Search

The large-scale pixel-based land use/land cover classification is a challenging task, which depends on many circumstances. This study aims to create LULC maps with the nomenclature of Coordination of Information on the Environment (CORINE) Land Cover (CLC) for years when the CLC databases are not available. Furthermore, testing the predicted maps for land use changes in the last 30 years in Hungary. Histogram-based gradient boosting classification tree (HGBCT) classifier was tested at classification. According to the results, the classifier, with the use of texture variance and landscape metrics is capable to generate accurate predicted maps, and the comparison of the predicted maps provides a detailed image of the land use changes.

Land cover change and deforestation are important global ecosystem hazards. As for Syria, the current conflict and the subsequent absence of the forest preservation are main reasons for land cover change. This study aims to investigate the temporal and spatial aspects and trends of the land cover alterations in the southern Syrian coastal basins. In this study, land cover maps were made from surface reflectance images of Landsat-5(TM), Landsat-7(ETM+) and Landsat-8(OLI) during May (period of maximum vegetation cover) in 1987, 2002 and 2017. The images were classified into four different thematic classes using the maximum likelihood supervised classification method. The classification results were validated using 160 validation points in 2017, where overall accuracy was 83.75%. Spatial analysis was applied to investigate the land cover change during the period of 30 years for each basin and the whole study area. The results show 262.40 km2 reduction of forest and natural vegetation area during (1987-2017) period, and 72.5% of this reduction occurred during (2002-2017) period due to over-cutting of forest trees as a source of heating by local people, especially during the conflict period. This reduction was particularly high in the Alabrash and Hseen basins with 76.13 and 79.49 km2 respectively, and was accompanied by major increase of agriculture lands area which is attributed to dam construction in these basins which allowed people to cultivate rural lands for subsistence or to enhance their economic situation. The results of this study must draw the relevant authorities’ attention to preserve the remaining forest area.

Crop yield forecasting is critical in modern agriculture to ensure food security, economic stability, and effective resource management. The main goal of this study was to combine historical multisource satellite and environmental datasets with a deep learning (DL) model for soybean yield forecasting in the United States' Corn Belt. The following Moderate Resolution Imaging Spectroradiometer (MODIS) products were aggregated at the county level. The crop data layer (CDL) in Google Earth Engine (GEE) was used to mask the data so that only soybean pixels were selected. Several machine learning (ML) models were trained by using 5 years of data from 2012 to 2016: random forest (RF), least absolute shrinkable and selection operator (LASSO) regression, extreme gradient boosting (XGBoost), and decision tree regression (DTR) as well as DL-based one-dimensional convolutional neural network (1D-CNN). The best model was determined by comparing their performances at forecasting the soybean yield in 2017-2021 at the county scale. The RF model outperformed all other ML models with the lowest RMSE of 0.342 t/ha, followed by XGBoost (0.373 t/ha), DTR (0.437 t/ha), and LASSO (0.452 t/ha) regression. However, the 1D-CNN model showed the highest forecasting accuracy for the 2018 growing season with RMSE of 0.280 t/ha. The developed 1D-CNN model has great potential for crop yield forecasting because it effectively captures temporal dependencies and extracts meaningful input features from sequential data. [ABSTRACT FROM AUTHOR]

Hyperspectral remote sensing combined with advanced image processing techniques is an efficient tool for the identification of agricultural crops. In our study we pursued spectral analysis on a relatively small sample area using low number of training points to examine the potential of high resolution imagery. Spectral separability measurements were applied to reveal spectral overlapping between 4 crop species and for the discrimination we also used statistical comparisons such as plotting the PC values and calculating standard deviation of single band reflectance values on our classes. These statistical results were proven to be good indicators of spectral similarity and potential confusion of data samples. The classification of Spectral Angle Mapper (SAM) had an overall accuracy of 72% for the four species where the poorest results were obtained from the test points of garlic and sugar beet. Comparing the statistical analyses we concluded that spectral homogeneity does not necessarily have influence on the accuracy of mapping, whereas separability scores strongly correlate with classification results, implying also that preliminary statistical assessments can improve the efficiency of training site selection and provide useful information to specify some technical requirements of airborne hyperspectral surveys.

Hyperspectral imaging combined with the potentials of airborne scanning is a powerful tool to monitor environmental processes. The aim of this research was to use high resolution remotely sensed data to map the spatial extent of inland excess water patches in a Hungarian study area that is known for its oil and gas production facilities. Periodic floodings show high spatial and temporal variability, nevertheless, former studies have proven that the affected soil surfaces can be accurately identified. Besides separability measurements, we performed spectral angle classification, which gave a result of 85% overall accuracy and we also compared the generated land cover map with LIDAR elevation data.

The restructuring of Hungarian higher education according to European expectations has resulted in fundamental changes. Due to the intensifying market and the decreasing number of applicants, institutions are interested in ensuring the necessary number of students. The objective of the study is to identify those schools where the greatest interest in the courses offered by the University of Szeged can be expected. The selection was based on spatial and temporal analysis of submitted applications using geographical information system methods. The results can contribute to attracting the necessary number of students and to developing a sound basis for future educational planning.

The aim of this study is to measure and analyze the effects of exterior annual temperature change on the interior temperature of a dripstone cave. The measurement was carried out in Hajnóczy Cave located in the southern part of the Bükk Mountains, Hungary. Although the cave has only one entrance known, there are more evidences that prove the strong effect of exterior conditions on the interior processes like temperature fluctuation and dripstone development. Using a high resolution wireless digital thermometer sensor network, the air temperature was measured at 10 points every 10 minutes for a longer period. The goal of our study is to analyze the spatial profile of air temperature of the cave that is developed during the summer and winter air circulation period between 11 November, 2012, and 10 April, 2013. Based on these data, different zones of the cave could be separated; and during the winter and summer conditions, the climatic variability of the entrance, the transitional, and the deep cave zone were described. The long-term analysis of the cave proved that the summer and winter air circulation changes are caused by the prolonged continuance of a below 10 °C average daily temperature.

In the environmental risk assessment of oil fields, a detailed knowledge of the heterogeneity of groundwater surfaces is absolutely indispensable. Based on theoretical considerations, in order to analyse small-scale heterogeneities, we decided that the Sequential Gaussian Simulation (SGS) approach seemed to be the most appropriate one. This method gives preference to the reproduction of small-scale heterogeneities at the expense of local accuracy. To test whether this kind of heterogeneity of the groundwater level corresponds to sedimentological variability, a point bar of the River Tisza (South-Hungary) was chosen. In variograms, the longest range was derived from the large-scale sedimentological heterogeneity of the point-bar, the medium range was in accordance with the radius of the meander and its direction coincided with the depositional strike of the meander, while the shortest range corresponded to the lateral heterogeneity of the deposits where the ground water level was measured. The similarities and differences of the realizations of SGS express the uncertainty of the map representation of the ground water surface. The E-type estimates of 100 equiprobable realizations resulted in a very detailed surface. The hydraulic gradient map obtained from the E-type estimates can provide us with a better understanding of the local flow characteristics.

The aim of this study the authors measured and analyzed the effect of the exterior daily temperature change on the interior temperature in a dripstone cave visited by cavers exclusively. The measurement was carried out in the Hajnóczy Cave located in the southern part of Bükk Mountains in Hungary. Although only one entrance is known, there are more evidences for the strong effect of exterior conditions on the interior processes like temperature fluctuation and dripstone development. Using high resolution wireless digital thermometer sensor network the air temperature and air humidity were measured in 32 points in every 10 minutes for long time but now the data of a 8-days period were analyzed. Based on these data different zones of the cave could be separated and during summer conditions the climatic variability of the entrance transitional and deep cave zone was described. Based on statistical analysis of spatial information significant correlation was found between the exterior temperature fluctuation and that of such a cave chamber, which is relatively far from the cave entrance. This fact proves that existence of a fissure system which is permeable for air but not passable for cavers. During the measurement the human effect was also analyzed and 0.3-0.6 °C temperature rising was recognized for a short time. Because of the surface vicinity the effects of the environmental change can have sensible impact on the cave and its natural phenomena. Among others temperature rising, air humidity decreasing were detected in present study.

The main purpose of this study is to simulate future land use up to 2030 and to evaluate the change in landscape pattern due to land-use change from 1995 to 2030 in Binh Duong province, Vietnam. Land-use maps generated from multi-temporal Landsat images from 1995 to 2020 and various physical and social driving variables were used as inputs. Markov chain and Decision Forest algorithm integrated in Land Change Modeler application of IDRISI software were used to predict quantity and location of future land-use allocation. Meanwhile, FRAGSTATS software was used to calculate landscape metrics at class and landscape levels. The simulation results showed that there will be 253.8 km2 of agricultural land urbanized in the period from 2020 to 2030. The urban areas will gradually expand from the edge of the existing zones and fill the newly planned areas from South to North and Northeast of the province. The results also revealed that the studied landscape was decreasing in dominance and increasing diversity and heterogeneity at landscape level. The processes of dispersion and aggregation were taking place at the same time in the entire landscape and in the urban class. Meanwhile, the classes of agriculture, mining, and greenspace were increasingly dispersed, but the shape of patches was becoming more regular. The water class increased the dispersion and the irregularity of the patch shape. Finally, the landscape metrics of the unused land fluctuated over time. [ABSTRACT FROM AUTHOR]

This paper examines the status of geography in higher education in Hungary. Stress is placed on reforms begun in the 1990s to launch new curricula for training professional geographers. The authors played an important role in developing this new curriculum by introducing new subjects into geography programmes, working out the scope and sequence of courses, obtaining accreditation and carrying out market research for graduates. The project was motivated by a decline in demand for geography and geography teachers in secondary schools accompanied by an increase in demand for geographers trained to work in public administration, government and business. The graduates of the new professional geographer curriculum receive a practice-oriented education designed to cultivate their spatial problem solving and applied geographical skills. In this paper the authors present the steps in the curriculum reform and suggest that it may serve as a model for reform in a number of nearby countries planning to join the EU. [ABSTRACT FROM AUTHOR]