scholarly journals Simulation of Titicaca Lake Water Level Fluctuations Using Hybrid Machine Learning Technique Integrated with Grey Wolf Optimizer Algorithm

Water ◽  
2020 ◽  
Vol 12 (11) ◽  
pp. 3015 ◽  
Author(s):  
Babak Mohammadi ◽  
Yiqing Guan ◽  
Pouya Aghelpour ◽  
Samad Emamgholizadeh ◽  
Ramiro Pillco Zolá ◽  
...  
Keyword(s):  
Random Forest ◽  
Water Level ◽  
Lake Water ◽  
Water Level Fluctuations ◽  
Support Vector ◽  
Grey Wolf Optimizer ◽  
Grey Wolf ◽  
Time Step ◽  
Lake Water Level ◽  
Input Variables

Lakes have an important role in storing water for drinking, producing hydroelectric power, and environmental, agricultural, and industrial uses. In order to optimize the use of lakes, precise prediction of the lake water level (LWL) is a main issue in water resources management. Due to the existence of nonlinear relations, uncertainty, and characteristics of the time series variables, the exact prediction of the lake water level is difficult. In this study the hybrid support vector regression (SVR) and the grey wolf algorithm (GWO) are used to predict lake water level fluctuations. Also, three types of data preprocessing methods, namely Principal component analysis, Random forest, and Relief algorithm were used for finding the best input variables for prediction LWL by the SVR and SVR-GWO models. Before the LWL simulation on monthly time step using the hybrid model, an evolutionary approach based on different monthly lags was conducted for determining the best mask of the input variables. Results showed that based on the random forest method, the best scenario of the inputs was Xt−1, Xt−2, Xt−3, Xt−4 for the SVR-GWO model. Also, the performance of the SVR-GWO model indicated that it could simulate the LWL with acceptable accuracy (with RMSE = 0.08 m, MAE = 0.06 m, and R2 = 0.96).

Lake water level response to drought in a lake-rich region explained by lake and landscape characteristics

2020 ◽  
Vol 77 (11) ◽  
pp. 1836-1845
Author(s):  
K. Martin Perales ◽  
Catherine L. Hein ◽  
Noah R. Lottig ◽  
M. Jake Vander Zanden
Keyword(s):  
Climate Change ◽  
Water Level ◽  
Lake Water ◽  
Water Levels ◽  
Water Level Fluctuations ◽  
Lake Area ◽  
Lake Water Level ◽  
Landscape Characteristics ◽  
Lake Ecology ◽  
Coarse Woody Habitat

Climate change is altering hydrologic regimes, with implications for lake water levels. While lakes within lake districts experience the same climate, lakes may exhibit differential climate vulnerability regarding water level response to drought. We took advantage of a recent drought (∼2005–2010) and estimated changes in lake area, water level, and shoreline position on 47 lakes in northern Wisconsin using high-resolution orthoimagery and hypsographic curves. We developed a model predicting water level response to drought to identify characteristics of the most vulnerable lakes in the region, which indicated that low-conductivity seepage lakes found high in the landscape, with little surrounding wetland and highly permeable soils, showed the greatest water level declines. To explore potential changes in the littoral zone, we estimated coarse woody habitat (CWH) loss during the drought and found that drainage lakes lost 0.8% CWH while seepage lakes were disproportionately impacted, with a mean loss of 40% CWH. Characterizing how lakes and lake districts respond to drought will further our understanding of how climate change may alter lake ecology via water level fluctuations.

Zooplankton species richness and abiotic conditions in Thirlmere Lakes, New South Wales, Australia, with reference to water-level fluctuations

2020 ◽  
Vol 41 (1) ◽  
pp. 107-123
Author(s):  
Tsuyoshi Kobayashi ◽  
Martin Krogh ◽  
Hiroyuki ◽  
Russell J. Shiel ◽  
Hendrik Segers ◽  
...  
Keyword(s):  
Species Richness ◽  
Water Level ◽  
Lake Water ◽  
New South ◽  
Water Levels ◽  
Water Level Fluctuations ◽  
Zooplankton Species ◽  
Abiotic Conditions ◽  
Lake Water Level ◽  
South Wales

Water-level fluctuations can have significant effects on lake biological communities. Thirlmere Lakes are a group of five interconnected lakes located near Sydney. Water levels in Thirlmere Lakes have fluctuated over time, but there has been a recent decline that is of significant concern. In this study, we examined over one year the species composition and richness of zooplankton (Rotifera, Cladocera and Copepoda) and abiotic conditions in Lakes Nerrigorang and Werri Berri, two of the five Thirlmere lakes, with reference to lake water level. We recorded a total of 66 taxa of zooplankton, with the first report of the rotifer Notommata saccigera from Australia, and the first report of the rotifers Keratella javana, Lecane rhytida and Rousseletia corniculata from New South Wales. There was a marked difference in abiotic conditions between the two lakes, with more variable conditions in Lake Nerrigorang. There was a significant positive correlation between zooplankton species richness and lake water level but only for Lake Nerrigorang. Although the two lakes are closely situated and thought to be potentially connected at high water levels, they show distinct ecological characters and the effect of water-level fluctuations on zooplankton species richness seems to differ between the lakes.

Prediction of Urmia Lake Water-Level Fluctuations by Using Analytical, Linear Statistic and Intelligent Methods

2013 ◽  
Vol 27 (13) ◽  
pp. 4469-4492 ◽  
Author(s):  
Hossein Kakahaji ◽  
Hamed Dehghan Banadaki ◽  
Abbas Kakahaji ◽  
Abdulamir Kakahaji
Keyword(s):  
Water Level ◽  
Lake Water ◽  
Urmia Lake ◽  
Water Level Fluctuations ◽  
Linear Statistic ◽  
Lake Water Level ◽  
Intelligent Methods

scholarly journals Study Clastic Sediments and Evaporite Deposits’ Changes in the Sedimentary Core Lake Maharlou, Iran

2016 ◽  
Vol 10 (4) ◽  
pp. 1 ◽  
Author(s):  
Abdolah Safe ◽  
Fatemeh Sabokkhiz ◽  
Mohamad Hosein Ramesht ◽  
Morteza Djamali ◽  
Abdolmajid Naderi Beni
Keyword(s):  
Magnetic Susceptibility ◽  
Water Level ◽  
Lake Water ◽  
Core Sample ◽  
Water Level Fluctuations ◽  
Gravimetric Analysis ◽  
Zagros Mountains ◽  
Lake Water Level ◽  
The Core ◽  
Sedimentary Core

The continental environments, lakes are proper for deposition locations of evaporites. Evaporite minerals are formed wherever the evaporation rate is more than incoming water to the basin. In this article the evaporate deposits (Calcite, Gypsum and Halite) are studied in a sedimentary core of Lake Maharlou, Zagros Mountains, South of Iran. The core sample treated for getting Magnetic Susceptibility values along with the core as well as basic sedimentological data including grain size, Total Organic Matter and carbonate contents. NaCl is determin ed by gravimetric analysis. Loss on Ignition is applied to measure and estimate the amount of (OC), (Ca) and (SO4) mineralogy of which is determined by SEM method. The exists a direct relation between evaporation deposit formation of lake water level reduction. Accordingly, the change in the sediment stratum indicating the level of evaporations. The results indicate a lower extant of gypsum than Ca and NaCl. The sequence of layers principle, changes in the shoreline (lake water level fluctuations) with respect to stratum zonation. Magnetic susceptibility level is directly related to the Silt layer thickness but also there is an indirect relation with the level of organically rich sediments’ occurrence and abundance.

scholarly journals Comparison of random forests and other statistical methods for the prediction of lake water level: a case study of the Poyang Lake in China

2016 ◽  
Vol 47 (S1) ◽  
pp. 69-83 ◽  
Author(s):  
Bing Li ◽  
Guishan Yang ◽  
Rongrong Wan ◽  
Xue Dai ◽  
Yanhui Zhang
Keyword(s):  
Water Level ◽  
Random Forests ◽  
Lake Water ◽  
Poyang Lake ◽  
Time Lag ◽  
Water Levels ◽  
Support Vector ◽  
Lake Water Level ◽  
Water Level Variations

Modeling of hydrological time series is essential for sustainable development and management of lake water resources. This study aims to develop an efficient model for forecasting lake water level variations, exemplified by the Poyang Lake (China) case study. A random forests (RF) model was first applied and compared with artificial neural networks, support vector regression, and a linear model. Three scenarios were adopted to investigate the effect of time lag and previous water levels as model inputs for real-time forecasting. Variable importance was then analyzed to evaluate the influence of each predictor for water level variations. Results indicated that the RF model exhibits the best performance for daily forecasting in terms of root mean square error (RMSE) and coefficient of determination (R2). Moreover, the highest accuracy was achieved using discharge series at 4-day-ahead and the average water level over the previous week as model inputs, with an average RMSE of 0.25 m for five stations within the lake. In addition, the previous water level was the most efficient predictor for water level forecasting, followed by discharge from the Yangtze River. Based on the performance of the soft computing methods, RF can be calibrated to provide information or simulation scenarios for water management and decision-making.

scholarly journals ESTIMATING WATER LEVEL IN THE URMIA LAKE USING SATELLITE DATA: A MACHINE LEARNING APPROACH

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 219-226
Author(s):  
M. Boueshagh ◽  
M. Hasanlou
Keyword(s):  
Water Level ◽  
Lake Water ◽  
Kernel Method ◽  
Urmia Lake ◽  
Gaussian Kernel ◽  
Support Vector ◽  
Substantial Impact ◽  
Lake Water Level ◽  
Global Environmental Issue ◽  
Rbf Kernel

Abstract. Lakes play a pivotal role in the development of cities and have major impacts on the ecosystem balancing of the area. Remote sensing techniques and advanced modeling methods make it possible to monitor natural phenomena, such as lakes’ water level. The ecosystem of Urmia Lake is one of the most momentous ecosystems in Iran, which is almost close-ended and has become a global environmental issue in recent years. One of the parameters affecting this lake water level is snowfall, which has a key role in the fluctuations of its water level and water resources management. Hence, the purpose of this paper is the Urmia Lake water level estimation during 2000–2006 using observed water level, snow cover, direct precipitation, and evaporation. For this purpose, Support Vector Regression (SVR), which is the most outstanding kernel method (with various kernel types), has been used. Furthermore, four scenarios are considered with different variables as inputs, and the output of all scenarios is the water level of the lake. The results of training and testing data indicate the substantial impact of snow on retrieving the water level of the Urmia Lake at the desired period, and due to the complexity of the data relationships, the Gaussian kernel generally had better results. On the other hand, Quadratic and Cubic kernels did not work well. The fourth scenario, with RBF kernel has the best results [Training: R2 = 97% and RMSE = 0.09 m, Testing: R2 = 96.97% and RMSE = 0.08 m].

Sign in / Sign up

Export Citation Format

Share Document