Találati lista | Tudóstér

001-es BibID:	BIBFORM111452
035-os BibID:	(cikkazonosító)1297 (Scopus)85160411163 (WoS)000994795300001
Első szerző:	Harsányi Endre (agrármérnök)
Cím:	Data Mining and Machine Learning Algorithms for Optimizing Maize Yield Forecasting in Central Europe / Endre Harsányi, Bashar Bashir, Sana Arshad, Akasairi Ocwa, Attila Vad, Abdullah Alsalman, István Bácskai, Tamás Rátonyi, Omar Hijazi, Adrienn Széles, Safwan Mohammed
Dátum:	2023
ISSN:	2073-4395
Megjegyzések:	Artificial intelligence, specifically machine learning (ML), serves as a valuable tool for decision support in crop management under ongoing climate change. However, ML implementation to predict maize yield is still limited in Central Europe, especially in Hungary. In this context, we assessed the performance of four ML algorithms (Bagging (BG), Decision Table (DT), Random Forest (RF) and Artificial Neural Network-Multi Layer Perceptron (ANN-MLP)) in predicting maize yield based on four different input scenarios. The collected data included both agricultural data (production (PROD) (ton) and maize cropped area (AREA) (ha)) and climate data (annual mean temperature ?C (Tmean), precipitation (PRCP) (mm), rainy days (RD), frosty days (FD) and hot days (HD)). This research adopted four scenarios, as follows: SC1: AREA+ PROD+ Tmean+ PRCP+ RD+ FD+ HD; SC2: AREA+ PROD; SC3: Tmean+ PRCP+ RD+ FD+ HD; and SC4: AREA+ PROD+ Tmean+ PRCP. In the training stage, ANN-MLP-SC1 and ANN-MLP-SC4 outperformed other ML algorithms; the correlation coefficient (r) was 0.99 for both, while the root mean squared errors (RMSEs) were 107.9 (ANN-MLP-SC1) and 110.7 (ANN-MLP-SC4). In the testing phase, the ANN-MLP-SC4 had the highest r value (0.96), followed by ANN-MLP-SC1 (0.94) and RF-SC2 (0.94). The 10-fold cross validation also revealed that the ANN-MLP-SC4 and ANN-MLP-SC1 have the highest performance. We further evaluated the performance of the ANN-MLP-SC4 in predicting maize yield on a regional scale (Budapest). The ANN-MLP-SC4 succeeded in reaching a high-performance standard (r = 0.98, relative absolute error = 21.87%, root relative squared error = 20.4399% and RMSE = 423.23). This research promotes the use of ANN as an efficient tool for predicting maize yield, which could be highly beneficial for planners and decision makers in developing sustainable plans for crop management.
Tárgyszavak:	Agrártudományok Növénytermesztési és kertészeti tudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk maize yield climate multilayer perceptron random forest optimum model
Megjelenés:	Agronomy-Basel. - 13 : 5 (2023), p. 1-22. -
További szerzők:	Bashir, Bashar Arshad, Sana Ocwa, Akasairi (1987-) (Crop scientist) Vad Attila (1981-) (agrármérnök) Alsalman, Abdullah Bácskai István (1985-) (Okleveles gépészmérnök) Rátonyi Tamás (1967-) (agrármérnök) Hijazi, Omar Széles Adrienn (1980-) (okleveles agrármérnök) Mohammed Safwan (1985-) (agrármérnök)
Pályázati támogatás:	TKP2021-NKTA-32 Egyéb
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon:

001-es BibID:	BIBFORM112086
035-os BibID:	(cikkazonosító)1499 (WoS)001013887900001 (Scopus)85163976318
Első szerző:	Radócz László (Növényorvos)
Cím:	Investigation of the detectability of corn smut fungus (Ustilago maydis DC. Corda) infection based on UAV multispectral technology / László Radócz, Atala Szabó, András Tamás, Árpád Illés, Csaba Bojtor, Péter Ragán, Attila Vad, Adrienn Széles, Endre Harsányi, László Radócz
Dátum:	2023
ISSN:	2073-4395
Megjegyzések:	Corn smut fungus (Ustilago maydis [DC.] Corda) is a globally widespread pathogen affecting both forage and sweet maize hybrids, with higher significance in sweet maize. Remote sensing technologies demonstrated favorable results for disease monitoring on the field scale. The study focused on the changes in vegetation index (VI) values influenced by the pathogen. In this study, four hybrids, two forage maize and two sweet maize hybrids were examined. Artificial infection was carried out at three different doses: a low (2500 sporidium number/mL), medium (5000 sporidium number/mL) and high dose (10,000 sporidium number/mL) with a non-infected control plot for each hybrid. The experimental plots were monitored using a multispectral UAV sensor of five monochrome channels on three different dates, i.e., 7, 14 and 21 days after infection. Five different indices (NDVI, GNDVI, ENDVI, LCI, and NDRE) were determined in Quantum GIS 3.20. The obtained results demonstrated that the infection had a significant effect on the VI values in sweet maize hybrids. A high-dose infection in the Dessert R 73 hybrid resulted in significantly lower values compared to the non-infected hybrids in three indices (NDVI, LCI and GNDVI). In the case of the NOA hybrids, GNDVI and ENDVI were able to show significant differences between the values of the infection levels.
Tárgyszavak:	Agrártudományok Növénytermesztési és kertészeti tudományok idegen nyelvű folyóiratközlemény külföldi lapban folyóiratcikk corn smut fungus disease monitoring multispectral imaging remote sensing
Megjelenés:	Agronomy-Basel. - 13 : 6 (2023), p. 1-15. -
További szerzők:	Szabó Atala (1995-) (növénytermesztő mérnök) Tamás András (1986-) (gazdasági agrármérnök, növénytermesztés és kertészeti tudományok) Illés Árpád (1994-) (növényorvos) Bojtor Csaba (1993-) (okleveles növényorvos) Ragán Péter (1986-) (környzetgazdálkodási agrármérnök) Vad Attila (1981-) (agrármérnök) Széles Adrienn (1980-) (okleveles agrármérnök) Radócz László (1965-) (növényvédő agrármérnök)
Pályázati támogatás:	TKP2021-NKTA-32 Egyéb
Internet cím:	Intézményi repozitóriumban (DEA) tárolt változat DOI
Borító:
Saját polcon: