ha in the wet season. Based on the standard error (8.2 ha), the wet season was more appropriate in gully identification than the dry season, which had a slightly higher standard error (8.6 ha). For the first time, this study sheds light on the influence of these resampling techniques on the accuracy of satellite-based gully mapping. More importantly, this study provides the basis for further investigations into the accuracy of such resampling techniques, especially when using different satellite images other than the PlanetScope data.
Tárgyszavak:	Természettudományok Földtudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk satellite imagery gully mapping machine learning random forest support vector machine south africa semi-arid environment
Megjelenés:	Remote Sensing. - 13 : 15 (2021), p. 1-18. -
További szerzők:	Abriha Dávid (1995-) (geográfus) Szabó Szilárd (1974-) (geográfus)
Pályázati támogatás:	TKP2020-NKA-04 Egyéb Department of Higher Education and Training (DHET) of South Africa Egyéb
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:

001-es BibID:	BIBFORM122872
Első szerző:	Shebl, Ali (geológus)
Cím:	PRISMA vs. Landsat 9 in lithological mapping ? a K-fold Cross-Validation implementation with Random Forest / Ali Shebl, Dávid Abriha, Maher Dawoud, Mosaad Ali Hussein Ali, Arpád Csámer
Dátum:	2024
ISSN:	1110-9823 2090-2476
Megjegyzések:	The selection of an optimal dataset is crucial for successful remote sensing analysis. The PRISMA hyperspectral sensor (with 240 spectral bands) and Landsat OLI-2 (boasting high dynamic resolution) offer robust data for various remote sensing applications, anticipating their increased demand in the coming years. However, despite their potential, we have not identified a rigorous evaluation of both datasets in geological applications utilizing Machine Learning Algorithms. Consequently, we conduct a comprehensive analysis using Random Forest, a widely-recommended machine learning algorithm, and employ K-fold cross-validation (with K = 2, 5, 10) with grid-search hyperparameter tuning for enhanced performance. Toward this aim, diverse image-processing ap- proaches, including Principal Component Analysis (PCA), Minimum Noise Fraction (MNF), and Independent Component Analysis (ICA), were applied to enhance feature selection and extraction. Subsequently, to ensure better performance of the RF algorithm, this study utilized well-distributed points instead of polygons to represent each target, thereby mitigating the effects of spatial autocorrelation. Our results reveal dataset- hyperparameter dependencies, with PRISMA mainly influenced by max_depth and Landsat 9 by max_features. Employing grid-search optimally balances dataset characteristics and data splitting (folds), generating accurate lithological maps across all K values. Notably, a significant hyperparameter shift at K = 10 produces the best lithological maps. Fieldwork and petrographic investigations validate the lithological maps, indicating PRISMA's slight superiority over Landsat OLI-2. Despite this, given the dataset nature and band count difference, we still advocate Landsat 9 as a potent multispectral input for future applications due to its superior radiometric resolution.
Tárgyszavak:	Természettudományok Földtudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk PRISMA Landsat 9 Random forest Geological mapping
Megjelenés:	Egyptian Journal of Remote Sensing and Space Science. - 27 : 3 (2024), p. 577-596. -
További szerzők:	Abriha Dávid (1995-) (geográfus) Dawoud, Maher Ali Hussein Ali, Mosaad Csámer Árpád (1976-) (geológus)
Pályázati támogatás:	K138079 NKFIH
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon: