Publikasjoner
NIBIOs ansatte publiserer flere hundre vitenskapelige artikler og forskningsrapporter hvert år. Her finner du referanser og lenker til publikasjoner og andre forsknings- og formidlingsaktiviteter. Samlingen oppdateres løpende med både nytt og historisk materiale. For mer informasjon om NIBIOs publikasjoner, besøk NIBIOs bibliotek.
2026
Forfattere
Anne Linn HykkerudSammendrag
Det er ikke registrert sammendrag
Forfattere
Anne Linn Hykkerud Mirjana Sadojevic Inger Martinussen Siv Fagertun Remberg Anita SønstebySammendrag
Det er ikke registrert sammendrag
Forfattere
Linghan Huang Tingxuan Zhuang Meiqi Zhang Syed Tahir Ata-Ul-Karim Kang Yu Krzysztof Kusnierek Wei Li Xiaojun Liu Yongchao Tian Yan Zhu Weixing Cao Qiang CaoSammendrag
Early-season prediction of winter wheat yield and grain protein content is essential for guiding fertilizer and irrigation decisions and reducing uncertainty in variable agroecosystems, as yield affects profitability and quality affects market value and nutrition. Although multi-source data and both single-task learning (STL) and multi-task learning (MTL) are widely used for predicting grain yield and quality, the conditions under which each approach performs best remain poorly understood, especially when data availability, noise, and measurement or computational constraints vary. To address this gap, we conducted a three-year field experiment in Henan Province, China, compiling environmental, agronomic, and proximal-sensing variables across five growth stages. Seven subsets were constructed, including environmental, agronomic, sensor, and combined subsets, and STL/MTL variants of Multilayer Perceptron (MLP), Transformer, and Random Forest (RF) were benchmarked. SHapley Additive exPlanations (SHAP) analysis quantified feature- and stage-level contributions and guided construction of compact Top-K subsets for accuracy–efficiency trade-offs. Multi-source fusion substantially improved accuracy over single-source inputs, with the combined agronomic-sensor subset providing the best performance (yield R2 = 0.823; GPC R2 = 0.743). Under the current stage-aggregated multi-source representation, MLPs outperformed Transformers and RFs across configurations, indicating that compact nonlinear models were better suited to the present medium-dimensional tabular setting. MTL provided the greatest benefit with sparse feature sets or imbalanced predictive difficulty, whereas STL performed better when information was abundant and signals were strong. SHAP analysis showed that agronomic and sensor features associated with biomass accumulation, nitrogen status, water availability, and canopy light interception were key drivers of model predictions, particularly during erecting and early grain filling. These findings further show that the value of STL versus MTL depends on data-source composition and information richness, and that SHAP can be used not only for interpretation but also for reduced-feature subset design. Within the present plot-scale setting, this study therefore provides a decision-oriented framework for identifying both accuracy-oriented and efficiency-oriented configurations, with efficiency referring to feature parsimony, reduced input and preprocessing burden, and computational time for winter wheat yield and GPC.
Forfattere
Linn Vassvik Anders Nielsen Michael P. D. Garratt Bjørn Arild Hatteland Joseph Chipperfield Erik Trond AschehougSammendrag
Apples are dependent upon pollinators for the transfer of pollen between cultivars to ensure high quality fruit production. Agricultural intensification has reduced the availability of stable floral resources for wild bees, leading to widespread declines of important pollinators of apples. Managed honeybees are commonly used to supplement pollination services in apple orchards, but honeybees are less efficient pollinators compared to wild bees. We investigated whether increased flower abundance in the understory vegetation of apple orchards can increase pollinator activity to apple flowers. We compared bee visitation in five orchards in Eastern Norway: three unmowed orchards, and two mowed orchards. In unmowed orchards, dandelions ( Taraxacum spp.) dominated the understory vegetation. Bee observations were conducted on the understory vegetation and apple trees, via manual observations and time-lapse cameras. Wild bees preferentially visited apple flowers over dandelions, while honeybees did not differ in their visits to apple flowers and dandelion flowers. We also found that the abundance of dandelion flowers in the understory increased visits by wild bees to apple flowers. Taken together, this suggests that within orchard floral resources do not compete for pollinators but instead increase apple visitation and improve pollination success. Our results highlight the importance of managing apple orchards for wild bee populations and the potential short-term benefits of understory floral resources on apple production. Implications for insect conservation Our results show that understory vegetation should be left unmowed to increase pollination of apple flowers and provide pollinators with alternate floral resources before, during, and after apple flowering.
Forfattere
Anne Linn Hykkerud Meeri Santikko Michel Verheul Baoru Yang Niina Kelanne Dmitry Kechasov Anita SønstebySammendrag
Det er ikke registrert sammendrag
Sammendrag
Det er ikke registrert sammendrag
Forfattere
Sean O’ConnorSammendrag
Det er ikke registrert sammendrag
Sammendrag
Det er ikke registrert sammendrag
Forfattere
Narta ElshaniSammendrag
Det er ikke registrert sammendrag
Forfattere
Darius KviklysSammendrag
Det er ikke registrert sammendrag