Enabling CMF estimation in data-constrained scenarios: A semantic-encoding knowledge mining model.

Availability of more accurate Crash Modification Factors (CMFs) is crucial for evaluating the effectiveness of various road safety treatments and prioritizing infrastructure investment accordingly. While customized study for each countermeasure scenario is desired, the conventional CMF estimation approaches rely heavily on the availability of crash data at specific sites. This dependency may hinder the development of CMFs when it is impractical to collect data for recent implementations. Additionally, the transferability of CMF knowledge faces challenges, as the intrinsic similarities between different safety countermeasure scenarios are not fully explored. Aiming to fill these gaps, this study introduces a novel knowledge-mining framework for CMF prediction. This framework delves into the connections of existing countermeasure scenarios and reduces the reliance of CMF estimation on crash data availability and manual data collection. Specifically, it draws inspiration from human comprehension processes and introduces advanced Natural Language Processing (NLP) techniques to extract intricate variations and patterns from existing CMF knowledge. It effectively encodes unstructured countermeasure scenarios into machine-readable representations and models the complex relationships between scenarios and CMF values. This new data-driven framework provides a cost-effective and adaptable solution that complements the case-specific approaches for CMF estimation, which is particularly beneficial when availability of crash data imposes constraints. Experimental validation using real-world CMF Clearinghouse data demonstrates the effectiveness of this new approach, which shows significant accuracy improvements compared to the baseline methods. This approach provides insights into new possibilities of harnessing accumulated transportation knowledge in various applications.

Functional differentiation determines the molecular basis of the symbiotic lifestyle of Ca. Nanohaloarchaeota.

BACKGROUND: Candidatus Nanohaloarchaeota, an archaeal phylum within the DPANN superphylum, is characterized by limited metabolic capabilities and limited phylogenetic diversity and until recently has been considered to exclusively inhabit hypersaline environments due to an obligate association with Halobacteria. Aside from hypersaline environments, Ca. Nanohaloarchaeota can also have been discovered from deep-subsurface marine sediments. RESULTS: Three metagenome-assembled genomes (MAGs) representing a new order within the Ca. Nanohaloarchaeota were reconstructed from a stratified salt crust and proposed to represent a novel order, Nucleotidisoterales. Genomic features reveal them to be anaerobes capable of catabolizing nucleotides by coupling nucleotide salvage pathways with lower glycolysis to yield free energy. Comparative genomics demonstrated that these and other Ca. Nanohaloarchaeota inhabiting saline habitats use a "salt-in" strategy to maintain osmotic pressure based on the high proportion of acidic amino acids. In contrast, previously described Ca. Nanohaloarchaeota MAGs from geothermal environments were enriched with basic amino acids to counter heat stress. Evolutionary history reconstruction revealed that functional differentiation of energy conservation strategies drove diversification within Ca. Nanohaloarchaeota, further leading to shifts in the catabolic strategy from nucleotide degradation within deeper lineages to polysaccharide degradation within shallow lineages. CONCLUSIONS: This study provides deeper insight into the ecological functions and evolution of the expanded phylum Ca. Nanohaloarchaeota and further advances our understanding on the functional and genetic associations between potential symbionts and hosts. Video Abstract.

A hybrid model for spatiotemporal forecasting of PM2.5 based on graph convolutional neural network and long short-term memory.

Increasing availability of data related to air quality from ground monitoring stations has provided the chance for data mining researchers to propose sophisticated models for predicting the concentrations of different air pollutants. In this paper, we proposed a hybrid model based on deep learning methods that integrates Graph Convolutional networks and Long Short-Term Memory networks (GC-LSTM) to model and forecast the spatiotemporal variation of PM2.5 concentrations. Specifically, historical observations on different stations are constructed as spatiotemporal graph series, and historical air quality variables, meteorological factors, spatial terms and temporal attributes are defined as graph signals. To evaluate the performance of the GC-LSTM, we compared our results with several state-of-the-art methods in different time intervals. Based on the results, our GC-LSTM model achieved the best performance for predictions. Moreover, evaluations of recall rate (68.45%), false alarm rate (4.65%) (both of threshold: 115 µg/m3) and correlation coefficient R2 (0.72) for 72-hour predictions also verify the feasibility of our proposed model. This methodology can be used for concentration forecasting of different air pollutants in future.