Simple item page
 

Application of Artificial Neural Networks Sensitivity Analysis for the Pre-Identification of Highly Significant Factors Influencing the Yield and Digestibility of Grassland Sward in the Climatic Conditions of Central Poland

cris.virtual.author-orcid0000-0003-3721-6473
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.author-orcid0000-0003-3663-8826
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.author-orcid0000-0002-2222-6866
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcid3fe42726-36c4-478a-818f-a10f72d4a6ef
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcid8cc3d8c6-eb76-45ba-b461-1a1d5e664c52
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcid09c81af2-c2b2-424c-b2ec-4cda600883bf
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
dc.abstract.enProgressive climate changes are the most important challenges for modern agriculture. Permanent grassland represents around 70% of all agricultural land. In comparison with other agroecosystems, grasslands are more sensitive to climate change. The aim of this study was to create deterministic models based on artificial neural networks to identify highly significant factors influencing the yield and digestibility of grassland sward in the climatic conditions of central Poland. The models were based on data from a grassland experiment conducted between 2014 and 2016. Phytophenological data (harvest date and botanical composition of sward) and meteorological data (average temperatures, total rainfall, and total effective temperatures) were used as independent variables, whereas qualitative and quantitative parameters of the feed made from the grassland sward (dry matter digestibility, dry matter yield, and protein yield) were used as dependent variables. Nine deterministic models were proposed Y_G, DIG_G, P_G, Y_GB, DIG_GB, P_GB, Y_GC, DIG_GC, and P_GC, which differed in the input variable and the main factor from the grassland experiment. The analysis of the sensitivity of the neural networks in the models enabled the identification of the independent variables with the greatest influence on the yield of dry matter and protein as well as the digestibility of the dry matter of the first regrowth of grassland sward, taking its diverse botanical composition into account. The results showed that the following factors were the most significant (rank 1): the average daily air temperature, total rainfall, and the percentage of legume plants. This research will be continued on a larger group of factors influencing the output variables and it will involve an attempt to optimise these factors.
dc.affiliationWydział Inżynierii Środowiska i Inżynierii Mechanicznej
dc.affiliationWydział Rolnictwa, Ogrodnictwa i Bioinżynierii
dc.affiliation.instituteKatedra Inżynierii Biosystemów
dc.affiliation.instituteKatedra Łąkarstwa i Krajobrazu Przyrodniczego
dc.contributor.authorNiedbała, Gniewko
dc.contributor.authorWróbel, Barbara
dc.contributor.authorPiekutowska, Magdalena
dc.contributor.authorZielewicz, Waldemar
dc.contributor.authorPaszkiewicz-Jasińska, Anna
dc.contributor.authorWojciechowski, Tomasz
dc.contributor.authorNiazian, Mohsen
dc.date.access2025-12-10
dc.date.accessioned2025-12-12T09:03:55Z
dc.date.available2025-12-12T09:03:55Z
dc.date.copyright2022-05-08
dc.date.issued2022
dc.description.abstract<jats:p>Progressive climate changes are the most important challenges for modern agriculture. Permanent grassland represents around 70% of all agricultural land. In comparison with other agroecosystems, grasslands are more sensitive to climate change. The aim of this study was to create deterministic models based on artificial neural networks to identify highly significant factors influencing the yield and digestibility of grassland sward in the climatic conditions of central Poland. The models were based on data from a grassland experiment conducted between 2014 and 2016. Phytophenological data (harvest date and botanical composition of sward) and meteorological data (average temperatures, total rainfall, and total effective temperatures) were used as independent variables, whereas qualitative and quantitative parameters of the feed made from the grassland sward (dry matter digestibility, dry matter yield, and protein yield) were used as dependent variables. Nine deterministic models were proposed Y_G, DIG_G, P_G, Y_GB, DIG_GB, P_GB, Y_GC, DIG_GC, and P_GC, which differed in the input variable and the main factor from the grassland experiment. The analysis of the sensitivity of the neural networks in the models enabled the identification of the independent variables with the greatest influence on the yield of dry matter and protein as well as the digestibility of the dry matter of the first regrowth of grassland sward, taking its diverse botanical composition into account. The results showed that the following factors were the most significant (rank 1): the average daily air temperature, total rainfall, and the percentage of legume plants. This research will be continued on a larger group of factors influencing the output variables and it will involve an attempt to optimise these factors.</jats:p>
dc.description.accesstimeat_publication
dc.description.bibliographyil., bibliogr.
dc.description.financepublication_nocost
dc.description.financecost0,00
dc.description.if3,7
dc.description.number5
dc.description.points100
dc.description.versionfinal_published
dc.description.volume12
dc.identifier.doi10.3390/agronomy12051133
dc.identifier.issn2073-4395
dc.identifier.urihttps://sciencerep.up.poznan.pl/handle/item/6376
dc.identifier.weblinkhttps://www.mdpi.com/2073-4395/12/5/1133
dc.languageen
dc.relation.ispartofAgronomy
dc.relation.pagesart. 1133
dc.rightsCC-BY
dc.sciencecloudnosend
dc.share.typeOPEN_JOURNAL
dc.subject.ensensitivity analysis
dc.subject.endeterministic modeling
dc.subject.enartificial neural networks
dc.subject.enmeadow sward
dc.subject.enbotanical composition of sward
dc.subject.enair temperature
dc.subject.enprecipitation
dc.titleApplication of Artificial Neural Networks Sensitivity Analysis for the Pre-Identification of Highly Significant Factors Influencing the Yield and Digestibility of Grassland Sward in the Climatic Conditions of Central Poland
dc.title.volumeSpecial Issue Predictions and Estimations in Agricultural Production under a Changing Climate
dc.typeJournalArticle
dspace.entity.typePublication
oaire.citation.issue5
oaire.citation.volume12