Naslov
Soybean yield prediction based on irrigation and nitrogen fertilization using machine learning

Autori
Galić Subašić, Daria ; Jurišić, Mladen ; Radočaj, Dorijan ; Plaščak, Ivan ; Rapčan, Irena

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, prošireni sažetak, ostalo

Izvornik
Book of Abstracts Digital Technologies in Agriculture No1/2022 / - Osijek : Fakultet agrobiotehničkih znanosti Sveučilišta Josipa Jurja Strossmayera u Osijeku, 2022, 24-24

ISBN
978-953-8421-03-7

Skup
1st International Symposium on Digital Technologies in Agriculture

Mjesto i datum
Osijek, Hrvatska, 06.12.2022. - 08.12.2022

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
crop management, regression algorithms, random forest, extreme gradient boost, decision trees

Sažetak
The production of soybean (Glycine max L. Merr.) has increased significantly in recent years and represents one of the most important highly profitable legumes. Multiple linear regression (MLR) represented a conventional prediction approach and served as the baseline for evaluating the efficiency of machine learning algorithms for the prediction of soybean yield according to irrigation and nitrogen fertilization. Random forest and Extreme gradient boost outperformed the conventional Multiple linear regression according to all three metrics, producing 9.7% and 9.5% higher R2 than baseline.

Izvorni jezik
Engleski

Znanstvena područja
Poljoprivreda (agronomija), Interdisciplinarne biotehničke znanosti

POVEZANOST RADA