Coupled effects of elevated CO2 and biochar on microbial communities of vegetated soil.

Soil microbial communities are important for plant growth and establishing healthy ecosystems. Although biochar is widely adopted as a sustainable fertilizer, its influence on soil ecological functions is still unclear, especially under climate change such as elevated carbon dioxide concentration (eCO2). This study explores the coupled effects between eCO2 and biochar on microbial communities in soil planted with tree seedlings of Schefflera heptaphylla. Root characteristics and soil microbial communities were examined and interpreted with statistical analysis. Results show that biochar application at ambient carbon dioxide concentration (aCO2) always improves plant growth, which is further promoted under eCO2. Similarly, ß-glucosidase, urease and phosphatase activities are enhanced by biochar at aCO2 (p < 0.05). In contrast, only urease activity increases with biochar added at eCO2 (p < 0.05). The beneficial effects of biochar on soil enzyme activities become less significant at eCO2. Depending on biochar type, biochar can increase bacterial diversity and fungal richness at aCO2. However, at eCO2, biochar does not significantly affect microbial richness (p > 0.05) while microbial diversity is reduced by peanut shell biochar (p < 0.05). Owing to better plant growth under biochar application and eCO2, plants are likely to become more dominant in specializing the microbial communities that are favourable to them. In such community, the abundance of Proteobacteria is the greatest and increases after biochar addition at eCO2. The most abundant fungus also shifts from Rozellomycota to Ascomycota and Basidiomycota. These microbes can improve soil fertility. Even though the microbial diversity is reduced, using biochar at eCO2 can further promote plant growth, which in turn enhances carbon sequestration. Thus, biochar application can be an effective strategy to facilitate ecological restoration under climate change and relieve the problem of eCO2.

Seismic Waveform Inversion Capability on Resource-Constrained Edge Devices.

Seismic full wave inversion (FWI) is a widely used non-linear seismic imaging method used to reconstruct subsurface velocity images, however it is time consuming, has high computational cost and depend heavily on human interaction. Recently, deep learning has accelerated it's use in several data-driven techniques, however most deep learning techniques suffer from overfitting and stability issues. In this work, we propose an edge computing-based data-driven inversion technique based on supervised deep convolutional neural network to accurately reconstruct the subsurface velocities. Deep learning based data-driven technique depends mostly on bulk data training. In this work, we train our deep convolutional neural network (DCN) (UNet and InversionNet) on the raw seismic data and their corresponding velocity models during the training phase to learn the non-linear mapping between the seismic data and velocity models. The trained network is then used to estimate the velocity models from new input seismic data during the prediction phase. The prediction phase is performed on a resource-constrained edge device such as Raspberry Pi. Raspberry Pi provides real-time and on-device computational power to execute the inference process. In addition, we demonstrate robustness of our models to perform inversion in the presence on noise by performing both noise-aware and no-noise training and feeding the resulting trained models with noise at different signal-to-noise (SNR) ratio values. We make great efforts to achieve very feasible inference times on the Raspberry Pi for both models. Specifically, the inference times per prediction for UNet and InversionNet models on Raspberry Pi were 22 and 4 s respectively whilst inference times for both models on the GPU were 2 and 18 s which are very comparable. Finally, we have designed a user-friendly interactive graphical user interface (GUI) to automate the model execution and inversion process on the Raspberry Pi.