Szilárd Szabó
Biographic Data
| ID | 6318525 |
|---|---|
| NAME | Szilárd Szabó |
| GIVEN NAMES | Szilárd |
| FAMILY NAME | Szabó |
| SIGNATURE | SZABO S |
| AFFILIATIONS | University of Debrecen |
| ORCID | 0000-0002-2670-7384 |
| VERIFIED | Yes |
| TOTAL WORKS | 8 |
| TOTAL CITATIONS | 0 |
| AUTHOR COUNT | 8 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2016 |
| LATEST PUBLICATION YEAR | 2025 |
| H-INDEX | 0 |
Lithological mapping with pseudo-labelling
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. Multiple Adaptive Regression Splines (MARS) and Random Forest (RF) were used to classify a …
Analysis of the association between image resolution and landscape metrics using multi-sensor Lulc maps
This study aims to investigate the changes in landscape metrics with varying spatial resolution from Sentinel-2 (10 m), SPOT 7 (1.5 m), Pleaides (0.5 m), and Worldview-4 (0.3 m) images. We implemented Geographic Object-Based Image Analysis (GEOBIA) techniques to all images to identify 21 land use and land cover (LULC) classes, which were then used to calculate several landscape metrics. We performed the Welch hypothesis testing on the class-level…
Performance evaluation of machine learning algorithms to assess soil erosion in Mediterranean farmland
The development of new techniques, such as machine learning (ML), can provide better insight into the processes and drivers of soil erosion and runoff. However, the performance of these techniques to assess soil erosion in agricultural landscapes is poorly understood. The aim of this study was to evaluate the performance of four machine learning algorithms, generalized linear model (GLM), Random Forest (RF), elastic net regression (EN) and multip…
Machine Learning for Gully Feature Extraction Based on a Pan-Sharpened Multispectral Image
Gullies reduce both the quality and quantity of productive land, posing a serious threat to sustainable agriculture, hence, food security. Machine Learning (ML) algorithms are essential tools in the identification of gullies and can assist in strategic decision-making relevant to soil conservation. Nevertheless, accurate identification of gullies is a function of the selected ML algorithms, the image and number of classes used, i.e., binary (two …
Parameterizing the modified water cloud model to improve soil moisture data retrieval using vegetation models
The objective was to parameterize a modified water cloud model using crop coefficients (A and B). These crop coefficients were derived from Landsat-8 and Sentinel-2 data. Whereas the coefficients C and D are of soil parameters. The water cloud model was modified using crop coefficients by minimizing the RMSE between observed VVσ0 and Sentinel-1 based simulated VVσ0. The comparison with observed and simulated VV polarized σ0 showed low RMSE (0.81 …
Pollution Assessment Based on Element Concentration of Tree Leaves and Topsoil in Ayutthaya Province, Thailand
Atmospheric aerosol particles containing heavy metal contaminants deposit on the surface of plant leaves and the topsoil. Our aim was to reveal the pollution along an industrial-urban-rural gradient (IURG) in the central provinces of Thailand. Leaf samples from Ficus religiosa and Mimusops elengi were collected along with topsoil samples under the selected trees. Al, Ba, Ca, Cr, Cu, Fe, K, Mg, Mn, Na, Ni, Pb, and Zn concentrations were determined…
Confirmation of a theory
Fluvial geomorphologists have tried to describe the outstanding tectonically affected avulsion process of Tisza River at the Great Hungarian Plain by various theoretical concepts.Flume experiments provide the ability to examine the main characteristic processes of a highlighted surface development theory under controlled settings within an accelerated time scale.Our goal was to reconstruct and refine these hypotheses from a new experimental point…
Mapping an ecological network of green habitat patches and their role in maintaining urban biodiversity in and around Debrecen city (Eastern Hungary)
No prominent works on this page.
Confirmation of a theory
Fluvial geomorphologists have tried to describe the outstanding tectonically affected avulsion process of Tisza River at the Great Hungarian Plain by various theoretical concepts.Flume experiments provide the ability to examine the main characteristic processes of a highlighted surface development theory under controlled settings within an accelerated time scale.Our goal was to reconstruct and refine these hypotheses from a new experimental point…
Mapping an ecological network of green habitat patches and their role in maintaining urban biodiversity in and around Debrecen city (Eastern Hungary)
Machine Learning for Gully Feature Extraction Based on a Pan-Sharpened Multispectral Image
Gullies reduce both the quality and quantity of productive land, posing a serious threat to sustainable agriculture, hence, food security. Machine Learning (ML) algorithms are essential tools in the identification of gullies and can assist in strategic decision-making relevant to soil conservation. Nevertheless, accurate identification of gullies is a function of the selected ML algorithms, the image and number of classes used, i.e., binary (two …
Parameterizing the modified water cloud model to improve soil moisture data retrieval using vegetation models
The objective was to parameterize a modified water cloud model using crop coefficients (A and B). These crop coefficients were derived from Landsat-8 and Sentinel-2 data. Whereas the coefficients C and D are of soil parameters. The water cloud model was modified using crop coefficients by minimizing the RMSE between observed VVσ0 and Sentinel-1 based simulated VVσ0. The comparison with observed and simulated VV polarized σ0 showed low RMSE (0.81 …
Pollution Assessment Based on Element Concentration of Tree Leaves and Topsoil in Ayutthaya Province, Thailand
Atmospheric aerosol particles containing heavy metal contaminants deposit on the surface of plant leaves and the topsoil. Our aim was to reveal the pollution along an industrial-urban-rural gradient (IURG) in the central provinces of Thailand. Leaf samples from Ficus religiosa and Mimusops elengi were collected along with topsoil samples under the selected trees. Al, Ba, Ca, Cr, Cu, Fe, K, Mg, Mn, Na, Ni, Pb, and Zn concentrations were determined…
Performance evaluation of machine learning algorithms to assess soil erosion in Mediterranean farmland
The development of new techniques, such as machine learning (ML), can provide better insight into the processes and drivers of soil erosion and runoff. However, the performance of these techniques to assess soil erosion in agricultural landscapes is poorly understood. The aim of this study was to evaluate the performance of four machine learning algorithms, generalized linear model (GLM), Random Forest (RF), elastic net regression (EN) and multip…
Analysis of the association between image resolution and landscape metrics using multi-sensor Lulc maps
This study aims to investigate the changes in landscape metrics with varying spatial resolution from Sentinel-2 (10 m), SPOT 7 (1.5 m), Pleaides (0.5 m), and Worldview-4 (0.3 m) images. We implemented Geographic Object-Based Image Analysis (GEOBIA) techniques to all images to identify 21 land use and land cover (LULC) classes, which were then used to calculate several landscape metrics. We performed the Welch hypothesis testing on the class-level…
Lithological mapping with pseudo-labelling
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. Multiple Adaptive Regression Splines (MARS) and Random Forest (RF) were used to classify a …
Geography (4 works) · Mathematics (4 works) · Computer Science (3 works) · Ecology (3 works) · Environmental Science (3 works) · Geology (3 works) · Remote sensing (3 works) · Soil erosion and sediment transport (3 works) · Soil Science (3 works) · Artificial Intelligence (2 works)