Uncertainty assessment of the multilayer perceptron (MLP) neural network model with implementation of the novel hybrid MLP-FFA method for prediction of biochemical oxygen demand and dissolved oxygen: a case study of Langat River

Accurate prediction of the chemical constituents in major river systems is a necessary task for water quality management, aquatic life well-being and the overall healthcare planning of river systems. In this study, the capability of a newly proposed hybrid forecasting model based on the firefly algorithm (FFA) as a metaheuristic optimizer, integrated with the multilayer perceptron (MLP-FFA), is investigated for the prediction of monthly water quality in Langat River basin, Malaysia. The predictive ability of the MLP-FFA model is assessed against the MLP-based model. To validate the proposed MLP-FFA model, monthly water quality data over a 10-year duration (2001–2010) for two different hydrological stations (1L04 and 1L05) provided by the Irrigation and Drainage Ministry of Malaysia are used to predict the biochemical oxygen demand (BOD) and dissolved oxygen (DO). The input variables are the chemical oxygen demand (COD), total phosphate (PO₄), total solids, potassium (K), sodium (Na), chloride (Cl), electrical conductivity (EC), pH and ammonia nitrogen (NH₄-N). The proposed hybrid model is then evaluated in accordance with statistical metrics such as the correlation coefficient (r), root-mean-square error, % root-mean-square error and Willmott’s index of agreement. Analysis of the results shows that MLP-FFA outperforms the equivalent MLP model. Also, in this research, the uncertainty of a MLP neural network model is analyzed in relation to the predictive ability of the MLP model. To assess the uncertainties within the MLP model, the percentage of observed data bracketed by 95 percent predicted uncertainties (95PPU) and the band width of 95 percent confidence intervals (d-factors) are selected. The effect of input variables on BOD and DO prediction is also investigated through sensitivity analysis. The obtained values bracketed by 95PPU show about 77.7%, 72.2% of data for BOD and 72.2%, 91.6% of data for DO related to the 1L04 and 1L05 stations, respectively. The d-factors have a value of 1.648, 2.269 for BOD and 1.892, 3.480 for DO related to the 1L04 and 1L05 stations, respectively. Based on the values in both stations for the 95PPU and d-factor, it is concluded that the neural network model has an acceptably low degree of uncertainty applied for BOD and DO simulations. The findings of this study can have important implications for error assessment in artificial intelligence-based predictive models applied for water resources management and the assessment of the overall health in major river systems.     

Biostratigraphy and seismic data analysis to detect the sequence stratigraphic depositional environment of the Miocene succession: Gulf of Suez (Egypt)

This work comprises a study of the sequence stratigraphy, seismic-facies analysis, biostratigraphy and depositional environments of the northern part of the Gulf of Suez, Egypt, using a set of 24 3D seismic profiles, composite logs and sonic logs from ten wells. The syn-rift formations in the studied ten wells are described lithologically and interpreted based on investigating two seismic profiles. Biostratigraphically, the Miocene fossils are identified to correlate the five planktonic foraminiferal biozones in the examined boreholes (RB-A1, RB-B1, RB-B3, EE85-2 and RB-C1). The sequence stratigraphic analysis suggests that the Miocene succession can be subdivided into two major third order depositional sequences (S1 and S2) separated by the three major sequence boundaries (DSB1, DSB2 and DSB3).     

Wrench structural deformation in Ras Al Hilal-Al Athrun area, NE Libya: a new contribution in Northern Al Jabal Al Akhdar Belt

Al Jabal Al Akhdar is a NE/SW- to ENE/WSW-trending mobile part in Northern Cyrenaica province and is considered a large sedimentary belt in northeast Libya. Ras Al Hilal-Al Athrun area is situated in the northern part of this belt and is covered by Upper Cretaceous–Tertiary sedimentary successions with small outcrops of Quaternary deposits. Unmappable and very restricted thin layers of Palaeocene rocks are also encountered, but still under debate whether they are formed in situ or represent allochthonous remnants of Palaeocene age. The Upper Cretaceous rocks form low-lying to unmappable exposures and occupy the core of a major WSW-plunging anticline. To the west, south, and southeast, they are flanked by high-relief Eocene, Oligocene, and Lower Miocene rocks. Detailed structural analyses indicated structural inversion during Late Cretaceous–Miocene times in response to a right lateral compressional shear. The structural pattern is themed by the development of an E–W major shear zone that confines inside a system of wrench tectonics proceeded elsewhere by transpression. The deformation within this system revealed three phases of consistent ductile and brittle structures (D₁, D₂, and D₃) conformable with three main tectonic stages during Late Cretaceous, Eocene, and Oligocene–Early Miocene times. Quaternary deposits, however, showed at a local scale some of brittle structures accommodated with such deformation and thus reflect the continuity of wrenching post-the Miocene. D₁ deformation is manifested, in Late Cretaceous, via pure wrenching to convergent wrenching and formation of common E- to ENE-plunging folds. These folds are minor, tight, overturned, upright, and recumbent. They are accompanied with WNW–ESE to E–W dextral and N–S sinistral strike-slip faults, reverse to thrust faults and pop-up or flower structures. D₂ deformation initiated at the end of Lutetian (Middle Eocene) by wrenching and elsewhere transpression then enhanced by the development of minor ENE–WSW to E–W asymmetric, close, and, rarely, recumbent folds as well as rejuvenation of the Late Cretaceous strike-slip faults and formation of minor NNW–SSE normal faults. At the end of Eocene, D₂ led to localization of the movement within E–W major shear zone, formation of the early stage of the WSW-plunging Ras Al Hilal major anticline, preservation of the contemporaneity (at a major scale) between the synthetic WNW–ESE to E–W and ENE–WSW strike-slip faults and antithetic N–S strike-slip faults, and continuity of the NW–SE normal faults. D₃ deformation is continued, during the Oligocene-Early Miocene, with the appearance of a spectacular feature of the major anticline and reactivation along the E–W shear zone and the preexisting faults. Estimating stress directions assumed an acted principal horizontal stress from the NNW (N33°W) direction.     

Investigation of seasonal droughts and related large-scale atmospheric dynamics over the Potwar Plateau of Pakistan

As a result of climate change and unsustainable land use management in the recent past, droughts have become one of the most devastating climatic hazards whose impacts may prolong from months to years. This study presents analysis of droughts for two major cropping seasons, i.e., Kharif (May–September) and Rabi (October–April), over the Potwar Plateau of Pakistan. The analysis is performed using various datasets viz. observational, reanalysis, and Regional Climate Models (RCMs), for the past (1981–2010) and future (2011–2100) time periods. The following two methods for the identification of dry and wet years, also referred to as drought and wetness, are applied: (1) the percentile rank approach and (2) the drought indices, Standardized Precipitation Index (SPI) and Reconnaissance Drought Index (RDI). Future projections of droughts are investigated using RCM (RegCM4.4 and RCA4) outputs from CORDEX South Asia domain under two Representative Concentration Pathway (RCP) scenarios, RCP4.5 and RCP8.5. Generally, the indices show non-significant decreasing trends of drought severity in the recent past for all cases; however, significant increasing trends are observed for annual (0.006) and Kharif (0.007) cases under RCP4.5 scenario. The analysis of large-scale atmospheric dynamics suggests the significant role of low-level geopotential height anomalies over Tibetan Plateau (northwest of Pakistan) during Kharif (Rabi) season in controlling drought occurrence by transporting moisture from the Bay of Bengal (Arabian Sea). Moreover, composites of vertically integrated moisture transport, moisture flux convergence/divergence, and precipitable water anomalies show their marked contribution in maintaining the drought/wetness conditions over the Potwar region.     

On rising temperature trends of Karachi in Pakistan

Karachi is the largest city of Pakistan. The temperature change in Karachi is studied in this research by analyzing the time series data of mean maximum temperature (MMxT), mean minimum temperature (MMiT) and mean annual temperature (MAT) from 1947 to 2005 (59 years). Data is analyzed in three parts by running linear regression and by taking anomalies of all time periods: (a) whole period from 1947–2005; (b) phase one 1947–1975 and (c) phase two 1976–2005. During 1947 to 2005 MMxT has increased about 4.6°C, MMiT has no change and MAT has increased 2.25°C. During 1947–1975, MMxT increased 1.9°C, in this period there is − 1.3°C decrease in MMiT and MAT has raised upto 0.3°C. During 1976–2005, the MMxT, MMiT and MAT increased 2.7°C, 1.2°C and 1.95°C, respectively. The analysis shows significantly the role of extreme vulnerability of MMxT in rising the temperature of Karachi than the MMiT.     

Application of soft computing based hybrid models in hydrological variables modeling: a comprehensive review

Theoretical and Applied Climatology - Snow is a key element for many socioeconomic activities in mountainous regions. Due to the sensitivity of the snow cover to variations of temperature and...     

利用SRTM绘制东Sahara大型古排水盆地及其对南埃及新发展计划的影响(英文)

In the current study, the shuttle radar topography mission (SRTM) data, with～90 m horizontal resolution, were used to delineate the paleodrainage system and their mega basin extent in the East Sahara area. One mega-drainage basin has been detected, covering an area of 256 000 km2. It is classified into two sub mega basins. The Uweinate sub mega basin, which is composed of four main tributaries, collected water from a vast catchment region and drained eastward from the north, west, and southwest, starting at...     

Evaluation of Electro-Oxidation of Textile Effluent Using Response Surface Methods

In the present investigation, treatment of textile effluent using an electrochemical technique was designed and analyzed using the Box-Behnken method. The influence of individual parameters on electro-oxidation of textile effluent has been critically examined using the response surface method (RSM), and a quadratic model for chemical oxygen demand (COD) reduction has been developed. It has been observed from the present analysis that the predicted values are in good agreement with experimental data with a correlation coefficient of 0.945.