A hybrid Wavelet-CNN-LSTM deep learning model for short-term urban water demand forecasting

● A novel deep learning framework for short-term water demand forecasting. ● Model prediction accuracy outperforms other traditional deep learning models. ● Wavelet multi-resolution analysis automatically extracts key water demand features. ● An analysis is performed to explain the improved mechanism of the proposed method. Short-term water demand forecasting provides guidance on real-time water allocation in the water supply network, which help water utilities reduce energy cost and avoid potential accidents. Although a variety of methods have been proposed to improve forecast accuracy, it is still difficult for statistical models to learn the periodic patterns due to the chaotic nature of the water demand data with high temporal resolution. To overcome this issue from the perspective of improving data predictability, we proposed a hybrid Wavelet-CNN-LSTM model, that combines time-frequency decomposition characteristics of Wavelet Multi-Resolution Analysis (MRA) and implement it into an advanced deep learning model, CNN-LSTM. Four models - ANN, Conv1D, LSTM, GRUN - are used to compare with Wavelet-CNN-LSTM, and the results show that Wavelet-CNN-LSTM outperforms the other models both in single-step and multi-steps prediction. Besides, further mechanistic analysis revealed that MRA produce significant effect on improving model accuracy.     

Mitigating microbiological risks of potential pathogens carrying antibiotic resistance genes and virulence factors in receiving rivers: Benefits of wastewater treatment plant upgrade

● Abundance of MAGs carrying ARG-VF pairs unchanged in rivers after WWTP upgrade. ● Upgrade of WWTPs significantly reduced diversity of pathogenic genera in rivers. ● Upgrade of WWTPs reduced most VF (ARG) types carried by potential pathogens in rivers. ● Upgrade of WWTPs narrowed the pathogenic host ranges of ARGs and VFs in rivers. Wastewater treatment plants (WWTPs) with additional tertiary ultrafiltration membranes and ozonation treatment can improve water quality in receiving rivers. However, the impacts of WWTP upgrade (WWTP-UP) on pathogens carrying antibiotic resistance genes (ARGs) and virulence factors (VFs) in rivers remain poorly understood. In this study, ARGs, VFs, and their pathogenic hosts were investigated in three rivers impacted by large-scale WWTP-UP. A five-year sampling campaign covered the periods before and after WWTP-UP. Results showed that the abundance of total metagenome-assembled genomes (MAGs) containing both ARGs and VFs in receiving rivers did not decrease substantially after WWTP-UP, but the abundance of MAGs belonging to pathogenic genera that contain both ARGs and VFs (abbreviated as PAVs) declined markedly. Genome-resolved metagenomics further revealed that WWTP-UP not only reduced most types of VFs and ARGs in PAVs, but also effectively eliminated efflux pump and nutritional VFs carried by PAVs in receiving rivers. WWTP-UP narrowed the pathogenic host ranges of ARGs and VFs and mitigated the co-occurrence of ARGs and VFs in receiving rivers. These findings underline the importance of WWTP-UP for the alleviation of pathogens containing both ARGs and VFs in receiving rivers.     

BP神经网络法预测唐山市需水量

需水量预测研究已成为当前水资源规划与管理研究中的重要课题之一.本文设定不同的神经网络运行次数,根据预测结果进行误差分析,BP神经网络在运行5 000次时,具有高度的可信度和可行性.应用5 000次运行次数的BP神经网络模型对唐山市规划水平年的需水量进行预测.最后引入人均综合用水量概念,结果表明,预测结果在理论上和实际上都具有可行性.     

The Power of Legitimation: The Role of Expert Networks in Global Environmental Governance

As part of the debate on the legitimacy of governance networks in global environmental politics, this article investigates the conditions under which policy solutions can be transferred worldwide as a result of a particular type of interaction within transnational expert networks and technical committees. To this end, the article hypothesises that policy solutions can be legitimised in governance networks meeting four cumulative criteria: participation, flexibility, horizontality and inclusiveness. This hypothesis is then tested by means of two heuristic case studies dedicated to the worldwide transfer of environmental standards via United Nations specialized agencies. The empirical work partly strengthens the validity of the hypothesis but also underscores the limits of legitimation strategies in the face of strong heterogeneity of interests. In such cases, environmental policy networks may adopt fairly “vertical” features and resort to classical bargaining and constraint strategies whereby compromises are exchanged and power asymmetries are mobilised.     

Hurricanes and hegemony: A qualitative analysis of micro-level climate change denial discourses

The climate change countermovement and its program of climate change denial have been well documented and studied. However, individual rationales for rejecting climate science remain under-studied. Twitter data related to Hurricane Sandy in 2012 are used to understand why individuals reject the orthodox climate consensus, using a summative content analysis of climate change denial discourses. Three major discourses are discovered: rejecting climate science because climate science is a conspiracy favoring growth of government; opposing renewable energy and energy taxation; and expressing fear of governmental abuse of power. Importantly, each discourse expressed certainty that climate science itself was a wholesale fraud; the denial discourses themselves focused far more on climate politics than on science.     

Using Social Network Analysis to examine the role that institutional integration plays in community-based adaptive capacity to climate change in Caribbean small island communities

Remote island communities in the Caribbean are known to be disproportionately vulnerable to the impacts of climate change. As a result, there is a need to better understand the factors that contribute to increasing local-scale adaptive capacity through large-scale adaptation projects. While it has been argued that strong institutional networks are highly influential in a community’s ability to leverage funds and to implement tailored adaptation projects, limited empirical research has been undertaken. Social Network Analysis was used to retrospectively evaluate the importance of institutional integration for enhancing adaptive capacity in the small island community of Paget Farm in St. Vincent and the Grenadines. Paget Farm successfully adapted to a lack of fresh water through the implementation of a funded solar-powered desalination plant – and as a result the community represents an ideal case study for analysis. Results reveal that while the level of vertical integration varied throughout the temporal phases of the adaptation project, horizontal integration was consistently low. These findings suggest that high integration between institutions may not be required during all project phases in order to ensure success and that more consistent rather than high levels of integration between sectors may be more meaningful for enhancing adaptive capacity.     

Evidence for the dominance of indirect effects in 50 trophic ecosystem networks

Indirect effects are powerful influences in ecosystems that may maintain species diversity and alter apparent relationships between species in surprising ways. Here, we applied network environ analysis to 50 empirically-based trophic ecosystem models to test the hypothesis that indirect flows dominate direct flows in ecosystem networks. Further, we used Monte Carlo based perturbations to investigate the robustness of these results to potential error in the underlying data. To explain our findings, we further investigated the importance of the microbial food web in recycling energy-matter using components of the Finn Cycling Index and analysis of environ centrality. We found that indirect flows dominate direct flows in 37/50 (74.0%) models. This increases to 31/35 (88.5%) models when we consider only models that have cycling structure and a representation of the microbial food web. The uncertainty analysis reveals that there is less error in the I/D values than the ±5% error introduced into the models, suggesting the results are robust to uncertainty. Our results show that the microbial food web mediates a substantial percentage of cycling in some systems (median = 30.2%), but its role is highly variable in these models, in agreement with the literature. Our results, combined with previous work, strongly suggest that indirect effects are dominant components of activity in ecosystems.     

Equivalence of the realized input and output oriented indirect effects metrics in Ecological Network Analysis

A new understanding of the consequences of how ecosystem elements are interconnected is emerging from the development and application of Ecological Network Analysis. The relative importance of indirect effects is central to this understanding, and the ratio of indirect flow to direct flow (I/D) is one indicator of their importance. Two methods have been proposed for calculating this indicator. The unit approach shows what would happen if each system member had a unit input or output, while the realized technique determines the ratio using the observed system inputs or outputs. When using the unit method, the input oriented and output oriented ratios can be different, potentially leading to conflicting results. However, we show that the input and output oriented I/D ratios are identical using the realized method when the system is at steady state. This work is a step in the maturation of Ecological Network Analysis that will let it be more readily testable empirically and ultimately more useful for environmental assessment and management.     

Disaster management and mitigation: the telecommunications infrastructure

Among the most typical consequences of disasters is the near or complete collapse of terrestrial telecommunications infrastructures (especially the distribution network–the 'last mile') and their concomitant unavailability to the rescuers and the higher echelons of mitigation teams. Even when such damage does not take place, the communications overload/congestion resulting from significantly elevated traffic generated by affected residents can be highly disturbing. The paper proposes innovative remedies to the telecommunications difficulties in disaster struck regions. The offered solutions are network-centric operations-cap able, and can be employed in management of disasters of any magnitude (local to national or international). Their implementation provide ground rescue teams (such as law enforcement, firemen, healthcare personnel, civilian authorities) with tactical connectivity among themselves, and, through the Next Generation Network backbone, ensure the essential bidirectional free flow of information and distribution of Actionable Knowledge among ground units, command/control centres, and civilian and military agencies participating in the rescue effort.     

Measurements of Wastewater True Color by 4/6 Wavelength Methods and Artificial Neural Network

The ADMI (American Dye Manufactures’ Institute) 3 and 31 wavelength (WL) methods are the most popular measurements of the wastewater true color. However, significantly different measured results were found between the ADMI 3 and 31 WL methods for the same sample. This finding indicates that the ADMI 3 and 31 WL values should not be directly substituted for each other, resulting in the incomparability of these two color values. An innovative calculation using the Back-Propagation Neural Network (BPN) was therefore proposed to replace the original calculation method proposed in Standard Method. The BPN-calculated ADMI 3 WL values were found to be very close to the corresponding measured ADMI 31 WL values. Additionally, for more accurate measurement of the true color, new measurement methods containing 4 and 6 wavelengths were proposed and cooperated with the BPN calculation model. The new approaches performed very accuracy measured results of the wastewater true color. Finally, the trained BPN calculation models were built to be applied to measure the true color of real textile samples and also performed very good measured results.