Yazar "Ahmadi, Farshad" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • Küçük Resim
    Öğe
    Developing a novel framework for forecasting groundwater level fluctuations using Bi-directional Long Short-Term Memory (BiLSTM) deep neural network
    (Elsevier Science Ltd, 2021) Ghasemlounia, Redvan; Gharehbaghi, Amin; Ahmadi, Farshad; Saadatnejadgharahassanlou, Hamid
    In this study, mean monthly groundwater level (GWL) fluctuations of four different monitoring piezometers are forecasted in an agricultural area by developing new proposed structures of BiLSTM based neural network models. For developing models, 186 monthly measured water table depth during time period (Sep 2001-Feb 2017) are employed. Due to a lack of meteorological variables records, the module of sequence-to-one is employed. By tuning several hyperparameters such as the number of hidden units (NHU), kind of state activation function (SAF), learning dropout rate (P-rate), and network topology pattern (NTP), the performance of designed models is improved. Based on results of modelling, in all designed models, the optimal P-rate is obtained 0.5, and the running time decrease by increasing P-rate in the same model. Since harsh fluctuations of GWL, the general Single-LSTM mode (1) and Single-BiLSTM model (2) perform too weak compared to other models. Nonetheless, by deepening models through adding the suitable hidden layers instead of many numbers of nodes, the performance of Single-BiLSTM model is improved strikingly. Based on statistical evaluation metrics, violin plot, and also TLP (Total Learnable Parameters) value, novel proposed model (5) (simple Double-BiLSTM model combined by a Multiplication layer (x)) is selected as the superior model. In the piezometer 4 with a range of 4.49 (m), the model (5) yielded in an R-2 of 0.89 and an RMSE of 0.17 (m), while in the same physical characteristics, the simple Double-BiLSTM model (3) yielded in an R-2 of 0.77 and an RMSE of 0.25 (m).
  • Küçük Resim
    Öğe
    Developing a novel hybrid model based on deep neural networks and discrete wavelet transform algorithm for prediction of daily air temperature
    (Springer Science and Business Media B.V., 2024) Ghasemlounia, Redvan; Gharehbaghi, Amin; Ahmadi, Farshad; Albaji, Mohammad
    The precise predicting of air temperature has a significant influence in many sectors such as agriculture, industry, modeling environmental processes. In this work, to predict the mean daily time series air temperature in Mu & gbreve;la city (AT(m)), Turkey, initially, five different layer structures of Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) deep learning-based neural network models through the seq2seq regression forecast module are developed. Then, based on performance evaluation metrics, an optimal DL-based layer network structure designed is chosen to hybridize with the wavelet transform (WT) algorithm (i.e., WT-DNN model) to enhance the estimation capability. In this direction, among potential meteorological variables considered, the average daily sunshine duration (SSD) (hours), total global solar radiation (TGSR) (kw. hour/m(2)), and total global insolation intensity (TGSI) (watt/m(2)) from Jan 2014 to Dec 2019 are picked as the most effective input variables through correlation analysis to predict AT(m). To thwart overfitting and underfitting problems, different algorithm tuning along with trial-and-error procedures through diverse types of hyper-parameters are performed. Consistent with the performance evaluation standards, comparison plots, and Total Learnable Parameters (TLP) value, the state-of-the-art and unique proposed hybrid WT-(LSTM x GRU) model (i.e., hybrid WT with the coupled version of LSTM and GRU models via Multiplication layer (x)) is confirmed as the best model developed. This hybrid model under the ideal hyper-parameters resulted in an R-2 = 0.94, an RMSE = 0.56 (degrees C), an MBE = -0.5 (degrees C), AICc = -382.01, and a running time of 376 (s) in 2000 iterations. Nonetheless, the standard single LSTM layer network model as benchmark model resulted in an R-2 = 0.63, an RMSE = 4.69 (degrees C), an MBE = -0.89 (degrees C), AICc = 1021.8, and a running time of 186 (s) in 2000 iterations.
  • Küçük Resim
    Öğe
    Developing a novel hybrid model based on GRU deep neural network and whale optimization algorithm for precise forecasting of river's streamflow
    (Nature Research, 2025) Gharehbaghi, Amin; Ghasemlounia, Redvan; Ahmadi, Farshad; Mirabbassi, Rasoul; Torabi Haghighi, Ali
    Streamflow contemplates a fundamental criterion to evaluate the impact of human activities and climate changes on the hydrological cycle. In this study, a novel innovative deep neural network (DNN) structure by integrating a double Gated Recurrent Units (GRU) neural network model with a multiplication layer and meta-heuristic whale optimization algorithm (WOA) (i.e., hybrid 2GRU×–WOA model) is developed to improve the prediction accuracy and performance of mean monthly Chehel-Chai River’s streamflow (CCRSFm) in Iran. The Pearson’s correlation coefficient (PCC) and Cosine Amplitude Sensitivity (CAS) as feature (input) selection process determine the only precipitation (Pm) as the most effective input variable among a list of on-site potential climate time series parameters recorded in the study area. Thanks to a well-proportioned layer network structural framework in the suggested hybrid 2GRU×–WOA model, it leads to an appropriate total learnable parameter (TLP) compared to standard individual GRU and Bi-GRU as the benchmark models developed in the comparable meta-parameters. This hybrid model under the optimal meant meta-parameters tuned i.e., coupling a state activation functions (SAF) of tanh-softsign, dropout rate (P-rate) of 0.5, numbers of hidden neurons (NHN) of 70, outperforms with an R2 of 0.79, NSE of 0.76, MAE of 0.21 (m3/s), MBE of -0.11(m3/s), and RMSE of 0.36 (m3/s). Hybridizing the 2GRU× model with WOA algorithm causes to increase in the value of R2 by 6.8% and reduce in the value of RMSE by 20.4%. Comparatively, standard individual GRU and Bi-GRU models result in an R2 of 0.59 and 0.66, NSE of 0.55 and 0.6, MAE of 0.91 and 0.53 (m3/s), MBE of 0.047 and − 0.06 (m3/s), RMSE of 1.29 and 0.83 (m3/s), respectively.
  • Küçük Resim
    Öğe
    Development of deep learning approaches for drought forecasting: a comparative study in a cold and semi-arid region
    (Springer Science and Business Media Deutschland GmbH, 2025) Gharehbaghi, Amin; Ghasemlounia, Redvan; Vaheddoost, Babak; Ahmadi, Farshad
    Drought is an intricate natural disaster that substantially menace the world. Its exact forecasting has a remarkable impact in several parts such as food production, business, industry, etc. In this study, in order to assess the drought procedure in Mahabad River basin, the temporal meteorological reconnaissance drought index (RDIMRB) in four diverse time scales including 3, 6, 9, and 12-month are computed using 576 monthly climatic datasets recorded from Sep 1974 to Aug 2022. To predict the time series RDIMRB, different standalone deep neural network (DNN) models including LSTM, GRU, Bi-directional LSTM (Bi-LSTM), and Bi-directional GRU (Bi-GRU) with the sequence-to-one regression module of forecasting (seq2one) are developed. For sake of this aim, the first 70% of data (395 months) and the last 30% of data (169 months) chronologically are used in the calibration and validation parts, respectively, to feed in the models development process. So as to achieve the most advantageous models’ structure, a lot of scenarios are adopted by tuning the meant meta-parameters including NHU (number of hidden units), SAF (state activation function), and P-rate (learning dropout rate). According to the performance assessment criteria, total learnable parameters (TLP) criterion, and comparison plots, the Bi-GRU model is verified as the most satisfactory model, and best results are obtained in RDIMRB-12. It under the epitome meant meta-parameters achieved (i.e., NHU = 120, P-rate = 0.5, and softsign as the suitable SAF) results in the RMSE, MBE, NSE, PBIAS, and R2 of 0.17, 0.011, 0.92, -2.02%, and 0.86, respectively, nonetheless for the GRU model are gotten 0.64, 0.071, 0.23, 17.97%, and 0.65, respectively.
  • Küçük Resim
    Öğe
    Groundwater level prediction with meteorologically sensitive Gated Recurrent Unit (GRU) neural networks
    (Elsevier, 2022) Gharehbaghi, Amin; Ghasemlounia, Redvan; Ahmadi, Farshad; Albaji, Mohammad
    Precise estimation of groundwater level (GWL) fluctuations has a substantial effect on water resources management. In the present study, to forecast the regional mean monthly time series groundwater level (GWL) with a range of 4.82 (m) in Urmia plain, three different layer structures of Gated Recurrent Unit (GRU) deep learningbased neural network models via the module of sequence-to-sequence regression are designed. In this sense, 180time series datasets of regional mean monthly meteorological, hydrological, and observed water table depths of 42 different monitoring piezometers during the period of Oct 2002-Sep 2017 are employed as the input variables. By using Shannon entropy method, the most influential parameters on GWL are determined as regional mean monthly air temperature (Tam), precipitation (Pm), total (sum) water diversion discharge (Wdm) of four main rivers. Nevertheless, Cosine amplitude sensitivity analysis confirmed Tam as a dominant factor. For preventing overfitting problem, an algorithm tuning technique via different kinds of hyperparameters is operated. In this respect, several scenarios are implemented and the optimal hyperparameters are accomplished via the trialand-error process. As stated by the performance evaluation metrics, Model Grading process, and Total Learnable Parameters (TLP) value, the innovative and unique suggested model (3), entitled GRU2+, (Double-GRU model coupled with Addition layer (+)) with seven layers is carefully chosen as the best model. The unique suggested model (3) in the optimal hyperparameters, resulted in an R2 of 0.91, a total grade (TG) of 7.76, an RMSE of 0.094 (m), and a running time of 47 (s). Thus, the model (3) can be certainly employed as an effective model to forecast GWL in different agricultural areas.
  • Küçük Resim
    Öğe
    Machine learning approaches coupled with variational mode decomposition: a novel method for forecasting monthly reservoir inflows
    (Springer Heidelberg, 2024) Ahmadi, Farshad; Ghasemlounia, Redvan; Gharehbaghi, Amin
    Reliable and precise reservoir inflow predicting is very significant for water resource management. In this research, different single and hybrid Variational Mode Decomposition (VMD) with estimation models including K-star (K*), Gaussian Process Regression (GPR), and Long Short-Term Memory (LSTM) models are developed to predict long-term time series of average monthly reservoir inflows in Baroon Dam (RIBDm) sited in Maku city, Northwest Iran. Using Pearson's correlation coefficient (PCC) analysis among observed potential meteorological predictors and RIBDm confirms the rainfall (Pave) as the only effective input variable. To reduce the influence of overfitting problems and well-configuration of the approaches developed, an algorithm tuning over meta-parameters together with a trial-and-error technique are applied. The outcomes of modeling show that in the both single K* and hybrid VMD-K* models, the optimum value of the global blend parameter (b) is 10%, yet, by rising the value of b from 10 to 100%, the accuracy of both models are markedly reduced. In both standard LSTM and hybrid VMD-LSTM models, the ideal dropout rate (P-rate) is gained 0.5. Likewise, in both models, as number of hidden neurons (NHN) is held constant, increasing P-rate causes to decrease running time, also as P-rate remains constant, increasing NHN causes to increase running time. Results of statistical indicators and visual analysis of comparison plots approve the hybrid VMD-LSTM model as the superior method with an R2 of 0.8, KGE of 0.87, RMSE of 1.15 (m3/s), and MBE of 0.15 (m3/s). Nonetheless, under the ideal scenario by the K* model, R2 is 0.27, RMSE is 2.75 (m3/s), KGE is 0.43, and MBE is 0.15 (m3/s).