dc.creator | Kovačević, Miloš | |
dc.creator | Bursać, Petar | |
dc.creator | Bajat, Branislav | |
dc.creator | Kilibarda, Milan | |
dc.date.accessioned | 2022-11-28T11:17:05Z | |
dc.date.available | 2022-11-28T11:17:05Z | |
dc.date.issued | 2022 | |
dc.identifier.uri | https://grafar.grf.bg.ac.rs/handle/123456789/2804 | |
dc.description.abstract | Soil organic carbon represents the main nutrient source for crop yields, which is of great importance to agricultural production. This research investigates the usage of a transfer learning-based neural network model to predict SOC values from geochemical soil parameters. The results on datasets representing five European countries showed that the model was able to capture the valuable information contained in grassland soil samples when predicting the SOC values in cropland areas. | sr |
dc.language.iso | en | sr |
dc.relation | info:eu-repo/grantAgreement/ScienceFundRS/AI/6527073/RS// | sr |
dc.rights | openAccess | sr |
dc.rights.uri | https://creativecommons.org/licenses/by-nc-nd/4.0/ | |
dc.source | 1st Serbian International Conference on Applied Artificial Intelligence (SICAAI), Kragujevac, Serbia | sr |
dc.subject | soil organic carbon (SOC) | sr |
dc.subject | transfer learning | sr |
dc.subject | neural network | sr |
dc.title | AI in Agriculture | sr |
dc.type | conferenceObject | sr |
dc.rights.license | BY-NC-ND | sr |
dc.identifier.fulltext | http://grafar.grf.bg.ac.rs/bitstream/id/10772/aai2022soc_final.pdf | |
dc.identifier.rcub | https://hdl.handle.net/21.15107/rcub_grafar_2804 | |
dc.type.version | publishedVersion | sr |