Találati lista | Tudóstér

001-es BibID:	BIBFORM116157
035-os BibID:	(WoS)001078595200001 (Scopus)85171617945
Első szerző:	Shebl, Ali (geológus)
Cím:	PRISMA hyperspectral data for lithological mapping in the Egyptian Eastern Desert : Evaluating the support vector machine, random forest, and XG boost machine learning algorithms / Ali Shebl, David Abriha, Amr S. Fahil, Hanna A. El-Dokouny, Abdelmajeed A. Elrasheed, Arpád Csámer
Dátum:	2023
ISSN:	0169-1368
Megjegyzések:	In essence, targeting mineralization necessitates exact structural delineation and thorough lithological mapping. The latter is still a challenge for geologists and its lack hinders meticulous exploration for various mineralizations. Here we show for the first time over a case study from Arabian Nubian Shield (ANS), the application of hyperspectral PRISMA (PRecursore IperSpettrale della Missione Applicativa) data for objective lithological mapping using the well-known Random Forest (RF), XGboost (XGB), and Support Vector Machine (SVM) algorithms. Our results manifested the worthiness of PRISMA data in further lithological mapping, especially with SVM with a resultant accuracy depending mainly on the input data combination. Upon field verification, the current research reveals the usefulness of PRISMA and its preceding four principal components in delivering a detailed lithological map for the study area. Additionally, the eligibility of RF, XGB, and SVM was confirmed in delivering acceptable results. SVM exceeds XGB and RF in their overall accuracy (95 %, 92 %, and 90 % for SVM, XGB, and RF respectively). Our research strongly recommends blending the vantages of Machine Learning Algorithms' (MLAs) objectivity and the wealth of PRISMA spectral coverage for further precise lithological mapping before applicable mineral exploration programs in similar terrains.
Tárgyszavak:	Természettudományok Földtudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk PRISMA Lithological mapping Arabian Nubian Shield RF XGB SVM
Megjelenés:	Ore Geology Reviews. - 161 (2023), p. 1-16. -
További szerzők:	Abriha Dávid (1995-) (geográfus) Fahil, Amr S. El-Dokouny, Hanna A. Abdelmajeed, Adam Elrasheed Ali (1988-) (Geologist) Csámer Árpád (1976-) (geológus)
Pályázati támogatás:	Stipendium Hungaricum scholarship Egyéb
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:

001-es BibID:	BIBFORM132954
Első szerző:	Szabó Szilárd (geográfus)
Cím:	Lithological mapping with pseudo-labeling: promise or overestimation in data-scarce settings? / Szilárd Szabó, Abdelmajeed A. Elrasheed, Lilla Kovács, Imre J. Holb, Szilárd Likó, Dávid Abriha
Dátum:	2025
ISSN:	2064-5031 2064-5147
Megjegyzések:	Reference data are the most crucial points in model building. In geoscience, a scarcity of sufficient reference data is common. Pseudo-labelling (PL), i.e., incorporating high-probability data in the model building process, offers a potential solution. We aimed to reveal the efficiency of PL in lithological mapping in a vegetation-free arid region of Sudan. Random Forest (RF) and Multiple Adaptive Regression Splines (MARS) were used to classify a Landsat 9 image. Reference data were collected during field work and visual interpretation. Image processing yielded classified maps with associated probability layers, from which 1000 additional traditional samples (PL data) were extracted at a 95% probability. A detailed accuracy assessment was conducted, and accuracy measures were evaluated using statistical analysis and visual inspection. MARS was found to be an ambiguous classifier because the probability was too optimistic related to the overall accuracy (OA) (81% of samples had above 99% probability, OA=98.2%) compared to RF (21% above 99%, OA=98.1%); that is, despite the high probability, the accuracy improvement was only 0.1%. At the class level, the correlation between probability and the F1-score was low (0.21%). The original and PL-based models resulted in different maps with improved accuracy, although the new model version showed lower probability values for both the classifiers. Visual inspection proved essential for better insights into the spatial patterns: expert knowledge is crucial for controlling the occurrence of rock types and identifying false classifications. The main finding is that probability should be handled carefully, as it does not guarantee high model performance in classification, although the PL approach can lead to more reliable maps
Tárgyszavak:	Természettudományok Földtudományok idegen nyelvű folyóiratközlemény hazai lapban folyóiratcikk Random Forest Multiple Adaptive Regression Splines self-training probability data augmentation
Megjelenés:	Hungarian Geographical Bulletin. - "Accepted by Publisher" (2025), p. 1-29. -
További szerzők:	Abdelmajeed, Adam Elrasheed Ali (1988-) (Geologist) Kovács Lilla (Msc hallgató) Holb Imre (1973-) (agrármérnök) Likó Szilárd Balázs Abriha Dávid (1995-) (geográfus)
Pályázati támogatás:	TÁMOP-4.1.1.C-13/1/KONV-2014-0001 SUPPORT
Internet cím:	Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon: