Találati lista | Tudóstér

001-es BibID:	BIBFORM113915
035-os BibID:	(WoS)001044509700001 (Scopus)85167334773
Első szerző:	Likó Szilárd Balázs
Cím:	Deep learning-based training data augmentation combined with post-classification improves the classification accuracy for dominant and scattered invasive forest tree species / Szilárd Balázs Likó, Imre J. Holb, Viktor Oláh, Péter Burai, Szilárd Szabó
Dátum:	2024
ISSN:	2056-3485
Megjegyzések:	Species composition of forests is a very important component from the point of view of nature conservation and forestry. We aimed to identify 10 tree species in a hilly forest stand using a hyperspectral aerial image with a particular focus on two invasive species, namely Ailanthus tree and black locust. Deep learning-based training data augmentation (TDA) and post-classification techniques were tested with Random Forest and Support Vector Machine (SVM) classifiers. SVM had better performance with 81.6% overall accuracy (OA). TDA increased the OA to 82.5% and post-classification with segmentation improved the total accuracy to 86.2%. The class-level performance was more convincing: the invasive Ailanthus trees were identified with 40% higher producer's and user's accuracies (PA and UA) to 70% related to the common technique (using a training dataset and classifying the trees). The PA and UA did not change in the case of the other invasive species, black locust. Accordingly, this new method identifies well Ailanthus, a sparsely distributed species in the area; while it was less efficient with black locust that dominates larger patches in the stand. The combination of the two ancillary steps of hyperspectral image classification proved to be reasonable and can support forest management planning and nature conservation in the future.
Tárgyszavak:	Természettudományok Földtudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk ailanthus black locust Convolutional Neural Network multiresolution segmentation Random Forest Support Vector Machine
Megjelenés:	Remote Sensing in Ecology and Conservation. - 10 : 2 (2024), p. 203-219. -
További szerzők:	Holb Imre (1973-) (agrármérnök) Oláh Viktor (1980-) (biológus) Burai Péter (1977-) (agrármérnök) Szabó Szilárd (1974-) (geográfus)
Pályázati támogatás:	K138079 Egyéb K138503 Egyéb K131478 Egyéb KKP144068 Egyéb
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:

001-es BibID:	BIBFORM105793
035-os BibID:	(WoS)000969757300056 (Scopus)85143205656
Első szerző:	Likó Szilárd Balázs
Cím:	Tree species composition mapping with dimension reduction and post-classification using very high-resolution hyperspectral imaging / Szilárd Balázs Likó, László Bekő, Péter Burai, Imre J. Holb, Szilárd Szabó
Dátum:	2022
ISSN:	2045-2322
Megjegyzések:	Tree species' composition of forests is essential in forest management and nature conservation. We aimed to identify the tree species structure of a floodplain forest area using a hyperspectral image. We proposed an efficient novel strategy including the testing of three dimension reduction (DR) methods: Principal Component Analysis, Minimum Noise Fraction (MNF) and Indipendent Component Analysis with five machine learning (ML) algorithms (Maximum Likelihood Classifier, Support Vector Classification, Support Vector Machine, Random Forest and Artificial Neural Network) to find the most accurate outcome; altogether 300 models were calculated. Post-classification was applied by combining the multiresolution segmentation and filtering. MNF was the most efficient DR technique, and at least 7 components were needed to gain an overall accuracy (OA) of?>?75%. Forty-five models had?>?80% OAs; MNF was 43, and the Maximum Likelihood was 19 times among these models. Best classification belonged to MNF with 10 components and Maximum Likelihood classifier with the OA of 83.3%. Post-classification increased the OA to 86.1%. We quantified the differences among the possible DR and ML methods, and found that even?>?10% worse model can be found using popular standard procedures related to the best results. Our workflow calls the attention of careful model selection to gain accurate maps.
Tárgyszavak:	Természettudományok Földtudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk
Megjelenés:	Scientific Reports. - 12 : 12 (2022), p. 1-14. -
További szerzők:	Bekő László (1986-) (okleveles vidékfejlesztési agrármérnök) Burai Péter (1994-) (informatikus) Holb Imre (1973-) (agrármérnök) Szabó Szilárd (1974-) (geográfus)
Pályázati támogatás:	TKP2020-NKA-04 Egyéb 2019-2.1.1-EUREKA-2019-00005 Egyéb NKFI-K-138079 Egyéb NKFI Co-operative Doctoral Program of the Ministry of Innovation and Technology 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: