Abstract Accurate and timely identification of pollution sources is the core of water-pollution emergency management. We propose a multimodal spatiotemporal synergy network that integrates Internet of Things sensor networks, Unmanned Aerial Vehicle aerial imagery, and Geographic Information System data within a Convolutional Neural Network-Gated Recurrent Unit-squeeze-and-excitation-You Only Look Once version 5 framework capable of delivering command-ready information within 10 h after a pollution event. The system simultaneously ingests hourly sensor data on water-quality parameters and 0.3 m resolution aerial images; an adaptive attention module recalibrates channel-wise weights, cutting the mean absolute error of pollutant-concentration prediction to 0.008 mg L − 1 and confining pollution-source localization error to within 300 m. A web-based visualization interface outputs ranked pollution hotspots and targeted inspection lists whose spatial agreement with authority-verified source locations reaches 96%. Diffusion-path reconstruction accuracy improves by 18.3% over conventional Long Short-Term Memory, and decision-response time is shortened from the usual 30 h to 10 h, a 67% reduction. The framework can be transferred to other basins with minor parameter tuning, strengthening timely response and adaptive management of sudden pollution incidents.
Forum papers are thought-provoking opinion pieces or essays founded in fact, sometimes containing speculation, on a civil engineering topic of general interest and relevance to the readership of the journal. The views expressed in this Forum article do not necessarily reflect the views of ASCE or the Editorial Board of the journal.
Abstract The interplay of population growth, climate change, and urbanization poses significant risks to the water–energy–food (WEF) nexus. This study investigates the security challenges and optimization strategies of the WEF nexus from 2015 to 2022 in China’s Yellow River Basin, a critical production base facing severe water constraints. A water footprint analysis reveals pronounced spatial inequalities, characterized by increasing water consumption for energy and declining use for food. Although the overall nexus security remains relatively stable, water resources, as represented by blue water availability and sectoral demand, inherently pose the greatest risk to regional stability. A nonlinear programming model, solved by sequential quadratic programming (SQP) following Monte Carlo-based initial-point screening, produces two optimization schemes—Nash and Rawlsian–Nash—to enhance basin security. Both strategies suggest reallocating water resources from the agricultural to the energy sector. Specifically, the Nash scheme produces a mean annual percentage change of + 7.18 % in the WEF nexus security index, whereas the equity-prioritizing Rawlsian–Nash scheme lowers overall WEF nexus security while producing a mean annual percentage change of + 0.69 % in the water resources security index. By combining water footprint analysis with equity-constrained optimization, this research provides a quantitative framework for balancing resource efficiency and sectoral security in water-scarce regions.
Abstract Lowndes County, Alabama, has struggled with inadequate wastewater management exacerbated by low population density, high rates of poverty, and suboptimal soil conditions prevalent throughout the Black Belt region. Steps are being taken to develop solutions, but a challenge in wastewater infrastructure planning is identifying the optimal number, location, and type of wastewater treatment systems (centralized, cluster, or onsite). Thus, the objectives of this research were to utilize a spatial optimization model, i.e., the sustainable infrastructure network planning model (SNIP), to determine the cost-optimal layout of wastewater treatment infrastructure for Lowndes County, Alabama, and assess how model results compare to existing technical assistance and proposed infrastructure improvement efforts in the town of White Hall (located in Lowndes County, AL). SNIP, created by Eggimann et al. (2015), minimizes the total wastewater system costs and requires only three input datasets: buildings, topography, and the street network. Overall, more centralized infrastructure, such as wastewater treatment plants or cluster wastewater treatment systems, is more cost optimal compared to the current heavy reliance on onsite wastewater treatment systems. Output geospatial data showing the location and capacity of wastewater treatment plants, sewer pipes, and pumps are particularly useful in communicating with stakeholders (e.g., residents, engineers, governing officials, and funders). Model outputs can guide household-level decision-making for the optimal wastewater treatment system (e.g., centralized, cluster, or onsite) not provided by current technical assistance. Ultimately, wastewater infrastructure planning requires consideration of local social, environmental, political, and economic dynamics, and this accessible tool can help communities quickly develop cost-optimal design options.
Abstract The expansion of urban water supply networks has exacerbated leakage issues, necessitating prompt assessment and optimization of network operations. To address the limitations of traditional steady-state hydraulic analysis, this study proposes an integrated leak-state identification framework combining transient pressure prediction and pattern recognition. A hybrid model was developed to predict instantaneous pressure variations by integrating convolutional neural networks (CNNs), long short-term memory (LSTM), and an attention mechanism. Given laboratory normal and leakage conditions, the CNN-LSTM-Attention model achieved mean absolute error (MAE) values of 0.007815 ± 0.000283 kPa and 0.005345 ± 0.000324 kPa , root mean square error (RMSE) values of 0.008450 ± 0.000281 kPa and 0.005457 ± 0.000321 kPa , and coefficient of determination ( R 2 ) values of 0.95961±0.00265 and 0.93274±0.00776, respectively. The proposed model outperformed CNN, LSTM, bidirectional long short-term memory (BiLSTM), and CNN-LSTM models. Subsequently, an optimized support vector machine (SVM) model was constructed for leak-state identification using transient monitored pressure and the CNN-LSTM-Attention predictions, achieving an accuracy of 97.50%, precision of 100.00%, recall of 94.74%, specificity of 100.00%, and F1-score of 97.30% in laboratory testing. Furthermore, the proposed framework was validated using data from a real-world water supply network. Given field conditions, the pressure prediction model maintained an R 2 of 0.91895, whereas the optimized SVM achieved accuracy of 92.50% and an F1-score of 91.89%. Although model performance decreased due to operational variability and more complex hydraulic conditions, the framework still demonstrated feasible pressure prediction and leak-state identification capability given monitored field conditions.
