@article{MTMT:30945995,
	title = {The application of a neural network-based ragweed pollen forecast by the Ragweed Pollen Alarm System in the Pannonian biogeographical region},
	url = {https://m2.mtmt.hu/api/publication/30945995},
	author = {Csépe, Zoltán and Leelőssy, Ádám and Manyoki, G. and Kajtor-Apatini, D. and Udvardy, O. and Peter, B. and Páldy, Anna and Gelybó, Györgyi and Szigeti, Tamás and Pándics, Tamás and Kofol-Seliger, A. and Simcic, A. and Leru, P. M. and Eftimie, A. -M. and Sikoparija, B. and Radisic, P. and Stjepanovic, B. and Hrga, I. and Vecenaj, A. and Vucic, A. and Peros-Pucar, D. and Skoric, T. and Scevkova, J. and Bastl, M. and Berger, U. and Magyar, Donát},
	doi = {10.1007/s10453-019-09615-w},
	journal-iso = {AEROBIOLOGIA},
	journal = {AEROBIOLOGIA},
	volume = {36},
	unique-id = {30945995},
	issn = {0393-5965},
	abstract = {Ragweed Pollen Alarm System (R-PAS) has been running since 2014 to provide pollen information for countries in the Pannonian biogeographical region (PBR). The aim of this study was to develop forecast models of the representative aerobiological monitoring stations, identified by analysis based on a neural network computation. Monitoring stations with 7-day Hirst-type pollen trap having 10-year long validated data set of ragweed pollen were selected for the study from the PBR. Variables including forecasted meteorological data, pollen data of the previous days and nearby monitoring stations were used as input of the model. We used the multilayer perceptron model to forecast the pollen concentration. The multilayer perceptron (MLP) is a feedforward artificial neural network. MLP is a data-driven method to forecast the behaviour of complex systems. In our case, it has three layers, one of which is hidden. MLP utilizes a supervised learning technique called backpropagation for training to get better performance. By testing the neural network, we selected different sets of variables to predict pollen levels for the next 3 days in each of the monitoring stations. The predicted pollen level categories (low-medium-high-very high) are shown on isarithmic map. We used the mean square error, mean absolute error and correlation coefficient metrics to show the forecasting system's performance. The average of the Pearson correlations is around 0.6 but shows big variability (0.13-0.88) among different locations. Model uncertainty is mainly caused by the limitation of the available input data and the variability in ragweed season patterns. Visualization of the results of the neural network forecast on isarithmic maps is a good tool to communicate pollen information to general public in the PBR.},
	keywords = {POLLEN; Neural network; RAGWEED; MLP; FORECAST},
	year = {2020},
	eissn = {1573-3025},
	pages = {131-140},
	orcid-numbers = {Leelőssy, Ádám/0000-0001-9583-0127; Szigeti, Tamás/0000-0001-5078-9503}
}

@article{MTMT:31775853,
	title = {Elaborating Hungarian Segment of the Global Map of Salt-Affected Soils (GSSmap): National Contribution to an International Initiative},
	url = {https://m2.mtmt.hu/api/publication/31775853},
	author = {Szatmári, Gábor and Bakacsi, Zsófia and Laborczi, Annamária and Petrik, Ottó and Pataki, Róbert and Tóth, Tibor and Pásztor, László},
	doi = {10.3390/rs12244073},
	journal-iso = {REMOTE SENS-BASEL},
	journal = {REMOTE SENSING},
	volume = {12},
	unique-id = {31775853},
	year = {2020},
	eissn = {2072-4292},
	orcid-numbers = {Szatmári, Gábor/0000-0003-3201-598X; Laborczi, Annamária/0000-0003-4095-7838; Pásztor, László/0000-0002-1605-4412}
}

@article{MTMT:30807941,
	title = {Spatio-temporal assessment of topsoil organic carbon stock change in Hungary},
	url = {https://m2.mtmt.hu/api/publication/30807941},
	author = {Szatmári, Gábor and Pirkó, Béla and Koós, Sándor and Laborczi, Annamária and Bakacsi, Zsófia and Szabó, József and Pásztor, László},
	doi = {10.1016/j.still.2019.104410},
	journal-iso = {SOIL TILL RES},
	journal = {SOIL & TILLAGE RESEARCH},
	volume = {195},
	unique-id = {30807941},
	issn = {0167-1987},
	year = {2019},
	eissn = {1879-3444},
	orcid-numbers = {Szatmári, Gábor/0000-0003-3201-598X; Laborczi, Annamária/0000-0003-4095-7838; Pásztor, László/0000-0002-1605-4412}
}

@article{MTMT:3413675,
	title = {Comparison of various uncertainty modelling approaches based on geostatistics and machine learning algorithms},
	url = {https://m2.mtmt.hu/api/publication/3413675},
	author = {Szatmári, Gábor and Pásztor, László},
	doi = {10.1016/j.geoderma.2018.09.008},
	journal-iso = {GEODERMA},
	journal = {GEODERMA},
	volume = {337},
	unique-id = {3413675},
	issn = {0016-7061},
	year = {2019},
	eissn = {1872-6259},
	pages = {1329-1340},
	orcid-numbers = {Szatmári, Gábor/0000-0003-3201-598X; Pásztor, László/0000-0002-1605-4412}
}

@article{MTMT:3076278,
	title = {Terrestrial Ecosystem Process Model Biome-BGCMuSo: Summary of improvements and new modeling possibilities},
	url = {https://m2.mtmt.hu/api/publication/3076278},
	author = {Hidy, Dóra and Barcza, Zoltán and Marjanović, H. and Ostrogović Sever, M. Z. and Dobor, Laura and Gelybó, Györgyi and Fodor, Nándor and Pintér, Krisztina and Churkina, G. and Running, S. and Thornton, P. and Bellocchi, G. and Haszpra, László and Horváth, Ferenc and Suyker, A. and Nagy, Zoltán},
	doi = {10.5194/gmd-9-4405-2016},
	journal-iso = {GEOSCI MODEL DEV},
	journal = {GEOSCIENTIFIC MODEL DEVELOPMENT},
	volume = {9},
	unique-id = {3076278},
	issn = {1991-959X},
	year = {2016},
	eissn = {1991-9603},
	pages = {4405-4437},
	orcid-numbers = {Barcza, Zoltán/0000-0002-1278-0636; Dobor, Laura/0000-0001-6712-9827; Haszpra, László/0000-0002-7747-6475; Nagy, Zoltán/0000-0003-2839-522X}
}

@article{MTMT:1980629,
	title = {Coupling the 4M crop model with national geo-databases for assessing the effects of climate change on agro-ecological characteristics of Hungary},
	url = {https://m2.mtmt.hu/api/publication/1980629},
	author = {Fodor, Nándor and Pásztor, László and Németh, Tamás},
	doi = {10.1080/17538947.2012.689998},
	journal-iso = {INT J DIGIT EARTH},
	journal = {INTERNATIONAL JOURNAL OF DIGITAL EARTH},
	volume = {7},
	unique-id = {1980629},
	issn = {1753-8947},
	abstract = {The 4M crop model was used to investigate the prospective effects of climate change on the agro-ecological characteristics of Hungary. The model was coupled with a detailed meteorological database and spatial soil information systems covering the whole territory of Hungary. Plant-specific model parameters were determined by inverse modeling. Future meteorological data were produced from the present meteorological data by combining a climate change scenario and a stochastic weather generator. Using the available and the generated data, the present and the prospective agro-ecological characteristics of Hungary were determined. According to the simulation results, average yields will decrease considerably (~30%) due to climate change. The rate of nitrate leaching will prospectively decrease as well. The fluctuations of both the yields and the annual nitrate leaching rates will most likely increase approaching the end of the twenty-first century. On the basis of the simulation results, the role of autumn crops is likely to become more significant in Hungary. The achieved results can be generalized for more extended regions based on the concept of spatial (geographical) analogy.},
	year = {2014},
	eissn = {1753-8955},
	pages = {391-410},
	orcid-numbers = {Pásztor, László/0000-0002-1605-4412}
}