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.
2023
Sammendrag
Weeds affect crop yield and quality due to competition for resources. In order to reduce the risk of yield losses due to weeds, herbicides or non-chemical measures are applied. Weeds, especially creeping perennial species, are generally distributed in patches within arable fields. Hence, instead of applying control measures uniformly, precision weeding or site-specific weed management (SSWM) is highly recommended. Unmanned aerial vehicle (UAV) imaging is known for wide area coverage and flexible operation frequency, making it a potential solution to generate weed maps at a reasonable cost. Efficient weed mapping algorithms need to be developed together with UAV imagery to facilitate SSWM. Different machine learning (ML) approaches have been developed for image-based weed mapping, either classical ML models or the more up-to-date deep learning (DL) models taking full advantage of parallel computation on a GPU (graphics processing unit). Attention-based transformer DL models, which have seen a recent boom, are expected to overtake classical convolutional neural network (CNN) DL models. This inspired us to develop a transformer DL model for segmenting weeds, cereal crops, and ‘other’ in low-resolution RGB UAV imagery (about 33 mm ground sampling distance, g.s.d.) captured after the cereal crop had turned yellow. Images were acquired during three years in 15 fields with three cereal species (Triticum aestivum, Hordeum vulgare, and Avena sativa) and various weed flora dominated by creeping perennials (mainly Cirsium arvense and Elymus repens). The performance of our transformer model, 1Dtransformer, was evaluated through comparison with a classical DL model, 1DCNN, and two classical ML methods, i.e., random forest (RF) and k-nearest neighbor (KNN). The transformer model showed the best performance with an overall accuracy of 98.694% on pixels set aside for validation. It also agreed best and relatively well with ground reference data on total weed coverage, R2 = 0.598. In this study, we showed the outstanding performance and robustness of a 1Dtransformer model for weed mapping based on UAV imagery for the first time. The model can be used to obtain weed maps in cereals fields known to be infested by perennial weeds. These maps can be used as basis for the generation of prescription maps for SSWM, either pre-harvest, post-harvest, or in the next crop, by applying herbicides or non-chemical measures.
Forfattere
Amos Samkumar Rajan Premkumar Katja Hannele Karppinen Inger Martinussen Richard V. Espley Laura Elina JaakolaSammendrag
Det er ikke registrert sammendrag
Forfattere
Lone Ross Gry Alfredsen Marie Bogstad Ree Fay Madeleine Farstad Erlend Andre T. HermansenSammendrag
Det er ikke registrert sammendrag
Forfattere
Heidi Udnes Aamot Hesam Mousavi Jafar Razzaghian Guro Brodal Michael Sulyok Rudolf Krska Simon G. Edwards Ingerd Skow HofgaardSammendrag
In Norway, high levels of mycotoxins are occasionally observed in oat grain lots, and this cause problems for growers, livestock producers and the food and feed industries. Mycotoxins of primary concern are deoxynivalenol (DON) produced by Fusarium graminearum and HT2- and T2-toxins (HT2+T2) produced by Fusarium langsethiae. Although effort has been made to understand the epidemiology of F. langsethiae in oats, this is still not fully understood. In the present study, we aimed to increase our understanding of the F. langsethiae – oat interaction. Resistance to F. langsethiae was studied in three oat varieties after inoculation at early (booting, heading, flowering) or late (flowering, milk, dough) growth stages in greenhouse experiments. The oat varieties had previously shown different levels of resistance to F. graminearum: Odal, Vinger (both moderately resistant), and Belinda (susceptible). The levels of F. langsethiae DNA and HT2+T2 in harvested grain were measured, and differences in aggressiveness (measured as the level of F. langsethiae DNA in grain) between F. langsethiae isolates were observed. Substantial levels of F. langsethiae DNA and HT2+T2 were detected in grain harvested from oats that had been spray-inoculated at heading or later growth stages, suggesting that oats are susceptible to F. langsethiae from heading and onwards. Vinger had a moderate resistance to F. langsethiae/HT2+T2, whereas Odal and Belinda were relatively susceptible. We observed that late inoculations resulted in relatively higher levels of trichothecene A metabolites other than HT2+T2 (mostly glycosylated HT-2, and smaller amounts of some other metabolites) in harvested grain, which indicate that infections close to harvest may pose a further risk to food and feed safety.
Forfattere
Stig Strandli GezeliusSammendrag
Det er ikke registrert sammendrag
Forfattere
Heidi Udnes AamotSammendrag
Det er ikke registrert sammendrag
Sammendrag
Det er ikke registrert sammendrag
Forfattere
Hadush Tsehaye Beyene Leif Sundheim Arne Tronsmo May Bente Brurberg Dereje Assefa Anne Marte TronsmoSammendrag
Det er ikke registrert sammendrag
Sammendrag
Material exiting the harvester is composed of chaff and straw. Chaff is a by-product of grain harvest comprises weed seeds and husk. Harvest Weed Seed Control (HWSC) systems aim at collecting and/or killing weed seeds in the chaff fraction during crop grain harvest. If chaff is removed or processed via impact mills or concentrated in a narrow zone in the field and collected, the overall weed infestation may be reduced in the following years. Chaff may be used as a new biomass feedstock, for example, as a renewable energy source, material for construction ( e.g. , insulating boards, cardboard, bedding), soil improvement ( e.g ., mulch, mushroom compost), and for agricultural purposes ( e.g. , weed growth inhibitor, animal diet). Using chaff directly is unfavorable because of its low bulk density. Therefore, compressing chaff into pellets can improve its handling. In this preliminary study, we assessed how pelletizing would affect the germinability of weed seeds in the chaff pellets. Whole wheat chaff and fine wheat chaff sieved were mixed with seeds of the two weed species scentless mayweed ( Tripleurospermum inodorum (L.) Sch.Bip.) and cornflower ( Centaurea cyanus L.), respectively. While 22% of T. inodorum seeds and 59% of C. cyanus seeds in wheat chaff samples were able to germinate, no weed seeds germinated from moist pelletized original and fine wheat chaff samples. The study indicates a low risk of spreading weed seeds with pelletized chaff probably because the heating during the pelletizing process kills the weed seeds.
Forfattere
Grete StokstadSammendrag
Det er ikke registrert sammendrag