Anita Sabat-Tomala

Mrs. Anita Sabat-Tomala

University of Warsaw, Warsaw, Mazowieckie, Poland
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 February 2020 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Anita Sabat-TomalaAnita Sabat-Tomala
Anita Sabat-Tomala
EREdwin Raczko
Edwin Raczko
Bogdan ZagajewskiBogdan Zagajewski
Bogdan Zagajewski
Invasive and expansive plant species are considered a threat to natural biodiversity because of their high adaptability and low habitat requirements. Species investigated in this research, including Solidago spp., Calamagrostis epigejos, and Rubus spp., are successfully displacing native vegetation and claiming new areas, which in turn severely decreases natural ecosystem richness, as they rapidly encroach on protected areas (e.g., Natura 2000 habitats). Because of the damage caused, the European Union (EU) has committed all its member countries to monitor biodiversity. In this paper we compared two machine learning algorithms, Support Vector Machine (SVM) and Random Forest (RF), to identify Solidago spp., Calamagrostis epigejos, and Rubus spp. on HySpex hyperspectral aerial images. SVM and RF are reliable and well-known classifiers that achieve satisfactory results in the literature. Data sets containing 30, 50, 100, 200, and 300 pixels per class in the training data set were used to train SVM and RF classifiers. The classifications were performed on 430-spectral bands and on the most informative 30 bands extracted using the Minimum Noise Fraction (MNF) transformation. As a result, maps of the spatial distribution of analyzed species were achieved; high accuracies were observed for all data sets and classifiers (an average F1 score above 0.78). The highest accuracies were obtained using 30 MNF bands and 300 sample pixels per class in the training data set (average F1 score > 0.9). Lower training data set sample sizes resulted in decreased average F1 scores, up to 13 percentage points in the case of 30-pixel samples per class.

23 December 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Anita Sabat-TomalaAnita Sabat-Tomala
Anita Sabat-Tomala
EREdwin Raczko
Edwin Raczko
Bogdan ZagajewskiBogdan Zagajewski
Bogdan Zagajewski
Recent developments in computer hardware made it possible to assess the viability of permutation-based approaches in image classification. Such approaches sample a reference dataset multiple times in order to train an arbitrary number of machine learning models while assessing their accuracy. So-called iterative accuracy assessment techniques or Monte-Carlo-based approaches can be a useful tool when it comes to assessment of algorithm/model performance but are lacking when it comes to actual image classification and map creation. Due to the multitude of models trained, one has to somehow reason which one of them, if any, should be used in the creation of a map. This poses an interesting challenge since there is a clear disconnect between algorithm assessment and the act of map creation. Our work shows one of the ways this disconnect can be bridged. We calculate how often a given pixel was classified as given class in all variations of a multitude of post-classification images delivered by models trained during the iterative assessment procedure. As a classification problem, a mapping of Calamagrostis epigejos, Rubus spp., Solidago spp. invasive plant species using three HySpex hyperspectral datasets collected in June, August and September was used. As a classification algorithm, the support vector machine approach was chosen, with training hyperparameters obtained using a grid search approach. The resulting maps obtained F1-scores ranging from 0.87 to 0.89 for Calamagrostis epigejos, 0.89 to 0.97 for Rubus spp. and 0.99 for Solidago spp.

27 March 2020 in Wetlands Ecology and Management
Verified
Journal Article
Open access
PDF file
Dominik KopećDominik Kopeć
Dominik Kopeć
Anita Sabat-TomalaAnita Sabat-Tomala
Anita Sabat-Tomala
DMDorota Michalska-Hejduk
Dorota Michalska-Hejduk
Anna JarocińskaAnna Jarocińska
Anna Jarocińska
Jan NiedzielkoJan Niedzielko
Jan Niedzielko
Remote sensing is increasingly widely used in nature conservation management. The research focuses on developing an optimal set of airborne raster data for the identification of the invasive alien species Spiraea tomentosa L. The plant species selected for the purposes of this study poses a serious threat to peat bog plant communities, moist coniferous forests, and meadows in Central Europe. The impact of the data acquisition time on the accuracy of classification and the percentage cover limit required for correct identification of a target species using the developed method were also investigated. The study area is located in the Lower Silesian forests in Poland and is protected as a Natura 2000 site. Airborne hyperspectral and laser scanning data were simultaneously acquired two times in the growing season (August and September 2016) parallel to on-ground reference data collection. The 1 m resolution HySpex images with spectral range of 0.4–2.5 μm were corrected atmospherically, radiometrically and geometrically. Airborne Laser Scanning (ALS) data acquired at 7 points/m2 were used to generate several products, e.g. Canopy Height Model (CHM), rasters representing morphometric features of the area (Multiresolution Index of the Ridge Top Flatness or Valley Bottom Flatness—MRRTF, MRVBF), wetness relations (Topographic Wetness Index—TWI) and the availability of light (Total Insolation—TI), intensity of laser pulse reflection and geometric relations of vegetation points (i.a. Vegetation Cover, Vegetation Mean Intensity). The Random Forest (RF) classification and different raster datasets were used to identify the target species. As a result, the highest accuracy was obtained for the scenario based on HySpex images acquired in September. The accuracy (f1 score) for the target species achieved 83%. The developed method for the identification of Spiraea tomentosa has a great potential for application and can be used for monitoring peat bogs threatened by invasion of alien plants.

3 February 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Anita Sabat-TomalaAnita Sabat-Tomala
Anita Sabat-Tomala
EREdwin Raczko
Edwin Raczko
Bogdan ZagajewskiBogdan Zagajewski
Bogdan Zagajewski
The mapping of invasive plant species is essential for effective ecosystem control and planning, especially in protected areas. One of the widespread invasive plants that threatens the species richness of Natura 2000 habitats in Europe is the large-leaved lupine (Lupinus polyphyllus). In our study, this species was identified at two Natura 2000 sites in southern Poland using airborne HySpex hyperspectral images, and support vector machine (SVM) and random forest (RF) classifiers. Aerial and field campaigns were conducted three times during the 2016 growing season (May, August, and September). An iterative accuracy assessment was performed, and the influence of the number of minimum noise fraction (MNF) bands on the obtained accuracy of lupine identification was analyzed. The highest accuracies were obtained for the August campaign using 30 MNF bands as input data (median F1 score for lupine was 0.82–0.85), with lower accuracies for the May (F1 score: 0.77–0.81) and September (F1 score: 0.78–0.80) campaigns. The use of more than 30 MNF bands did not significantly increase the classification accuracy. The SVM and RF algorithms allowed us to obtain comparable results in both research areas (OA: 89–94%). The method of the multiple classification and thresholding of frequency images allowed the results of many predictions to be included in the final map.

31 May 2018 in European Journal of Remote Sensing
Verified
Journal Article
Open access
Anita Sabat-TomalaAnita Sabat-Tomala
Anita Sabat-Tomala
Anna JarocińskaAnna Jarocińska
Anna Jarocińska
Bogdan ZagajewskiBogdan Zagajewski
Bogdan Zagajewski
AMArtur Magnuszewski
Artur Magnuszewski
ŁSŁukasz Maciej Sławik
Łukasz Maciej Sławik
JLJerzy Ryszard Lechnio
Jerzy Ryszard Lechnio
This research focuses on the use of HySpex hyperspectral images for verification of two-dimensional hydrodynamic modelling of open-channel flow over loose bed (CCHE2D) and assessment of water quality in the Zegrze Reservoir. The CCHE2D hydrodynamic model results show the distribution of hydraulic parameters of water flow and the sediment concentrations in the reservoir. HySpex images were used to obtain remote sensing indices of water quality. The images were compared to the hydrodynamic model results and field measurements. The analysis of hydrodynamic model results and hyperspectral image indices show the spatial distribution of the water’s physico-chemical properties in the reservoir, and poor mixing of the Bug River and the Narew River at their confluence. This study shows that there is synergy potential in using hydrodynamic modelling results and remote sensing indices of water quality for analysis of the reservoir’s water quality.