Comparison study of artificial intelligence method for short term groundwater level prediction in the northeast Gachsaran unconfined aquifer

2020 ◽  
Vol 20 (3) ◽  
pp. 909-921 ◽  
Author(s):  
Akbar Khedri ◽  
Nasrollah Kalantari ◽  
Meysam Vadiati
Keyword(s):  
Groundwater Level ◽  
Unconfined Aquifer ◽  
Least Square ◽  
Data Driven ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Data Set ◽  
Groundwater Levels ◽  
Statistical Performance Evaluation ◽  
Groundwater Level Prediction

Abstract Accurate and reliable groundwater level prediction is an important issue in groundwater resource management. The objective of this research is to compare groundwater level prediction of several data-driven models for different prediction periods. Five different data-driven methods are compared to evaluate their performances to predict groundwater levels with 1-, 2- and 3-month lead times. The four quantitative standard statistical performance evaluation measures showed that while all models could provide acceptable predictions of groundwater level, the least square support vector machine (LSSVM) model was the most accurate. We developed a set of input combinations based on different levels of groundwater, total precipitation, average temperature and total evapotranspiration at monthly intervals. For each model, the antecedent inputs that included Ht-1, Ht-2, Ht-3, Tt, ETt, Pt, Pt-1 produced the best-fit model for 1-month lead time. The coefficient of determination (R2) and the root mean square error (RMSE) were calculated as 0.99%, 1.05 meters for the train data set, and 95%, 2.3 meters for the test data set, respectively. It was also demonstrated that many combinations the above-mentioned approaches could model groundwater levels for 1 and 2 months ahead appropriately, but for 3 months ahead the performance of the models was not satisfactory.

scholarly journals Assessing the suitability of extreme learning machines (ELM) for groundwater level prediction

2017 ◽  
Vol 32 (1) ◽  
pp. 103-112 ◽  
Author(s):  
Basant Yadav ◽  
Sudheer Ch ◽  
Shashi Mathur ◽  
Jan Adamowski
Keyword(s):  
Soft Computing ◽  
Groundwater Level ◽  
Groundwater Resources ◽  
Support Vector ◽  
Complex Nature ◽  
Data Set ◽  
Groundwater Levels ◽  
Soft Computing Techniques ◽  
Learning Machine ◽  
The Comparative Study

Abstract Fluctuation of groundwater levels around the world is an important theme in hydrological research. Rising water demand, faulty irrigation practices, mismanagement of soil and uncontrolled exploitation of aquifers are some of the reasons why groundwater levels are fluctuating. In order to effectively manage groundwater resources, it is important to have accurate readings and forecasts of groundwater levels. Due to the uncertain and complex nature of groundwater systems, the development of soft computing techniques (data-driven models) in the field of hydrology has significant potential. This study employs two soft computing techniques, namely, extreme learning machine (ELM) and support vector machine (SVM) to forecast groundwater levels at two observation wells located in Canada. A monthly data set of eight years from 2006 to 2014 consisting of both hydrological and meteorological parameters (rainfall, temperature, evapotranspiration and groundwater level) was used for the comparative study of the models. These variables were used in various combinations for univariate and multivariate analysis of the models. The study demonstrates that the proposed ELM model has better forecasting ability compared to the SVM model for monthly groundwater level forecasting.

scholarly journals Correlation between the structure and skin permeability of compounds

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ruolan Zeng ◽  
Jiyong Deng ◽  
Limin Dang ◽  
Xinliang Yu
Keyword(s):  
Large Data ◽  
Qsar Model ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Skin Permeability ◽  
Data Set ◽  
Test Set ◽  
Svm Algorithm ◽  
Svm Model ◽  
Toxicity Relationship

AbstractA three-descriptor quantitative structure–activity/toxicity relationship (QSAR/QSTR) model was developed for the skin permeability of a sufficiently large data set consisting of 274 compounds, by applying support vector machine (SVM) together with genetic algorithm. The optimal SVM model possesses the coefficient of determination R2 of 0.946 and root mean square (rms) error of 0.253 for the training set of 139 compounds; and a R2 of 0.872 and rms of 0.302 for the test set of 135 compounds. Compared with other models reported in the literature, our SVM model shows better statistical performance in a model that deals with more samples in the test set. Therefore, applying a SVM algorithm to develop a nonlinear QSAR model for skin permeability was achieved.

scholarly journals Assessment of Soft Computing Techniques for the Prediction of Compressive Strength of Bacterial Concrete

Materials ◽  
2022 ◽  
Vol 15 (2) ◽  
pp. 489
Author(s):  
Fadi Almohammed ◽  
Parveen Sihag ◽  
Saad Sh. Sammen ◽  
Krzysztof Adam Ostrowski ◽  
Karan Singh ◽  
...  
Keyword(s):  
Compressive Strength ◽  
Performance Evaluation ◽  
Absolute Error ◽  
Coefficient Of Determination ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Curing Time ◽  
Data Set ◽  
Soft Computing Techniques ◽  
Bacterial Concrete

In this investigation, the potential of M5P, Random Tree (RT), Reduced Error Pruning Tree (REP Tree), Random Forest (RF), and Support Vector Regression (SVR) techniques have been evaluated and compared with the multiple linear regression-based model (MLR) to be used for prediction of the compressive strength of bacterial concrete. For this purpose, 128 experimental observations have been collected. The total data set has been divided into two segments such as training (87 observations) and testing (41 observations). The process of data set separation was arbitrary. Cement, Aggregate, Sand, Water to Cement Ratio, Curing time, Percentage of Bacteria, and type of sand were the input variables, whereas the compressive strength of bacterial concrete has been considered as the final target. Seven performance evaluation indices such as Correlation Coefficient (CC), Coefficient of determination (R2), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Bias, Nash-Sutcliffe Efficiency (NSE), and Scatter Index (SI) have been used to evaluate the performance of the developed models. Outcomes of performance evaluation indices recommend that the Polynomial kernel function based SVR model works better than other developed models with CC values as 0.9919, 0.9901, R2 values as 0.9839, 0.9803, NSE values as 0.9832, 0.9800, and lower values of RMSE are 1.5680, 1.9384, MAE is 0.7854, 1.5155, Bias are 0.2353, 0.1350 and SI are 0.0347, 0.0414 for training and testing stages, respectively. The sensitivity investigation shows that the curing time (T) is the vital input variable affecting the prediction of the compressive strength of bacterial concrete, using this data set.

scholarly journals The Role of Environmental Background Processes in Determining Groundwater Level Variability—An Investigation of a Record Flood Event Using Dynamic Factor Analysis

Water ◽  
2020 ◽  
Vol 12 (9) ◽  
pp. 2336
Author(s):  
Balázs Trásy ◽  
Norbert Magyar ◽  
Tímea Havril ◽  
József Kovács ◽  
Tamás Garamhegyi
Keyword(s):  
Factor Analysis ◽  
Groundwater Level ◽  
Coefficient Of Determination ◽  
Dynamic Factor Analysis ◽  
Dynamic Factor ◽  
Climate Change Scenarios ◽  
Background Factors ◽  
Groundwater Levels ◽  
Groundwater Level Fluctuations ◽  
Environmental Background

Since groundwater is a major source of water for drinking and for industrial and irrigation uses, the identification of the environmental processes determining groundwater level fluctuation is potentially a matter of great consequence, especially in light of the fact that the frequency of extreme climate events may be expected to increase, causing changes in groundwater recharge systems. In the recent study, data measured at a frequency of one hour were collected from the Szigetköz, an inland delta of the Danube. These were then used to determine the presence, or not, and magnitude of any hidden environmental background factors that may be causing groundwater level fluctuations. Through the application of dynamic factor analysis, it was revealed that changes in groundwater level are mainly determined by (i) the water level of neighboring rivers and (ii) evapotranspiration. The intensity of these factors may also be estimated spatially. If the background factors determined by dynamic factor analysis do indeed figure in the linear model as variables, then the time series of groundwater levels can be said to have been accurately estimated with the use of linear regression. The accuracy of the estimate is indicated by the fact that adjusted coefficient of determination exceeds 0.9 in 80% of the wells. The results, via an enhanced understanding of the reasons for changes in the fluctuation of groundwater, could assist in the development of sustainable water management and irrigation strategies and the preparation for varying potential climate change scenarios.

scholarly journals Validating a spatially distributed hydrological model with soil morphology data

2014 ◽  
Vol 18 (9) ◽  
pp. 3481-3498 ◽  
Author(s):  
T. Doppler ◽  
M. Honti ◽  
U. Zihlmann ◽  
P. Weisskopf ◽  
C. Stamm
Keyword(s):  
Groundwater Level ◽  
Morphological Data ◽  
Distributed Model ◽  
Management Decisions ◽  
Data Set ◽  
Detailed Model ◽  
Groundwater Levels ◽  
Artificial Drainage ◽  
Spatial Coverage ◽  
Spatially Distributed

Abstract. Spatially distributed models are popular tools in hydrology claimed to be useful to support management decisions. Despite the high spatial resolution of the computed variables, calibration and validation is often carried out only on discharge time series at specific locations due to the lack of spatially distributed reference data. Because of this restriction, the predictive power of these models, with regard to predicted spatial patterns, can usually not be judged. An example of spatial predictions in hydrology is the prediction of saturated areas in agricultural catchments. These areas can be important source areas for inputs of agrochemicals to the stream. We set up a spatially distributed model to predict saturated areas in a 1.2 km2 catchment in Switzerland with moderate topography and artificial drainage. We translated soil morphological data available from soil maps into an estimate of the duration of soil saturation in the soil horizons. This resulted in a data set with high spatial coverage on which the model predictions were validated. In general, these saturation estimates corresponded well to the measured groundwater levels. We worked with a model that would be applicable for management decisions because of its fast calculation speed and rather low data requirements. We simultaneously calibrated the model to observed groundwater levels and discharge. The model was able to reproduce the general hydrological behavior of the catchment in terms of discharge and absolute groundwater levels. However, the the groundwater level predictions were not accurate enough to be used for the prediction of saturated areas. Groundwater level dynamics were not adequately reproduced and the predicted spatial saturation patterns did not correspond to those estimated from the soil map. Our results indicate that an accurate prediction of the groundwater level dynamics of the shallow groundwater in our catchment that is subject to artificial drainage would require a model that better represents processes at the boundary between the unsaturated and the saturated zone. However, data needed for such a more detailed model are not generally available. This severely hampers the practical use of such models despite their usefulness for scientific purposes.

scholarly journals Multi-step streamflow forecasting using data-driven non-linear methods in contrasting climate regimes

2013 ◽  
Vol 16 (3) ◽  
pp. 671-689 ◽  
Author(s):  
Daniel J. Karran ◽  
Efrat Morin ◽  
Jan Adamowski
Keyword(s):  
Wavelet Transforms ◽  
Model Performance ◽  
Probability Of Detection ◽  
Data Driven ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Lead Times ◽  
Streamflow Forecasting ◽  
Non Linear ◽  
Using Data

Considering the popularity of using data-driven non-linear methods for forecasting streamflow, there has been no exploration of how well such models perform in climate regimes with differing hydrological characteristics, nor has the performance of these models, coupled with wavelet transforms, been compared for lead times of less than 1 month. This study compares the use of four different models, namely artificial neural networks (ANNs), support vector regression (SVR), wavelet-ANN, and wavelet-SVR in a Mediterranean, Oceanic, and Hemiboreal watershed. Model performance was tested for 1, 2 and 3 day forecasting lead times, measured by fractional standard error, the coefficient of determination, Nash–Sutcliffe model efficiency, multiplicative bias, probability of detection and false alarm rate. SVR based models performed best overall, but no one model outperformed the others in more than one watershed, suggesting that some models may be more suitable for certain types of data. Overall model performance varied greatly between climate regimes, suggesting that higher persistence and slower hydrological processes (i.e. snowmelt, glacial runoff, and subsurface flow) support reliable forecasting using daily and multi-day lead times.

scholarly journals DEPTH ESTIMATION OF SHALLOW WATER USING MULTISPECTRAL SATELLITE IMAGERY SENTINEL-2A

Jurnal Segara ◽  
2020 ◽  
Vol 16 (3) ◽  
Author(s):  
Arip Rahman
Keyword(s):  
Shallow Water ◽  
Test Data ◽  
Remote Sensing Data ◽  
Depth Estimation ◽  
Training Data ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Data Set ◽  
Svm Algorithm ◽  
Sentinel 2A

Shallow water bathymetry estimation from remote sensing data has been increasing widespread, as an alternative to traditional bathymetry measurement that has disturbed by technical and logistic problem. Deriving bathymetry data from Sentinel 2A images, at visible wavelength (blue, green and red) 10 meter spatial resolution was carried out around the waters of the Kemujan Island Karimunjawa National Park Central Java. Amount of 1280 points data are used as training data sets and 854 points data as test data set produced from sounding. Dark Object Substraction (DOS) has been to correct atmospherically the Sentinel-2A images. Several algorithm has been applied to derive bathymetry data, including: linear transform, ratio transform and support vector machine (SVM). The highest correlation between depth prediction and observe resulted from SVM algorithm with a coefficient of determination (R2) 0.71 (training data) and 0.56 (test data). The assessment of the accuracy of the three methods using RMSE and MAE values, the SVM algorithm has the smallest value (< 1 m). This indicates that the SVM algorithm has a high accuracy compared to the other two methods. The bathymetry map derived from Sentinel 2A imagery cannot be used as a reference for navigation.

Sign in / Sign up

Export Citation Format

Share Document