No abstract

Depending on interparticle structure and chemical behavior, fillers greatly influence the mechanical properties in rubber compounds. In this work, the influence of the filler-matrix versus filler-filler interaction on the mechanical properties of a silica nanoparticle-rubber composite was investigated. For this purpose, nanostructured microraspberry particles with different surface properties were designed and prepared using colloidal silica and two different kinds of silane agents, one coating agent (triethoxyoctylsilane, OCTEO) and one coupling agent (bis(triethoxysilylpropyl)tetrasulfide, Si69 TM ). In addition, the degree of silane coverage of the nanoparticles was adjusted in a precisely controlled way. This sophisticated particle system allowed for straightforward integration into the composite formation process while ensuring that a redispersion of the nanoparticles in the rubber matrix occurred during compounding. With this microraspberry particle system, it was possible to influence the mechanical properties by the degree of silane surface coverage on the nanoparticles while the filler content could be kept constant. The two silane systems were carefully compared and the impact of the particle/particle and the particle/rubber interactions with respect to the mechanical properties of the composite was studied. Ultimately, an overall picture of the influence of the type and the amount of silane on mechanical properties in silica-rubber composites could be obtained.

Deep learning is an emerging data analytic tool that can improve predictability, efficiency and sustainability in agriculture. With a bibliometric analysis of 156 articles, we show how deep learning methods have been applied in the context of sustainable agriculture. As a general publication trend, China and India are leading countries for publication, international collaboration is still minor. Deep learning has been popularly applied in the context of smart agriculture across scales for individual plant monitoring, field monitoring, field operation and robotics, predicting soil, water and climate conditions and landscape-level monitoring of land use and crop types. We identified that the potential of deep learning had been investigated mainly for predicting soil (abiotic), water, climate and vegetation dynamics, but ecological characteristics are critically understudied. We also highlight key themes that can be better addressed with deep learning for fostering sustainable agriculture: (i) including aboveand belowground ecological dynamics such as ecosystem functioning and ecotone, (ii) evaluating agricultural impacts on other ecosystems and (iii) incorporating the knowledge and opinions of domain experts and stakeholders into artificial intelligence. We propose that deep learning needs to go beyond automatic data analysis by integrating ecological and human knowledge to foster sustainable agriculture.

Deep learning applications in taxonomic classification for animals and plants from images have become popular, while those for microorganisms are still lagging behind. Our study investigated the potential of deep learning for the taxonomic classification of hundreds of filamentous fungi from colony images, which is typically a task that requires specialized knowledge. We isolated soil fungi, annotated their taxonomy using standard molecular barcode techniques, and took images of the fungal colonies grown in petri dishes (n = 606). We applied a convolutional neural network with multiple training approaches and model architectures to deal with some common issues in ecological datasets: small amounts of data, class imbalance, and hierarchically structured grouping. Model performance was overall low due mainly to the relatively small data set, class imbalance, and the high morphological plasticity exhibited by fungal colonies. However, our approach indicates that morphological features such as color, patchiness, and colony extension rate, could be used for the recognition of fungal colonies at higher taxonomic ranks (i.e., phylum, class, and order). Model explanation implies that image recognition characters appear at different positions within the colony (e.g., outer or inner hyphae), depending on the taxonomic resolution. Our study suggests the potential of deep learning applications for better understanding the taxonomy and ecology of filamentous fungi amenable to axenic culturing. Meanwhile, our study also highlights some technical challenges in deep learning image analysis in ecology, highlighting that the domain of applicability of these methods needs to be carefully considered.