Találati lista | Tudóstér

001-es BibID:	BIBFORM109207
035-os BibID:	(cikkazonosító)e14045 (Scopus)85149799289
Első szerző:	Abriha Dávid (geográfus)
Cím:	Smaller is better? Unduly nice accuracy assessments in roof detection using remote sensing data with machine learning and k-fold cross-validation / Dávid Abriha, Prashant K. Srivastava, Szilárd Szabó
Dátum:	2023
ISSN:	2405-8440
Megjegyzések:	Deriving the thematic accuracy of models is a fundamental part of image classification analyses. K-fold cross-validation (KCV), as an accuracy assessment technique, can be biased because existing built-in algorithms of software solutions do not handle the high autocorrelation of remotely sensed images, leading to overestimation of accuracies. We aimed to quantify the magnitude of the overestimation of KCV-based accuracies and propose a method to overcome this problem with the example of rooftops using a WorldView-2 (WV2) satellite image, and two orthophotos. Random split to training/testing subsets, independent testing and different types of repeated KCV sampling strategies were used to generate input datasets for classification. Results revealed that applying the random splitting of reference data to training/testing subsets and KCV methods had significantly biased the accuracies by up to 17%; overall accuracies (OAs) can incorrectly reach >99%. We found that repeated KCV can provide similar results to independent testing when spatial sampling is applied with a sufficiently large distance threshold (in our case 10 m). Coarser resolution of WV2 ensured more reliable results (up to a 5?9% increase in OA) than orthophotos. Object-based pixel purity of buildings showed that when using a majority filter for at least of 50% of objects the final accuracy approached 100% with each sampling method. The final conclusion is that KCV-based modelling ensures better accuracy than single models (with better pixel purity on the object level), but the accuracy metrics without spatially filtered sampling are not reliable.
Tárgyszavak:	Természettudományok Földtudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk Urban environment Roof classification Accuracy assessment Salt-and-pepper effect Post-classification Object-based pixel purity
Megjelenés:	Heliyon. - 9 : 3 (2023), e14045, p.1-17. -
További szerzők:	Srivastava, Prashant K. Szabó Szilárd (1974-) (geográfus)
Pályázati támogatás:	Kooperatív Doktori Program Egyéb NKFI K 138079 Egyéb NKFI K 142121 Egyéb TKP2020-NKA-04 Egyéb
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:

001-es BibID:	BIBFORM093929
035-os BibID:	(cikkazonosító)e06764
Első szerző:	Mohammed Safwan (agrármérnök)
Cím:	Assessing the WEPP model performance for predicting daily runoff in three terrestrial ecosystems in western Syria / Safwan Mohammed, Mais Hussien, Karam Alsafadi, Ali Mokhtar, Guido Rianna, Issa Kbibo, Mona Barkat, Swapan Talukdar, Szilárd Szabó, Endre Harsanyi
Dátum:	2021
ISSN:	2405-8440
Megjegyzések:	Soil erosion is one of the main threats facing the agriculture and natural resources sector all over the world, and the same is true for Syria. Several empirical and physically based tools have been proposed to assess erosion induced soil losses and runoff driving the processes, from plot to regional spatial scales. The main goal of this research is to evaluate the performance of the Water Erosion Prediction Project (WEPP) model in predicting runoff in comparison with field experiments in the Al-Sabahia region of Western Syria in three ecosystems: agricultural lands (AG), burned forest (BF) and forest (FO). To achieve this, field experimental plots (2?1.65?0.5 m) were prepared to obtain runoff observation data between September 2012 and December 2013. In addition, the input data (atmospheric forcing, soil, slope, land management) were prepared to run the WEPP model to estimate the runoff. The results indicate that the average observed runoffs in the AG, BF and FO were 12.54 ? 1.17, 4.81 ? 0.97 and 1.72 ? 0.16 mm/event, respectively, while the simulated runoffs in the AG, BF and FO were 15.15 ? 0.89, 9.23 ? 1.48 and 2.61 ? 0.47mm/event, respectively. The statistical evaluation of the model's performance showed an unsatisfactory performance of the WEPP model for predicting the run-offs in the study area. This may be caused by the structural flaws in the model, and/or the insufficient site-specific input parameters. So, to achieve good performance and reliable results of the WEPP model, more observation data is required from different ecosystems in Syria. These findings can provide guidance to planners and environmental engineers for proposing environmental protection and water resources management plans in the Coastal Region in Syria.
Tárgyszavak:	Agrártudományok Növénytermesztési és kertészeti tudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk soil erosion wepp model runoff prediction ecosystem statistical analysis
Megjelenés:	Heliyon. - 7 : 4 (2021), p. 1-12. -
További szerzők:	Hussien, Mais Alsafadi, Karam Mokhtar, Ali Rianna, Guido Kbibo, Issa Barkat, Mona Talukdar, Swapan Szabó Szilárd (1974-) (geográfus) Harsányi Endre (1976-) (agrármérnök)
Pályázati támogatás:	TKP2020-IKA-04 Egyéb 2020-4.1.1-TKP2020 Egyéb
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon: