TY - JOUR AU - Szabó, Szilárd AU - Holb, Imre AU - Abriha-Molnár, Vanda Éva AU - Szatmári, Gábor AU - Singh, Sudhir Kumar AU - Abriha, Dávid TI - Classification Assessment Tool: A program to measure the uncertainty of classification models in terms of class-level metrics JF - APPLIED SOFT COMPUTING J2 - APPL SOFT COMPUT VL - 155 PY - 2024 PG - 15 SN - 1568-4946 DO - 10.1016/j.asoc.2024.111468 UR - https://m2.mtmt.hu/api/publication/34741333 ID - 34741333 AB - Accuracy assessments are important steps of classifications and get higher relevance with the soar of machine and deep learning techniques. We provided a method for quick model evaluations with several options: calculate the class level accuracy metrics for as many models and classes as needed; calculate model stability using random subsets of the testing data. The outputs are single calculations, summaries of the repetitions, and/or all accuracy results per repetitions. Using the application, we demonstrated the possibilities of the function and analyzed the accuracies of three experiments. We found that some popular metrics, the binary Overall Accuracy, Sensitivity, Precision, and Specificity, as well as ROC curve, can provide false results when the true negative cases dominate. F1-score, Intersection over Union and the Matthews correlation coefficient were reliable in all experiments. Medians and interquartile ranges (IQR) of the repeated sampling from the testing dataset showed that IQR were small when a model was almost perfect or completely unacceptable; thus, IQR reflected the model stability, reproducibility. We found that there were no general, statistically justified relationship with the median and IQR, furthermore, correlations of accuracy metrics varied by experiments, too. Accordingly, a multi-metric evaluation is suggested instead of a single metric. LA - English DB - MTMT ER - TY - JOUR AU - Bibi, Dina AU - Tőzsér, Dávid AU - Sipos , Bianka AU - Abriha-Molnár, Vanda Éva AU - Simon, Edina AU - Tóthmérész, Béla TI - Complex study of air pollution based on tree species in Vienna JF - AIR QUALITY ATMOSPHERE AND HEALTH J2 - AIR QUAL ATMOS HLTH VL - 17 PY - 2024 IS - 2 SP - 417 EP - 424 PG - 8 SN - 1873-9318 DO - 10.1007/s11869-023-01452-8 UR - https://m2.mtmt.hu/api/publication/34238026 ID - 34238026 AB - Plants are especially useful as biological indicators to assess air pollution and the effects of urbanisation. The aim of this study was to investigate tree species’ sensitivity to air pollution using the Air Pollution Tolerance Index (APTI), the dust content (PM 10 ) of leaves, and the heavy metal concentration of leaves. Sampling sites were in a city park (urban area), a location on the edge of the city (suburban area), and a forested location (rural area) along an urbanisation gradient in the city of Vienna in Austria. Leaf samples were collected from Acer platanoides , Fraxinus excelsior , and Quercus robur tree species. The APTI was determined by measuring the content of relative water ascorbic acid and chlorophyll, and the pH of leaf extracts. We found significant difference among species in their relative water content, pH, and content of ascorbic acid and chlorophyll Additionally, we found significant differences in chlorophyll content and pH based on sampling site. The highest chlorophyll content was found in A. platanoides . There was a significant difference among species in Al, Ba, Cr, Ni, and Zn concentrations in each stage of urbanisation. Based on APTI values, the studied species were sensitive indicators of air pollution; thus, they are useful bioindicator species, and they are suitable for air pollution monitoring. We demonstrated the effects of urbanisation with these bioindicator species with elevated PM 10 , Al, Ba, Cu, Fe, Sr, and Zn concentrations in urban area samples. LA - English DB - MTMT ER - TY - GEN AU - Abriha-Molnár, Vanda Éva AU - Szabó, Szilárd AU - Magura, Tibor AU - Tóthmérész, Béla AU - Abriha, Dávid AU - Sipos , Bianka AU - Simon, Edina TI - Assessment of environmental impacts based on particulate matter, and chlorophyll content of urban trees PY - 2023 UR - https://m2.mtmt.hu/api/publication/34011378 ID - 34011378 LA - English DB - MTMT ER - TY - CHAP AU - Abriha-Molnár, Vanda Éva AU - Simon, Edina AU - Szabó, Szilárd ED - Abriha-Molnár, Vanda Éva TI - Classification of tree species and estimation of Leaf Area Index based on satellite imagery T2 - Az elmélet és a gyakorlat találkozása a térinformatikában XII.: Theory meets practice in GIS PB - Debreceni Egyetemi Kiadó CY - Debrecen SN - 9789633189771 PY - 2021 SP - 215 EP - 218 PG - 4 UR - https://m2.mtmt.hu/api/publication/32640249 ID - 32640249 LA - English DB - MTMT ER - TY - CHAP AU - Abriha-Molnár, Vanda Éva AU - Szabó, Szilárd AU - Simon, Edina ED - Abriha-Molnár, Vanda Éva TI - Species level classification using images from WorldView–2 and WorldView–3 satellites, in a study area in Debrecen T2 - Az elmélet és a gyakorlat találkozása a térinformatikában XII.: Theory meets practice in GIS PB - Debreceni Egyetemi Kiadó CY - Debrecen SN - 9789633189771 PY - 2021 SP - 211 EP - 214 PG - 4 UR - https://m2.mtmt.hu/api/publication/32640237 ID - 32640237 LA - English DB - MTMT ER - TY - JOUR AU - Simon, Edina AU - Abriha-Molnár, Vanda Éva AU - Lajtos, Domonkos AU - Bibi, Dina AU - Tóthmérész, Béla AU - Szabó, Szilárd TI - Usefulness of Tree Species as Urban Health Indicators JF - PLANTS-BASEL J2 - PLANTS-BASEL VL - 10 PY - 2021 IS - 12 PG - 12 SN - 2223-7747 DO - 10.3390/plants10122797 UR - https://m2.mtmt.hu/api/publication/32588712 ID - 32588712 AB - We used the Air Pollution Tolerance Index (APTI), the amount of PM5 and PM10, and the elemental analysis of leaves to explore the sensitivity of tree species to air pollution. We assessed the tolerance of Robinia pseudoacacia, Acer saccharinum, Tilia x europaea, Acer platanoides, Fraxinus excelsior, Betula pendula, Celtis occidentalis, and Platanus x acerifolia to the amount of dust, APTI, and the elemental concentration of leaves. Leaves were collected in Debrecen (Hungary), which has a high intensity of vehicular traffic. The highest amount of PM (both PM10 and PM5) was found on the leaves of A. saccharinum and B. pendula. Our results demonstrated that A. saccharinum was moderately tolerant, while P. acerifolia was intermediate, based on the APTI value. There was a significant difference in the parameters of APTI and the elemental concentration of leaves among species. We found that tree leaves are reliable bioindicators of air pollution in urban areas. Based on the value of APTI, A. saccharinum and P. acerifolia, and based on PM, A. saccharinum and B. pendula are recommended as pollutant-accumulator species, while other studied species with lower APTI values are useful bioindicators of air pollution. The results support landscape engineers and urban developers in finding the best tree species that are tolerant to pollution and in using those as proxies of urban environmental health. LA - English DB - MTMT ER - TY - BOOK ED - Abriha-Molnár, Vanda Éva TI - Az elmélet és a gyakorlat találkozása a térinformatikában XII.: Theory meets practice in GIS PB - Debreceni Egyetemi Kiadó CY - Debrecen PY - 2021 SP - 360 SN - 9789633189771 UR - https://m2.mtmt.hu/api/publication/32491691 ID - 32491691 LA - Hungarian DB - MTMT ER - TY - JOUR AU - Abriha-Molnár, Vanda Éva AU - Simon, Edina AU - Szabó, Szilárd TI - Species-level classification of urban trees from WorldView-2 imagery in Debrecen, Hungary: an effective tool for planning a comprehensive green network to reduce dust pollution JF - EUROPEAN JOURNAL OF GEOGRAPHY J2 - EUROPEAN JOURNAL OF GEOGRAPHY VL - 11 PY - 2020 IS - 2 SP - 33 EP - 46 PG - 14 SN - 1792-1341 DO - 10.48088/ejg.v.mol.11.1.33.46 UR - https://m2.mtmt.hu/api/publication/31787272 ID - 31787272 AB - Urban green spaces of cities are crucial elements of city structure that ensure habitat for species and ecological functionality of habitat patches, maintain biodiversity, and provide environmental services. However, detailed maps intended for planning and improving the existing network require a quick and effective technique for assessing the possibilities. Multispectral imagery is an accessible source for species-level classification of urban trees. Using a multispectral image from the WorldView–2 satellite sensor, we classified six of the most common urban tree species in Debrecen, Hungary. Maximum Likelihood (ML) and Support Vector Machine (SVM) classifiers were applied to different numbers of the MNF-transformed bands. The best overall accuracy was achieved with the ML algorithm applied to the first four transformed bands (75.1%), and with the SVM algorithm applied to eight bands (71.0%). In general, ML performed better than SVM. Despite the relatively low number of spectral bands, we achieved moderately good accuracy for basic vegetation mapping, which can be used in spatial planning and decision making. In a future interdisciplinary research study, we could merge the classification results with the dust adsorption capacity of individual species to assess the reduction of dust pollution by urban trees. LA - English DB - MTMT ER - TY - JOUR AU - Abriha-Molnár, Vanda Éva AU - Tőzsér, Dávid AU - Szabó, Szilárd AU - Tóthmérész, Béla AU - Simon, Edina TI - Use of Leaves as Bioindicator to Assess Air Pollution Based on Composite Proxy Measure (APTI), Dust Amount and Elemental Concentration of Metals JF - PLANTS-BASEL J2 - PLANTS-BASEL VL - 9 PY - 2020 IS - 12 PG - 11 SN - 2223-7747 DO - 10.3390/plants9121743 UR - https://m2.mtmt.hu/api/publication/31750283 ID - 31750283 AB - Monitoring air pollution and environmental health are crucial to ensure viable cities. We assessed the usefulness of the Air Pollution Tolerance Index (APTI) as a composite index of environmental health. Fine and coarse dust amount and elemental concentrations of Celtis occidentalis and Tilia × europaea leaves were measured in June and September at three sampling sites (urban, industrial, and rural) in Debrecen city (Hungary) to assess the usefulness of APTI. The correlation between APTI values and dust amount and elemental concentrations was also studied. Fine dust, total chlorophyll, and elemental concentrations were the most sensitive indicators of pollution. Based on the high chlorophyll and low elemental concentration of tree leaves, the rural site was the least disturbed by anthropogenic activities, as expected. We demonstrated that fine and coarse dust amount and elemental concentrations of urban tree leaves are especially useful for urban air quality monitoring. Correlations between APTI and other measured parameters were also found. Both C. occidentalis and T. europaea were sensitive to air pollution based on their APTI values. Thus, the APTI of tree leaves is an especially useful proxy measure of air pollution, as well as environmental health. LA - English DB - MTMT ER - TY - BOOK ED - Abriha-Molnár, Vanda Éva TI - Az elmélet és a gyakorlat találkozása a térinformatikában XI.: Theory meets practice in GIS PB - Debreceni Egyetemi Kiadó CY - Debrecen PY - 2020 SN - 9789633188866 UR - https://m2.mtmt.hu/api/publication/31676150 ID - 31676150 LA - Hungarian DB - MTMT ER -