https://easychair.org/publications/preprint_open/f943

Wind speed prediction using a hybrid model of the multi-layer perceptron and whale optimization algorithm

The most important motivation for streamflow forecasts is flood prediction and longtime continuous prediction in hydrological research. As for many traditional statistical models, forecasting flood peak discharge is nearly impossible. They can only get acceptable results in normal year. On the other hand, the numerical methods including physics mechanisms and rainfall-atmospherics could provide a better performance when floods coming, but the minima prediction period of them is about one month ahead, which is too short to be used in hydrological application. In this study, a deep neural network was employed to predict the streamflow of the Hankou Hydrological Station on the Yangtze River. This method combined the Empirical Mode Decomposition (EMD) algorithm and Encoder Decoder Long Short-Term Memory (En-De-LSTM) architecture. Owing to the hydrological series prediction problem usually contains several different frequency components, which will affect the precision of the longtime prediction. The EMD technique could read and decomposes the original data into several different frequency components. It will help the model to make longtime predictions more efficiently. The LSTM based En-De-LSTM neural network could make the forecasting closer to the observed in peak flow value through reading, training, remembering the valuable information and forgetting the useless data. Monthly streamflow data (from January 1952 to December 2008) from Hankou Hydrological Station on the Yangtze River was selected to train the model, and predictions were made in two years with catastrophic flood events and ten years rolling forecast. Furthermore, the Root Mean Square Error (RMSE), Coefficient of Determination (R
 2
), Willmott's Index of agreement (WI) and the Legates-McCabe's Index (LMI) were used to evaluate the goodness-of-fit and performance of this model. The results showed the reliability of this method in catastrophic flood years and longtime continuous rolling forecasting.

/pdf/streamflow-prediction-using-deep-learning-neural-network-15ce3goatk.pdf

Streamflow Prediction Using Deep Learning Neural Network: Case Study of Yangtze River

Current development of Pakistan’s economy, transportation and industry with the improvement of urbanization, environmental pollution problems have gradually become prominent, but this is contrary to people’s vision of pursuing a high-quality life. Now the problem of haze, photochemical problems in the air, and global warming is already a key issue of global concern. This is focused on the ambient air quality of Lahore city of Pakistan. The study reveals that the particulate matter in the Lahore season (PM2.5, PM10) exceeds Pakistan’s National Environmental Quality Standards (NEQS). Correlation study suggests the positive correlation between the particulate matter and other mass concentration particles like Ozone (O3), Nitrogen Oxide (NO), Sulphur Dioxide (SO2). Higher values of CO/NO suggest that mobile sources are one of the major factors of this increase in NO. Further estimation of backward trajectory is done by the Hybrid-Single Particle Lagrangian Integrated Trajectory (HYSPLIT) model which provides the path of those particles in the last year period and the source of origin is from Afghanistan. This study provides in depth analysis of all factors of air pollutants by correlation between those factors. Prediction of future concentration of PM2.5 is predicted using the Seasonal Autoregressive Integrated Moving Average (SARIMA) model which gives the increasing value of PM2.5 in next year and provides the lowest and highest predicts (more than $100~\mu \text{g}/\text{m}^{3}$ ).

/pdf/time-series-analysis-and-forecasting-of-air-pollution-56nlwj70w6.pdf

Time Series Analysis and Forecasting of Air Pollution Particulate Matter (PM 2.5 ): An SARIMA and Factor Analysis Approach

In the present study, an improved adaptive neuro fuzzy inference system (ANFIS) and multilayer perceptron (MLP) models are hybridized with a sunflower optimization (SO) algorithm and are introduced for lake water level simulation. The Urmia Lake water level is predicted and assessed using the potential of the proposed advanced artificial intelligence (AI) models. The sunflower optimization algorithm is implemented to find the optimal tuning parameters. The results indicated that the ANFIS-SO model with the combination of three lags of rainfall and temperature as input attributes attained the best predictability performance. The minimal values of the root mean square error were RMSE = 1.89 m and 1.92 m for the training and testing modeling phases, respectively. The worst prediction capacity was attained for the long lead (i.e., six months rainfall lag times). The uncertainty analysis showed that the ANFIS-SO model had less uncertainty based on the percentage of more responses in the confidence band and lower bandwidth. Also, different scenarios of water harvesting were investigated with the consideration of environmental restrictions and fair water allocation to stakeholders. Further, studying Urmia Lake water harvesting scenarios displayed that the 30% water harvesting scenario of the lake water improves the lake’s water level.

Hybridization of artificial intelligence models with nature inspired optimization algorithms for lake water level prediction and uncertainty analysis

The modelling of drought is of utmost importance for the efficient management of water resources. This article used the adaptive neuro-fuzzy interface system (ANFIS), multilayer perceptron (MLP), r ...

Zoning map for drought prediction using integrated machine learning models with a nomadic people optimization algorithm

Hydrological droughts are characterized based on their duration, severity, and magnitude. Among the most critical factors, precipitation, evapotranspiration, and runoff  are essential in modeling t...

https://www.tandfonline.com/doi/pdf/10.1080/19942060.2020.1715844

Predicting Standardized Streamflow index for hydrological drought using machine learning models

Rainfall, as one of the key components of hydrological cycle, plays an undeniable role for accurate modelling of other hydrological components. Therefore, a precise forecasting of annual rainfall is of the high importance. In this regard, several studies have been tried to predict annual rainfall of different climate zones using machine learning and soft computing algorithms. This study investigates the application of an innovative hybrid method, namely Multilayer Perceptron-Whale Optimization Algorithm (MLP-WOA) to predict annual rainfall comparatively to the ordinary Multilayer Perceptron models (MLP). The models were developed by using 3-Input variables of annual rainfall at lag1, 2 and 3 corresponding to Pt-1, Pt-2 and Pt-3, respectively of two synoptic stations of Senegal (Fatick and Goudiry) in the time period of 1933–2013. 75% of the dataset were utilized for training and the other 25% for testing the studied models Accurateness of the mentioned models was examined using root mean squared error, correlation coefficient, and KlingGupta efficiency. Results showed that MLP-WOA3 and MLP3 using both Pt-1, Pt-2 and Pt-3 as inputs presented the most accurate forecasting in Fatick and Goudiry stations, respectively. In Fatick station, MLP-WOA3 decreased the RMSE value of MLP3 by 18.3% and increased the R and KGE values by 3.0% and 130%, respectively in testing period. But, in Goudiry station, MLP-WOA3 increased the RMSE value of MLP3 by 3.9% and increased the R and KGE values by 10.2% and 91% in testing period. Therefore, it can be realized that the MLP-WOA3 could not able to reduce the RMSE value of correspondent MLP model in Goudiry station. The conclusive results indicated that MLP-WOA slightly improved the accuracy of correspondent MLP models and may be recommended for annual rainfall forecasting.

Annual Rainfall Forecasting Using Hybrid Artificial Intelligence Model: Integration of Multilayer Perceptron with Whale Optimization Algorithm

With respect to the necessity of comprehensive studies on drought and also high damages that caused by drought, this research studied the meteorological and hydrological droughts. In this study, Lighvan, Navroud and Seqez basins with different climates were selected. We used monthly data of stream flow, precipitation and evaporation from 1992 to 2016 for the study of drought phenomena. The aim at this study is to analyze the SPI and SPEI for determination of dry and wet meteorological periods and use of the SSI for the exploration of hydrological drought. The analysis of drought characteristics such as intensity and duration in three areas with different climates shows that the climate change has a major impact on the characteristics of the droughts. The relations between the duration and severity of drought have been more accurate in the period of 9 months in the Navroud watershed basin. The most significant events are SPI-9 with the duration of 57 months and the severity of 34.7, SPEI-9 with the duration of 34 months and the severity of 28.09 and SSI-9 with the duration of 41 months and the severity of 30.2. According to the obtained equations in different time periods, it was resulted that the highest accuracy was observed in the relationship between the meteorological and hydrological drought characteristics in the watershed basin of Seqez for a period of 6 months. The results show that in all three basins, the correlation between the meteorological and hydrological drought is significant at the level of 99%. Results show that hydrological and meteorological droughts in Navroud and Lighvan basins have a significant correlation with 48-month periods and in the Seqez basin with 12- and 24-month periods, and the relations between hydrological droughts and meteorological droughts were obtained using the nonlinear linear models (polynomial, exponential and logarithmic). The good R2 between the duration and severity of SPI-9 and SSI-9 is 0.8 and 0.92, respectively, for polynomial equations. The maximum determination coefficient of duration and severity of SPEI-9 and SSI-9 is 0.72 and 0.82, respectively, using polynomial equation. The application of several indices indicating different components of the hydrological cycle integrates many factors that affect and trigger droughts, and thus can help in providing a wider realization of the characteristics of droughts on various water sections.

/pdf/meteorological-and-hydrological-drought-monitoring-using-346dxx18u9.pdf

Meteorological and hydrological drought monitoring using several drought indices

In this research, De Martonne’s index of aridity (IDM), Pinna combinative aridity index (IP), and UNEP aridity index (AI) were used for the drought analysis in the Sirvan river basin, Iran, during the period 2002–2018. Spatiotemporal analysis of aridity indices on each station was determined by calculating the Z statistic value of the nonparametric Mann–Kendall (MK) method of time series on the index values, and the slope of trend lines was calculated by Sen’s slope estimator method. The percentage change (tv%) in the amount of indicators was obtained during the studied period for each station. The results showed that eight stations out of 10 studied stations had a downward trend and the other stations had an upward trend (close to zero and nonsignificant) for the IDM on an annual scale, and one station (Janevareh, Z = −1.66) was statistically significant at the level of 10%. In the IP method, five stations had a downward trend, and the station (Janevareh, Z = −1.93) was statistically significant at the level of 10%. Also, in the AI method, nine stations had a downward trend, and the station of Janevareh (Z = −1.93) was statistically significant at the level of 10%. Among the stations that have experienced the highest amount of drying, Sarcheshmeh station in IDM with a slope of −0.45, Janevareh station in IP with a slope of −0.22, and Sarcheshmeh and Janevareh stations in AI index with a slope of −0.01 and more have tended toward drying, respectively. In general, it can be concluded that the climate of most of the studied stations in the Sirvan river basin has become significantly drier and warmer.

Hana Salimi

Papers

Predicting Standardized Streamflow index for hydrological drought using machine learning models

Annual Rainfall Forecasting Using Hybrid Artificial Intelligence Model: Integration of Multilayer Perceptron with Whale Optimization Algorithm

Meteorological and hydrological drought monitoring using several drought indices

Spatiotemporal analysis of aridity indices by using the nonparametric methods (case study: Sirvan river basin, Kurdistan Province, Iran)