scholarly journals Applying Cascade-Correlation Neural Networks to In-Fill Gaps in Mediterranean Daily Flow Data Series

Water ◽  
2019 ◽  
Vol 11 (8) ◽  
pp. 1691 ◽  
Author(s):  
Cristina Vega-Garcia ◽  
Mathieu Decuyper ◽  
Jorge Alcázar
Keyword(s):  
Neural Networks ◽  
Water Resources ◽  
Water Flow ◽  
General Rule ◽  
Hydrological Regime ◽  
Weather Data ◽  
Data Series ◽  
Flow Data ◽  
Cascade Correlation ◽  
Management Flow

The analyses of water resources availability and impacts are based on the study over time of meteorological and hydrological data trends. In order to perform those analyses properly, long records of continuous and reliable data are needed, but they are seldom available. Lack of records as in gaps or discontinuities in data series and quality issues are two of the main problems more often found in databases used for climate studies and water resources management. Flow data series from gauging stations are not an exception. Over the last 20 years, forecasting models based on artificial neural networks (ANNs) have been increasingly applied in many fields of natural resources, including hydrology. This paper discusses results obtained on the application of cascade-correlation ANN models to predict daily water flow using Julian day and rainfall data provided by nearby weather stations in the Ebro river watershed (Northeast Spain). Five unaltered gauging stations showing a rainfall-dominated hydrological regime were selected for the study. Daily flow and weather data series covered 30 years to encompass the high variability of Mediterranean environments. Models were then applied to the in-filling of existing gaps under different conditions related to the characteristics of the gaps (6 scenarios). Results showed that when short periods before and after the gap are considered, this is a useful approach, although no general rule applied to all stations and gaps investigated. Models for low-water-flow periods provided better results (r = 0.76–0.8).

scholarly journals Estimating surface water and vadose water resources for an ungauged inland catchment in Vietnam

2021 ◽  
Author(s):  
Liem Duy Nguyen ◽  
Phuong Dong Nguyen Dang ◽  
Loi Kim Nguyen
Keyword(s):  
Water Resources ◽  
Water Flow ◽  
Water Discharge ◽  
Water Storage ◽  
Green Water ◽  
Weather Data ◽  
Coefficient Of Determination ◽  
Blue Water ◽  
Time Step ◽  
Statistical Measures

Abstract This study aimed to assess water resources for the La Vi catchment, an ungauged inland basin in Vietnam. An Internet of Things-based automatic meteorological station has been installed in the catchment to record hourly weather data from 2016. By comparing water level observations with limited discharge measurements, discharges from November 2015 to February 2018 were calculated at Tan Hoa bridge using the slope-area method. The Soil and Water Assessment Tool was calibrated and validated for the wet season of 2015 and 2017, respectively, using the previously calculated water discharges. Statistical measures including Nash–Sutcliffe index, percent bias, and coefficient of determination indicated the satisfactory performance of the model in simulating water discharge on daily time step during both periods. The results of the water resources assessment in the catchment showed that the annual average of blue water flow, green water flow, and green water storage reached 1,596.50, 371.13, and 15.36 mm, respectively. The blue water flow reached a higher value in the center of the catchment. Meanwhile, the high-value areas of green water flow and green water storage were in the western upstream and the riverside downstream. These findings could provide a valuable scientific foundation for sustainable watershed management.

scholarly journals Dewpoint Temperature Prediction Using Artificial Neural Networks

2008 ◽  
Vol 47 (6) ◽  
pp. 1757-1769 ◽  
Author(s):  
D. B. Shank ◽  
G. Hoogenboom ◽  
R. W. McClendon
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Air Temperature ◽  
Heat Waves ◽  
Weather Data ◽  
Temperature Prediction ◽  
Related Data ◽  
Dewpoint Temperature ◽  
Artificial Neural ◽  
Selection Of

Abstract Dewpoint temperature, the temperature at which water vapor in the air will condense into liquid, can be useful in estimating frost, fog, snow, dew, evapotranspiration, and other meteorological variables. The goal of this study was to use artificial neural networks (ANNs) to predict dewpoint temperature from 1 to 12 h ahead using prior weather data as inputs. This study explores using three-layer backpropagation ANNs and weather data combined for three years from 20 locations in Georgia, United States, to develop general models for dewpoint temperature prediction anywhere within Georgia. Specific objectives included the selection of the important weather-related inputs, the setting of ANN parameters, and the selection of the duration of prior input data. An iterative search found that, in addition to dewpoint temperature, important weather-related ANN inputs included relative humidity, solar radiation, air temperature, wind speed, and vapor pressure. Experiments also showed that the best models included 60 nodes in the ANN hidden layer, a ±0.15 initial range for the ANN weights, a 0.35 ANN learning rate, and a duration of prior weather-related data used as inputs ranging from 6 to 30 h based on the lead time. The evaluation of the final models with weather data from 20 separate locations and for a different year showed that the 1-, 4-, 8-, and 12-h predictions had mean absolute errors (MAEs) of 0.550°, 1.234°, 1.799°, and 2.280°C, respectively. These final models predicted dewpoint temperature adequately using previously unseen weather data, including difficult freeze and heat stress extremes. These predictions are useful for decisions in agriculture because dewpoint temperature along with air temperature affects the intensity of freezes and heat waves, which can damage crops, equipment, and structures and can cause injury or death to animals and humans.

scholarly journals ANALISIS BANJIR KELURAHAN TANJUNG DUREN SELATAN

2020 ◽  
Vol 3 (3) ◽  
pp. 569
Author(s):  
Natanael Tadeus Sutanto ◽  
Wati Asriningsih Pranoto
Keyword(s):  
Water Resources ◽  
Natural Disasters ◽  
Water Flow ◽  
Channel Capacity ◽  
Rainfall Intensity ◽  
Chi Square ◽  
Channel Condition ◽  
Direct Measurements ◽  
Kolmogorov Smirnov ◽  
City Water

Flood is one of the natural disasters that occur due to various factors and causes many losses. Tanjung Duren Selatan village was recorded as having floods in January 2020. This research aims to determine the causes of the flood in the area as well as the solution. The data obtained were taken from BMKG, West Jakarta City Water Resources Department, and direct measurements in the review area. This research analyzed rainfall, channel capacity, channel condition dan topography in Tanjung Duren Selatan village. Rainfall is tested for data compatibility using Chi-Square and Kolmogorov-Smirnov methods. Rainfall intensity is calculated using the Mononobe formula. The capacity of the existing channels is analyzed using Manning formula that will be compared with the planned discharge calculated using Rasional method. The analysis included secondary channels and tertiary channels, based on the calculation of 8 of the 48 channels reviewed that were unable to accommodate the planned discharge. After the analysis, it can be concluded that the flooding in Tanjung Duren Selatan village was caused by the lack of existing channel capacity, contours, and rubbish that blocked the water flow. Floods that occurred on January 1, 2020 due to rainfall that occurred exceeded the planned rainfall.ABSTRAKBanjir merupakan salah satu bencana alam yang terjadi akibat berbagai faktor dan menimbulkan banyak kerugian. Di Kelurahan Tanjung Duren Selatan tercatat mengalami banjir pada bulan Januari 2020. Penelitian ini bertujuan untuk mengetahui faktor penyebab terjadinya banjir pada daerah tersebut serta solusinya. Data-data yang didapat diambil dari BMKG, Suku Dinas Sumber Daya Air Kota Jakarta Barat, serta pengukuran langsung di daerah tinjauan. Pada penelitian ini dianalisis curah hujan, kapasitas saluran, kondisi saluran, serta topografi di Kelurahan Tanjung Duren Selatan. Curah hujan di uji kecocokan datanya menggunakan metode Chi-Square dan Kolmogorov-Smirnov. Intensitas curah hujan di hitung menggunakan rumus Mononobe. Kapasitas saluran eksisting di analisis menggunakan rumus Manning yang akan dibandingkan dengan debit rencana yang dihitung menggunakan metode Rasional. Analisis yang dilakukan mencakup saluran sekunder dan saluran tersier, berdasarkan perhitungan 8 dari 48 saluran yang ditinjau tidak mampu menampung debit rencana. Setelah analisis dilakukan dapat disimpulkan bahwa banjir di Kelurahan Tanjung Duren Selatan disebabkan oleh kurangnya kapasitas saluran eksisting, kontur, serta sampah yang menghalangi aliran air. Banjir yang terjadi pada tanggal 1 Januari 2020 dikarenakan curah hujan yang terjadi melebihi curah hujan rencana.

scholarly journals Artificial Intelligence Techniques for river flow forecasting in the Seyhan River Catchment, Turkey

2007 ◽  
Vol 4 (3) ◽  
pp. 1369-1406 ◽  
Author(s):  
M. Firat
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
River Flow ◽  
Fuzzy Inference ◽  
Flow Data ◽  
Data Set ◽  
Inference System ◽  
Forecasting Models ◽  
River Flow Forecasting ◽  
Best Fit

Abstract. The use of Artificial Intelligence methods is becoming increasingly common in the modeling and forecasting of hydrological and water resource processes. In this study, applicability of Adaptive Neuro Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN) methods, Generalized Regression Neural Networks (GRNN) and Feed Forward Neural Networks (FFNN), for forecasting of daily river flow is investigated and the Seyhan catchment, located in the south of Turkey, is chosen as a case study. Totally, 5114 daily river flow data are obtained from river flow gauges station of Üçtepe (1818) on Seyhan River between the years 1986 and 2000. The data set are divided into three subgroups, training, testing and verification. The training and testing data set include totally 5114 daily river flow data and the number of verification data points is 731. The river flow forecasting models having various input structures are trained and tested to investigate the applicability of ANFIS and ANN methods. The results of ANFIS, GRNN and FFNN models for both training and testing are evaluated and the best fit forecasting model structure and method is determined according to criteria of performance evaluation. The best fit model is also trained and tested by traditional statistical methods and the performances of all models are compared in order to get more effective evaluation. Moreover ANFIS, GRNN and FFNN models are also verified by verification data set including 731 daily river flow data at the time period 1998–2000 and the results of models are compared. The results demonstrate that ANFIS model is superior to the GRNN and FFNN forecasting models, and ANFIS can be successfully applied and provide high accuracy and reliability for daily River flow forecasting.

scholarly journals Integrated assessment of impact of water resources of important river basins in Eastern India under projected climate conditions

2015 ◽  
Vol 17 (3) ◽  
pp. 594-606 ◽  
Keyword(s):  
Climate Change ◽  
Water Resources ◽  
Catchment Area ◽  
River Basins ◽  
Weather Data ◽  
Distributed Hydrological Model ◽  
Eastern India ◽  
Impact Of Climate Change ◽  
Daily Weather Data ◽  
The Impact

<div> <p>The impact of climate change on water resources through increased evaporation combined with regional changes in precipitation characteristics has the potential to affect mean runoff, frequency and intensity of floods and droughts, soil moisture and water supply for irrigation and hydroelectric power generation. The Ganga-Brahmaputra-Meghna (GBM) system is the largest in India with a catchment area of about 110Mha, which is more than 43% of the cumulative catchment area of all the major rivers in the country. The river Damodar is an important sub catchment of GBM basin and its three tributaries- the Bokaro, the Konar and the Barakar form one important tributary of the Bhagirathi-Hughli (a tributary of Ganga) in its lower reaches. The present study is an attempt to assess the impacts of climate change on water resources of the four important Eastern River Basins namely Damodar, Subarnarekha, Mahanadi and Ajoy, which have immense importance in industrial and agricultural scenarios in eastern India. A distributed hydrological model (HEC-HMS) has been used on the four river basins using HadRM2 daily weather data for the period from 2041 to 2060 to predict the impact of climate change on water resources of these river systems.&nbsp;</p> </div> <p>&nbsp;</p>

Long-term (1900-2100) Hydrometeorological and Snow Water Equivalent reconstructions in the French Southern Alps (Mercantour Natural Parc).

2021 ◽  
Author(s):  
Thibault Mathevet ◽  
Cyril Thébault ◽  
Jérôme Mansons ◽  
Matthieu Le Lay ◽  
Audrey Valery ◽  
...  
Keyword(s):  
Climate Change ◽  
Time Series ◽  
Water Resources ◽  
Air Temperature ◽  
Snow Water Equivalent ◽  
Hydrological Regime ◽  
Southern Alps ◽  
Snow Line ◽  
Snow Water

&lt;p&gt;The aim of this communication is to present a study on climate variability and change on snow water equivalent (SWE) and streamflow over the 1900-2100 period in a mediteranean and moutainuous area. &amp;#160;It is based on SWE and streamflow observations, past reconstructions (1900-2018) and future GIEC scenarii (up to 2100) of some snow courses and hydrological stations situated within the French Southern Alps (Mercantour Natural Parc). This has been conducted by EDF (French hydropower company) and Mercantour Natural Parc.&lt;/p&gt;&lt;p&gt;This issue became particularly important since a decade, especially in regions where snow variability had a large impact on water resources availability, poor snow conditions in ski resorts and artificial snow production or impacts on mountainous ecosystems (fauna and flora). As a water resources manager in French mountainuous regions, EDF developed and managed a large hydrometeorological network since 1950. A recent data rescue research allowed to digitize long term SWE manual measurements of a hundred of snow courses within the French Alps. EDF have been operating an automatic SWE sensors network, complementary to historical snow course network. Based on numerous SWE observations time-series and snow modelization (Garavaglia et al., 2017), continuous daily historical SWE time-series have been reconstructed within the 1950-2018 period. These reconstructions have been extented to 1900 using 20 CR (20&lt;sup&gt;th&lt;/sup&gt; century reanalyses by NOAA) reanalyses (ANATEM method, Kuentz et al., 2015) and up to 2100 using GIEC Climate Change scenarii (+4.5 W/m&amp;#178; and + 8.5 W/m&amp;#178; hypotheses). In the scope of this study, Mercantour Natural Parc is particularly interested by snow scenarii in the future and its impacts on their local flora and fauna.&lt;/p&gt;&lt;p&gt;Considering observations within Durance watershed and Mercantour region, this communication focuses on: (1) long term (1900-2018) analyses of variability and trend of hydrometeorological and snow variables (total precipitation, air temperature, snow water equivalent, snow line altitude, snow season length, streamflow regimes) , (2) long term variability of snow and hydrological regime of snow dominated watersheds and (3) future trends (2020 -2100) using GIEC Climate Change scenarii.&lt;/p&gt;&lt;p&gt;Comparing old period (1950-1984) to recent period (1984-2018), quantitative results within these regions roughly shows an increase of air temperature by 1.2 &amp;#176;C, an increase of snow line height by 200m, a reduction of SWE by 200 mm/year and a reduction of snow season duration by 15 days. Characterization of the increase of snow line height and SWE reduction are particularly important at a local and watershed scale. Then, this communication focuses on impacts on long-term time scales (2050, 2100). This long term change of snow dynamics within moutainuous regions both impacts (1) water resources management, (2) snow resorts and artificial snow production developments or (3) ecosystems dynamics.Connected to the evolution of snow seasonality, the impacts on hydrological regime and some streamflow signatures allow to characterize the possible evolution of water resources in this mediteranean and moutianuous region This study allowed to provide some local quantitative scenarii.&lt;/p&gt;

Methods for Multi-Step Time Series Forecasting Neural Networks

2011 ◽  
pp. 226-250 ◽  
Author(s):  
Douglas M. Kline
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Iterative Method ◽  
Time Series Forecasting ◽  
Independent Method ◽  
Data Series ◽  
Operating Characteristics ◽  
Quarterly Data ◽  
Joint Method

In this study, we examine two methods for Multi-Step forecasting with neural networks: the Joint Method and the Independent Method. A subset of the M-3 Competition quarterly data series is used for the study. The methods are compared to each other, to a neural network Iterative Method, and to a baseline de-trended de-seasonalized naïve forecast. The operating characteristics of the three methods are also examined. Our findings suggest that for longer forecast horizons the Joint Method performs better, while for short forecast horizons the Independent Method performs better. In addition, the Independent Method always performed at least as well as or better than the baseline naïve and neural network Iterative Methods.

Sign in / Sign up

Export Citation Format

Share Document