Long-term Reservoir Inflow Forecasts: Enhanced Water Supply and Inflow Volume Accuracy Using Deep Learning

2021 ◽  
pp. 126676
Author(s):  
Zachary C. Herbert ◽  
Zeeshan Asghar ◽  
Carlos Oroza
Keyword(s):  
Deep Learning ◽  
Water Supply ◽  
Reservoir Inflow

scholarly journals Domain randomization-enhanced deep learning models for bird detection

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Xin Mao ◽  
Jun Kang Chow ◽  
Pin Siang Tan ◽  
Kuan-fu Liu ◽  
Jimmy Wu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Continuous Monitoring ◽  
Bird Species ◽  
Training Data ◽  
Learning Models ◽  
Fine Grained ◽  
Bird Detection ◽  
Relationship Of ◽  
The Relationship

AbstractAutomatic bird detection in ornithological analyses is limited by the accuracy of existing models, due to the lack of training data and the difficulties in extracting the fine-grained features required to distinguish bird species. Here we apply the domain randomization strategy to enhance the accuracy of the deep learning models in bird detection. Trained with virtual birds of sufficient variations in different environments, the model tends to focus on the fine-grained features of birds and achieves higher accuracies. Based on the 100 terabytes of 2-month continuous monitoring data of egrets, our results cover the findings using conventional manual observations, e.g., vertical stratification of egrets according to body size, and also open up opportunities of long-term bird surveys requiring intensive monitoring that is impractical using conventional methods, e.g., the weather influences on egrets, and the relationship of the migration schedules between the great egrets and little egrets.

scholarly journals Long-Term Data Traffic Forecasting for Network Dimensioning in LTE with Short Time Series

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1151
Author(s):  
Carolina Gijón ◽  
Matías Toril ◽  
Salvador Luna-Ramírez ◽  
María Luisa Marí-Altozano ◽  
José María Ruiz-Avilés
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Time Series Analysis ◽  
Data Traffic ◽  
Medium Term ◽  
Short Term ◽  
Traffic Forecasting ◽  
Series Analysis ◽  
Radio Planning

Network dimensioning is a critical task in current mobile networks, as any failure in this process leads to degraded user experience or unnecessary upgrades of network resources. For this purpose, radio planning tools often predict monthly busy-hour data traffic to detect capacity bottlenecks in advance. Supervised Learning (SL) arises as a promising solution to improve predictions obtained with legacy approaches. Previous works have shown that deep learning outperforms classical time series analysis when predicting data traffic in cellular networks in the short term (seconds/minutes) and medium term (hours/days) from long historical data series. However, long-term forecasting (several months horizon) performed in radio planning tools relies on short and noisy time series, thus requiring a separate analysis. In this work, we present the first study comparing SL and time series analysis approaches to predict monthly busy-hour data traffic on a cell basis in a live LTE network. To this end, an extensive dataset is collected, comprising data traffic per cell for a whole country during 30 months. The considered methods include Random Forest, different Neural Networks, Support Vector Regression, Seasonal Auto Regressive Integrated Moving Average and Additive Holt–Winters. Results show that SL models outperform time series approaches, while reducing data storage capacity requirements. More importantly, unlike in short-term and medium-term traffic forecasting, non-deep SL approaches are competitive with deep learning while being more computationally efficient.

scholarly journals Development and Verification of the Available Number of Water Intake Days in Ungauged Local Water Source Using the SWAT Model and Flow Recession Curves

Water ◽  
2021 ◽  
Vol 13 (11) ◽  
pp. 1511
Author(s):  
Jung-Ryel Choi ◽  
Il-Moon Chung ◽  
Se-Jin Jeung ◽  
Kyung-Su Choo ◽  
Cheong-Hyeon Oh ◽  
...  
Keyword(s):  
Water Supply ◽  
Water Intake ◽  
Water Resource Management ◽  
Assessment Tool ◽  
Swat Model ◽  
High Water ◽  
Coefficient Of Determination ◽  
Severe Drought ◽  
Regional Government

Climate change significantly affects water supply availability due to changes in the magnitude and seasonality of runoff and severe drought events. In the case of Korea, despite high water supply ratio, more populations have continued to suffer from restricted regional water supplies. Though Korea enacted the Long-Term Comprehensive Water Resources Plan, a field survey revealed that the regional government organizations limitedly utilized their drought-related data. These limitations present a need for a system that provides a more intuitive drought review, enabling a more prompt response. Thus, this study presents a rating curve for the available number of water intake days per flow, and reviews and calibrates the Soil and Water Assessment Tool (SWAT) model mediators, and found that the coefficient of determination, Nash–Sutcliffe efficiency (NSE), and percent bias (PBIAS) from 2007 to 2011 were at 0.92, 0.84, and 7.2%, respectively, which were “very good” levels. The flow recession curve was proposed after calculating the daily long-term flow and extracted the flow recession trends during days without precipitation. In addition, the SWAT model’s flow data enables the quantitative evaluations of the number of available water intake days without precipitation because of the high hit rate when comparing the available number of water intake days with the limited water supply period near the study watershed. Thus, this study can improve drought response and water resource management plans.

Spoken content retrieval and understanding using deep learning

Impact ◽  
2021 ◽  
Vol 2021 (1) ◽  
pp. 9-11
Author(s):  
Lin-shan Lee
Keyword(s):  
Deep Learning ◽  
Scientific Community ◽  
Online Courses ◽  
The Internet ◽  
Human Voice ◽  
Content Retrieval ◽  
Youtube Videos ◽  
Access Information ◽  
Teaching Machines

Spoken content refers to all content over the Internet which includes human voice, essentially those in multimedia, such As YouTube videos and online courses. Today such content is retrieved via Google primarily based on human-generated text labels, because Google can only retrieve text over the Internet. The goal of this project is to produce technologies to retrieve accurately and efficiently such spoken content directly based on the included audio sounds instead of text labels, because machines today can listen to human voice just as they can read the text. The long term goal is to create a spoken version of Google, which may revolutionize the ways in which humans access information and improve their knowledge. Professor Lin-shan Lee at National Taiwan University is leading this project. He has been a distinguished leader in the global scientific community for the area of teaching machines to speak and listen to human voice for many years.

scholarly journals Water Woes in Zimbabwe’s Urban Areas in the Middist Of Plenty: 2000 -Present

2012 ◽  
Vol 1 (2) ◽  
pp. 151 ◽  
Author(s):  
Enock C. Makwara
Keyword(s):  
Waste Management ◽  
Water Supply ◽  
Urban Area ◽  
Urban Areas ◽  
Service Failure ◽  
Urban Residents ◽  
Contaminated Water ◽  
Recent Outbreak

Zimbabwe’s urban areas are choking under the weight of over-crowdedness amidstdilapidated infrastructure that is characterised by constant service failure. The water andsewer systems of the country’s major urban centres are on the verge of collapse, thusputting millions of people in danger of consuming contaminated water, including thatfrom underground sources. Waste management and water supply problems manifestthemselves as challenges bedevilling many an urban area in the country. The quality andquantity of water supplied in Zimbabwe’s urban centres has plummeted in recent yearsand has assumed crisis proportions owing to the difficult economic situation and otherchallenges faced by the country. The situation is desperate and dire, as is evidenced by thepoor quality of delivered water, severe water rationing and the outbreak of water-bornediseases in the urban areas dotted across the country. The situation demands and dictatesthat solutions be proffered as a matter of urgency.The recent outbreak of epidemics hasbeen blamed on lack of access to safe water and poor sanitation, two crucial factors incontrolling the spread of diseases. An overly bureaucratic environment, where decisionsand processes take longer, makes life complicated for poor urban residents. Such ascenario motivated the researchers to examine the problem with a view to suggest waysand means of intervening to mitigate and resolve the problem. It emerged from thefindings that the problem is multifaceted in nature, hence a whole range of measures needto be adopted if a long-term solution is to be provided.

Corn and Velvetleaf (Abutilon theophrasti) Growth and Transpiration Efficiency under Varying Water Supply

Weed Science ◽  
2016 ◽  
Vol 64 (4) ◽  
pp. 596-604
Author(s):  
Logan G. Vaughn ◽  
Mark L. Bernards ◽  
Timothy J. Arkebauer ◽  
John L. Lindquist
Keyword(s):  
Water Supply ◽  
Soil Water ◽  
Leaf Area ◽  
Biomass Accumulation ◽  
Transpiration Efficiency ◽  
Plastic Bags ◽  
Comparative Response ◽  
Competitive Success ◽  
Daily Transpiration

The supply of soil resources is critical for the establishment and long-term competitive success of a plant species. Although there is considerable research on the effects of water supply on crop growth and productivity, there is little published research on the comparative response of crops and weeds to limiting soil water supply. The objective of this research was to determine the growth and transpiration efficiency of corn and velvetleaf at three levels of water supply. One corn or velvetleaf plant was grown in a large pot lined with plastic bags. When seedlings reached 10 cm, bags were sealed around the base of the plant, so the only water loss was from transpiration. Daily transpiration was measured by weighing the pots at the same time each day. The experiment was conducted in the fall of 2007 and in the spring of 2008. Four replicates of each species–water treatment were harvested periodically to determine biomass accumulation and leaf area. The relationship between cumulative aboveground biomass and water transpired was described using a linear function in which the slope defined the transpiration efficiency (TE). Corn TE was greater than velvetleaf TE in all treatments during both trials. In the fall trial, corn TE was 6.3 g kg–1, 47% greater than that of velvetleaf TE. In the spring trial, TEs of both species were lower overall, and corn TE increased with declining water supply. Corn produced more biomass and leaf area than velvetleaf did at all water-supply levels. Velvetleaf partitioned more biomass to roots compared with shoots during early growth than corn did. The ability of corn to generate more leaf area and its investment in a greater proportion of biomass into root growth at all levels of water supply may enable it to more-effectively avoid velvetleaf interference under all levels of soil-water supply.

Microbiological requirements for safe drinking water production at a large river impacted by human wastewater: a scenario analysis

2021 ◽  
Author(s):  
Katalin Demeter ◽  
Julia Derx ◽  
Jürgen Komma ◽  
Juraj Parajka ◽  
Jack Schijven ◽  
...  
Keyword(s):  
Climate Change ◽  
Drinking Water ◽  
Wastewater Treatment ◽  
Population Growth ◽  
Water Supply ◽  
Large River ◽  
Wastewater Management ◽  
Reference Scenario ◽  
Safe Drinking Water

<p><strong>Background</strong>: Rivers are important sources for drinking water supply, however, they are often impacted by wastewater discharges from wastewater treatment plants (WWTP) and combined sewer overflows (CSO). Reduction of the faecal pollution burden is possible through enhanced wastewater treatment or prevention of CSOs. Few methodological efforts have been made so far to investigate how these measures would affect the long-term treatment requirements for microbiologically safe drinking water supply under future changes.</p><p><strong>Objectives</strong>: This study aimed to apply a new integrative approach to decipher the interplay between the effects of future changes and wastewater management measures on the required treatment of river water to produce safe drinking water. We investigated scenarios of climate change and population growth, in combination with different wastewater management scenarios (i.e., no upgrades and upgrades at WWTPs, CSOs, and both). To the best of our knowledge, this is the first study to investigate this interplay. We focussed on the viral index pathogens norovirus and enterovirus and made a cross-comparison with a bacterial and a protozoan reference pathogen (Campylobacter and Cryptosporidium).</p><p><strong>Methods</strong>: We significantly extended QMRAcatch (v1.0 Python), a probabilistic-deterministic model that combines virus fate and transport modelling in the river with quantitative microbial risk assessment (QMRA). To investigate the impact of climatic changes, we used a conceptual semi-distributed hydrological model and regional climate model outputs to simulate river discharges for the period 2035 – 2049. We assumed that population growth leads to a corresponding increase in WWTP discharges. QMRAcatch was successfully calibrated and validated based on a four-year dataset of a human-associated genetic MST marker and enterovirus. The study site was the Danube in Vienna, Austria.</p><p><strong>Results</strong>: In the reference scenario, approx. 98% of the enterovirus and norovirus loads at the study site (median: 10<sup>10</sup> and 10<sup>13</sup> N/d) originated from WWTP effluent, while the remainder was via CSO events. The required log reduction value (LRV) to produce safe drinking water was 6.3 and 8.4 log<sub>10</sub> for enterovirus and norovirus. Future changes in population size, river flows and CSO events did not affect these treatment requirements, and neither did the prevention of CSOs. In contrast, in the scenario of enhanced wastewater treatment, which showed lower LRVs by 2.0 and 1.3 log<sub>10</sub>, climate-change-driven increases in CSO events had a considerable impact on the treatment requirements, as they affected the main pollution source. Preventing CSOs and installing enhanced treatment at the WWTPs together had the most significant positive effect with a reduction of LRVs by 3.9 and 3.8 log<sub>10</sub> compared to the reference scenario.</p><p><strong>Conclusions</strong>: The integrative modelling approach was successfully realised. The simultaneous consideration of source apportionment and concentrations of the reference pathogens were found crucial to understand the interplay among the effects of climate change, population growth and pollution control measures. The approach was demonstrated for a study site representing a large river impacted by WWTP and CSO discharges, but is applicable at other sites to support long term water safety planning.</p>

Long Term Predictions of NO2 Average Values via Deep Learning

2021 ◽  
pp. 595-610
Author(s):  
Pierfrancesco Bellini ◽  
Stefano Bilotta ◽  
Daniele Cenni ◽  
Enrico Collini ◽  
Paolo Nesi ◽  
...  
Keyword(s):  
Deep Learning
Sign in / Sign up

Export Citation Format

Share Document