TY - JOUR AU - Vári, Tamás Zsolt AU - Sümegi, Pál TI - Geochemical and sedimentological analyses on the Romanian Sphagnum peat bog Tăul fără fund JF - MIRES AND PEAT J2 - MIRES PEAT VL - 31 PY - 2024 IS - 4 SP - 1 EP - 16 PG - 16 SN - 1819-754X DO - 10.19189/MaP.2023.OMB.Sc.2308958 UR - https://m2.mtmt.hu/api/publication/34785080 ID - 34785080 LA - English DB - MTMT ER - TY - JOUR AU - Amankulova, Khilola AU - Farmonov, Nizom AU - Omonov, Khasan AU - Abdurakhimova, Mokhigul AU - Mucsi, László TI - Integrating the Sentinel-1, Sentinel-2 and Topographic data into soybean yield modelling using Machine Learning JF - ADVANCES IN SPACE RESEARCH J2 - ADV SPACE RES VL - 73 PY - 2024 IS - 8 SP - 4052 EP - 4066 PG - 15 SN - 0273-1177 DO - 10.1016/j.asr.2024.01.040 UR - https://m2.mtmt.hu/api/publication/34539323 ID - 34539323 LA - English DB - MTMT ER - TY - JOUR AU - Szilágyi, Gábor AU - Gulyás, Sándor AU - Vári, Tamás Zsolt AU - Sümegi, Pál TI - Late Quaternary Paleoecology and Environmental History of the Hortobágy, an Alkaline Steppe in Central Europe JF - DIVERSITY (BASEL) J2 - DIVERSITY-BASEL VL - 16 PY - 2024 IS - 1 SP - 67 SN - 1424-2818 DO - 10.3390/d16010067 UR - https://m2.mtmt.hu/api/publication/34427009 ID - 34427009 LA - English DB - MTMT ER - TY - THES AU - Szalai, Ádám TI - Az okosvárostól az okosfalvakig: a smart city koncepció alkalmazhatóságának néhány földrajzi aspektusa Magyarországon PY - 2023 SP - 148 UR - https://m2.mtmt.hu/api/publication/34656363 ID - 34656363 LA - Hungarian DB - MTMT ER - TY - CHAP AU - SOHRAB, SEYEDEH MEHRMANZAR AU - Csikós, Nándor AU - Szilassi, Péter ED - Blanka, Viktória TI - Spatio-temporal variability of the connection between spatial characteristics of the transportation networks and PM10 air pollution: a European scale analysis T2 - Natural Hazards and Climate Change - conference and workshop for identifying and tackling challenges together PB - Szegedi Tudományegyetem, Geoinformatikai, Természet- és Környezetföldrajzi Tanszék CY - Szeged SN - 9789633069301 PY - 2023 SP - 36 EP - 36 PG - 1 UR - https://m2.mtmt.hu/api/publication/34571144 ID - 34571144 LA - English DB - MTMT ER - TY - CHAP AU - SOHRAB, SEYEDEH MEHRMANZAR AU - Csikós, Nándor AU - Szilassi, Péter ED - Markovic, SB TI - Seasonal Variability in PM10 Concentrations: A European-Scale Analysis of Urban and Suburban Land Cover Influences. T2 - International Conference Natural Resources and Environmental Risks: Towards a Sustainable Future PB - University of Novi Sad, Faculty of Sciences CY - Novi Sad SN - 9788670316508 PY - 2023 SP - 59 EP - 59 PG - 1 UR - https://m2.mtmt.hu/api/publication/34570957 ID - 34570957 LA - English DB - MTMT ER - TY - JOUR AU - Rosiani, Diyah AU - Gibral Walay, Muhamad AU - Rahalintar, Pradini AU - Candra, Arya Dwi AU - Sofyan, Akhmad AU - Arison Haratua, Yesaya TI - Application of Artificial Intelligence in Predicting Oil Production Based on Water Injection Rate JF - INTERNATIONAL JOURNAL ON ADVANCED SCIENCE, ENGINEERING AND INFORMATION TECHNOLOGY J2 - INT J ADV SCI ENG INFORM TECHNOL VL - 13 PY - 2023 IS - 6 SP - 2338 EP - 2344 PG - 7 SN - 2088-5334 DO - 10.18517/ijaseit.13.6.19399 UR - https://m2.mtmt.hu/api/publication/34506642 ID - 34506642 AB - The utilization of artificial intelligence (AI) has become imperative across various domains, including the oil and gas industry, which covers several fields, including reservoirs, drilling, and production. In oil and gas production, conventional methods, such as reservoir simulation, are used to predict the oil production rate. This simulation requires comprehensive data, so each process step takes a long time and is expensive. AI is urgently needed and can be a solution in this case. This research aims to apply AI techniques to forecast oil production rates based on water injection rates from two injection wells. Three wells are connected with a direct line drive pattern. Three different AI methods were applied, including multiple linear polynomial regression (PR), multiple linear regression (MLR), and artificial neural networks (ANN) in constructing oil production rate prediction models. Actual field data of 1180 data are used, including water injection rate data from two injection wells and oil production history data from one production well. The dataset has been split randomly into 80% training and 20% allocated for testing subsets. The training data is used to build predictive models, while the testing data is used to validate model performance. Comparative analysis selects the model with the lowest root mean square error (RMSE) and the highest R^2 test value. Results demonstrate that the ANN model achieves the smallest Root Mean Square Error (RMSE) of 0.142 and the highest R^2 test value of 16.2%, outperforming the PR and MLR methods. The ANN prediction model provides a rapid and efficient approach to estimating oil production rates. LA - English DB - MTMT ER - TY - JOUR AU - Farmonov, Nizom AU - Amankulova, Khilola AU - Khan, Shahid Nawaz AU - Abdurakhimova, Mokhigul AU - Szatmári, József AU - Khabiba, Tukhtaeva AU - Makhliyo, Radjabova AU - Khodicha, Meiliyeva AU - Mucsi, László TI - Effectiveness of machine learning and deep learning models at county-level soybean yield forecasting JF - HUNGARIAN GEOGRAPHICAL BULLETIN (2009-) J2 - HUNG GEOGR BULL (2009-) VL - 72 PY - 2023 IS - 4 SP - 383 EP - 398 PG - 16 SN - 2064-5031 DO - 10.15201/hungeobull.72.4.4 UR - https://m2.mtmt.hu/api/publication/34500549 ID - 34500549 AB - 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. LA - English DB - MTMT ER - TY - JOUR AU - Torma, Andrea AU - Náfrádi, Katalin AU - Törőcsik, Tünde AU - Sümegi, Pál TI - Integrated archaeobotanical evidence on the vegetation reconstruction around the tomb of Sultan Suleiman I at Szigetvár (SW Hungary) JF - ARCHEOMETRIAI MŰHELY J2 - ARCHEOMETRIAI MŰHELY VL - 20 PY - 2023 IS - 3 SP - 201 EP - 226 PG - 26 SN - 1786-271X DO - 10.55023/issn.1786-271X.2023-017 UR - https://m2.mtmt.hu/api/publication/34445428 ID - 34445428 N1 - University of Szeged, Department of Geology and Paleontology, Egyetem street 2-6, Szeged, H-6722, Hungary Eötvös Loránd Research Network, Institute for Nuclear Research, Bem tér 18/c, Debrecen, 4026, Hungary Export Date: 15 January 2024 Correspondence Address: Náfrádi, K.; University of Szeged, Egyetem street 2-6, Hungary; email: nafradi@geo.u-szeged.hu AB - During the archaeological excavation of the memorial place (türbe) of the Ottoman sultan Suleiman I, a moat was revealed north of the memorial place in 2015. The moat system was identified by boreholes and excavated in 2015, when 30–30 liter samples were taken from the 250 cm deep moat at 15 cm intervals for archaeobotanical and anthracological analyses. Samples were taken at 10 cm intervals for pollen studies from the archaeological profile of the moat filling. In our publication, based on the previously presented geochronological results, our aim was to reconstruct the vegetation around the memorial tomb of Suleiman, on the basis of archaeobotanical, anthracological and pollen analytical data. We were able to reconstruct ploughed lands (cereal cultivation), vegetable, fruit and vineyards, pasture lands, forest patches and trampled areas related to human activity (settlement). The military census of 1689 indicated similar tract of land structure of the crop production areas. The tomb and the Islamic pilgrimage monastery and pilgrim town (Ottoman name was Türbe kasabası) were demolished from 1692/1693 and divided into agricultural zones, where orchards, arable lands, gardens and vineyards were established. LA - English DB - MTMT ER - TY - CHAP AU - Sümegi, Pál AU - Gulyás, Sándor AU - Náfrádi, Katalin AU - Törőcsik, Tünde ED - Bosnakoff, Mariann ED - Szives, Ottilia ED - Főzy, István TI - Püspökfürdői termálvízhez kötődő refúgium jégkor végi és jelenkori jelentősége T2 - 26. Magyar Őslénytani Vándorgyűlés PB - Magyarhoni Földtani Társulat CY - Budapest SN - 9789638221865 PY - 2023 SP - 33 EP - 34 PG - 2 UR - https://m2.mtmt.hu/api/publication/34434371 ID - 34434371 LA - Hungarian DB - MTMT ER -