Dataset Information

The potential of UAV-borne spectral and textural information for predicting aboveground biomass and N fixation in legume-grass mixtures.

ABSTRACT: Organic farmers, who rely on legumes as an external nitrogen (N) source, need a fast and easy on-the-go measurement technique to determine harvestable biomass and the amount of fixed N (NFix) for numerous farm management decisions. Especially clover- and lucerne-grass mixtures play an important role in the organic crop rotation under temperate European climate conditions. Multispectral sensors mounted on unmanned aerial vehicles (UAVs) are new promising tools for a non-destructive assessment of crop and grassland traits on large and remote areas. One disadvantage of multispectral information and derived vegetations indices is, that both ignore spatial relationships of pixels to each other in the image. This gap can be filled by texture features from a grey level co-occurrence matrix. The aim of this multi-temporal field study was to provide aboveground biomass and NFix estimation models for two legume-grass mixtures through a whole vegetation period based on UAV multispectral information. The prediction models covered different proportions of legumes (0-100% legumes) to represent the variable conditions in practical farming. Furthermore, the study compared prediction models with and without the inclusion of texture features. As multispectral data usually suffers from multicollinearity, two machine learning algorithms, Partial Least Square and Random Forest (RF) regression, were used. The results showed, that biomass prediction accuracy for the whole dataset as well as for crop-specific models were substantially improved by the inclusion of texture features. The best model was generated for the whole dataset by RF with an rRMSE of 10%. For NFix prediction accuracy of the best model was based on RF including texture (rRMSEP = 18%), which was not consistent with crop specific models.

SUBMITTER: Gruner E

PROVIDER: S-EPMC7316270 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The potential of UAV-borne spectral and textural information for predicting aboveground biomass and N fixation in legume-grass mixtures.

Grüner Esther E Wachendorf Michael M Astor Thomas T

PloS one 20200625 6

Organic farmers, who rely on legumes as an external nitrogen (N) source, need a fast and easy on-the-go measurement technique to determine harvestable biomass and the amount of fixed N (NFix) for numerous farm management decisions. Especially clover- and lucerne-grass mixtures play an important role in the organic crop rotation under temperate European climate conditions. Multispectral sensors mounted on unmanned aerial vehicles (UAVs) are new promising tools for a non-destructive assessment of ...[more]

PMID: 32584839

Similar Datasets

Project description:Soil heterogeneity significantly affects plant dynamics such as plant growth and biomass. Most studies developed soil heterogeneity in two dimensions, i.e. either horizontally or vertically. However, soil heterogeneity in natural ecosystems varies both horizontally and vertically, i.e. in three dimensions. Previous studies on plant biomass and biomass allocation rarely considered the joint effects of soil heterogeneity and species composition. Thus, to investigate such joint effects on plant biomass and biomass allocation, a controlled experiment was conducted, where three levels of soil heterogeneity and seven types of species compositions were applied. Such soil heterogeneity was developed by filling nutrient-rich and nutrient-poor substrates in an alternative pattern in pots with different patch sizes (small, medium or large), and species compositions was achieved by applying three plant species (i.e. Festuca elata, Bromus inermis, Elymus breviaristatus) in all possible combinations (growing either in monoculture or in mixtures). Results showed that patch size significantly impacted plant biomass and biomass allocation, which differed among plant species. Specially, at the pot scale, with increasing patch size, shoot biomass decreased, while root biomass and R:S ratio increased, and total biomass tended to show a unimodal pattern, where the medium patch supported higher total biomass. Moreover, at the substrate scale, more shoot biomass and total biomass were found in nutrient-rich substrate. Furthermore, at the community scale, two of the three target plant species growing in monoculture had more shoot biomass than those growing together with other species. Thus, our results indicate soil heterogeneity significantly affected plant biomass and biomass allocation, which differ among plant species, though more research is needed on the generalization on biomass allocation. We propose that soil heterogeneity should be considered more explicitly in studies with more species in long-term experiments.

Project description:Background and Aims:Grassland-based livestock systems in cool maritime regions are commonly dominated by grass monocultures receiving relatively high levels of fertilizer. The current study investigated whether grass-legume mixtures can improve the productivity, resource efficiency and robustness of yield persistence of cultivated grassland under extreme growing conditions over a period of 5 years. Methods:Monocultures and mixtures of two grasses (Phleum pratense and Festuca pratensis) and two legumes (Trifolium pratense and Trifolium repens), one of which was fast establishing and the other temporally persistent, were sown in a field trial. Relative abundance of the four species in the mixtures was systematically varied at sowing. The plots were maintained under three N levels (20, 70 and 220 kg N ha-1 year-1) and harvested twice a year for five consecutive years. Yields of individual species and interactions between all species present were modelled to estimate the species diversity effects. Key Results:Significant positive diversity effects in all individual years and averaged across the 5 years were observed. Across years, the four-species equi-proportional mixture was 71 % (N20: 20 kg N ha-1 year-1) and 51 % (N70: 70 kg N ha-1 year-1) more productive than the average of monocultures, and the highest yielding mixture was 36 % (N20) and 39 % (N70) more productive than the highest yielding monoculture. Importantly, diversity effects were also evident at low relative abundances of either species group, grasses or legumes in the mixture. Mixtures suppressed weeds significantly better than monocultures consistently during the course of the experiment at all N levels. Conclusions:The results show that even in the less productive agricultural systems in the cool maritime regions grass-legume mixtures can contribute substantially and persistently to a more sustainable agriculture. Positive grass-legume interactions suggest that symbiotic N2 fixation is maintained even under these marginal conditions, provided that adapted species and cultivars are used.

Dataset Information

The potential of UAV-borne spectral and textural information for predicting aboveground biomass and N fixation in legume-grass mixtures.

Publications

The potential of UAV-borne spectral and textural information for predicting aboveground biomass and N fixation in legume-grass mixtures.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets