Search

Machine learning classifiers have been widely used for crop mapping; however, employing numerous features can reduce classifier accuracy. Feature selection is a widely recognized technique that addresses the issue of high dimensionality by choosing the most relevant subset of features with the highest degree of relevance and practicality. Therefore, the optimal combination of feature selection methods and classifiers for high-precision crop mapping remains an open problem. In this study, we introduce a novel hybrid feature selection approach to obtain the optimal subset of features for effective crop mapping. Initially, spectro-temporal remote sensing features from the dataset were ranked using two distinct feature selection techniques: Mutual Information (MI) and ReliefF filter. The most relevant features from each filter-based approach were combined into a union subset. Subsequently, the Gray Wolf Optimization (GWO), a metaheuristic optimization technique, was applied to enhance the feature set generated in the initial step. In the final stage, a random forest classifier leveraged the optimized feature subset for accurate crop type prediction. The effectiveness of the proposed approach was evaluated in Behiera governorate, Egypt. Comparative analysis against existing crop mapping methods demonstrated the superior performance of the proposed approach, achieving an accuracy rate of 82%. Furthermore, this approach showcased a significant reduction in the feature count, streamlining the set from 308 down to only 26 features. [ABSTRACT FROM AUTHOR]

This paper provides a novel, unique, and improved optimization algorithm called the modified Orca Predation Algorithm (mOPA). The mOPA is based on the original Orca Predation Algorithm (OPA), which combines two enhancing strategies: Lévy flight and opposition-based learning. The mOPA method is proposed to enhance search efficiency and avoid the limitations of the original OPA. This mOPA method sets up to solve the global optimization issues. Additionally, its effectiveness is compared with various well-known metaheuristic methods, and the CEC'20 test suite challenges are used to illustrate how well the mOPA performs. Case analysis demonstrates that the proposed mOPA method outperforms the benchmark regarding computational speed and yields substantially higher performance than other methods. The mOPA is applied to ensure that all load demand is met with high reliability and the lowest energy cost of an isolated hybrid system. The optimal size of this hybrid system is determined through simulation and analysis in order to service a tiny distant location in Egypt while reducing costs. Photovoltaic panels, biomass gasifier, and fuel cell units compose the majority of this hybrid system's configuration. To confirm the mOPA technique's superiority, its outcomes have been compared with the original OPA and other well-known metaheuristic algorithms. [ABSTRACT FROM AUTHOR]

The crop coefficient (Kc) is a scaling factor to calculate crop evapotranspiration (ETc). Accurate prediction of Kc affects planning to allocate water resources, especially in arid and semi-arid areas with limited water sources availability. The conventional FAO approach has some limited applications due to using plant characteristics. However, existing artificial intelligence approaches have high performances, but encounter some instability in prediction. In the present study, the generalized likelihood uncertainty estimation (GLUE) approach was applied to assess uncertainties arising from both model structure and input parameters. In addition, this study aims to derive the explicit predictive and usable equation for calculating the monthly Kc of maize. The equations were developed from the best hybrid MLP model using minimal meteorological data in four regions of Egypt. For this, the predictive utility of MLP-based models that hybridized with meta-heuristic optimization algorithms was examined. The rat swarm optimization (RSO), firefly algorithm (FFA), bat algorithm (BA), and genetic algorithm (GA) hybridized with MLP (MLP-RSO, MLP-FFA, MLP-BA, and MLP-GA) are used as equation derivation tools. The results showed that a unique hybrid Gamma Test-RSO is a powerful approach for determining the optimal combination (Tmax, Tmin, Rs) as the best input vector. The results showed that the hybrid MLP-RSO model decreased the average RMSE by 13.87, 39.95, 45.68, and 53.09% than MLP-BA, MLP-FFA, MLP-GA, and MLP models, respectively. In addition, the uncertainty results showed that the Kc predictions were more stable and confident in MLP-RSO, while the average of 95PPU covered 94.5 and 91.5% of actual Kc for input parameters and model structure uncertainties, respectively. In conclusion, the developed hybrid model and the techniques illustrated in the current study suggest substantial benefits for other researchers to derive mathematical equations from easily available meteorological variables in different regions and climates. Also, the findings provide a fundamental guideline for the local water users and agricultural development planners to achieve accurate and fast irrigation scheduling. [ABSTRACT FROM AUTHOR]

Metaheuristic algorithms are increasingly being utilized as a global optimal method in the inversion and modeling of magnetic data. We proposed the Bat Algorithm Optimization (BAO) technique that is based on bat echolocation performance to find the global optimum solution. The best-estimated source parameters that correspond to the objective function minimum value are obtained after achieving the global optimum (best) solution. The suggested BAO technique does not require any prior knowledge; rather, it is a global search method that provides an effective tool for scanning the space of data to appraise sources parameters. The BAO technique is applied to magnetic data in the class of dipping and vertical dikes along 2D profiles to estimate the dimensional source parameters that include the depth to top, origin location, amplitude coefficient, index angle of magnetization, and width of the dipping dikes. The BAO technique has been used for single and multiple dikes structures. The accuracy and stability of the BAO technique are achieved on different synthetic examples of free and noisy data for single and multiple cases. Furthermore, the presented BAO technique was effectively utilized in three field examples from China and Egypt for iron ore deposits and metavolcanics basalt rock investigations. Overall, the BAO technique recovered inversion outcomes are in good agreement with borehole, geology, and published literature results. [ABSTRACT FROM AUTHOR]

Increasing the energy extracted from the wind is of great importance because wind energy is renewable and inexhaustible. Based on this research, wind cubes are placed in front of wind turbines to improve airflow on turbine blades and maximize the energy produced by the turbine. The previous design of the wind cubes was crude and did not adhere to any scientific principles. This study proposes a novel method for obtaining optimum output from wind turbines throughout the year regardless of wind speed fluctuations by optimizing a design of the front and rear diameters of the wind cubes while also setting the lowest cost criterion within the design circumstances. An optimizer of this design employs several optimization techniques, including the cuckoo search optimization algorithm (CSA), the grey wolf optimizer (GWO), the sine cosine algorithm (SCA), and the moth flame optimizer (MFO). In the MATLAB environment, simulations and programs were created and performed. The CSA, GWO, SCA, and MFO all yield the same optimum design values, but the arrival time of the best solution is the mean difference between them, and a comparison of their arrival times is presented. Using data from four turbines in Zafarana, Egypt's Red Sea Governorate, the researchers found that wind energy may grow up to 56 times. [ABSTRACT FROM AUTHOR]

The main objective of hyper/multispectral image fusion is producing a composite color image that allows for an appropriate visualization of the relevant spatial and spectral information. In this paper, we propose a general framework for spectral weighting-based image fusion. The proposed methodology relies on weight updates conducted using nature-inspired algorithms and a goodness-of-fit criterion defined as the average root mean square error. Simulations on four public data sets and a recent Landsat 8 image of Brullus Lake, Egypt, as an area of study prove the efficiency of the proposed framework. The purpose of the study is to present a framework of multi-band image fusion that produces a fused image of high quality to be further used in computer processing and the results show that the image produced by the presented framework has the highest quality compared with some of the state-of-the art algorithms. To prove the increase in the image quality, we used general quality metrics such as Universal Image Quality Index, Mutual Information, the Variance and Information Measure. [ABSTRACT FROM AUTHOR]

Renewable energy is a safe and limitless energy source that can be utilized for heating, cooling, and other purposes. Wind energy is one of the most important renewable energy sources. Power fluctuation of wind turbines occurs due to variation of wind velocity. A wind cube is used to decrease power fluctuation and increase the wind turbine's power. The optimum design for a wind cube is the main contribution of this work. The decisive design parameters used to optimize the wind cube are its inner and outer radius, the roughness factor, and the height of the wind turbine hub. A Gradient-Based Optimizer (GBO) is used as a new metaheuristic algorithm in this problem. The objective function of this research includes two parts: the first part is to minimize the probability of generated energy loss, and the second is to minimize the cost of the wind turbine and wind cube. The Gradient-Based Optimizer (GBO) is applied to optimize the variables of two wind turbine types and the design of the wind cube. The metrological data of the Red Sea governorate of Egypt is used as a case study for this analysis. Based on the results, the optimum design of a wind cube is achieved, and an improvement in energy produced from the wind turbine with a wind cube will be compared with energy generated without a wind cube. The energy generated from a wind turbine with the optimized cube is more than 20 times that of a wind turbine without a wind cube for all cases studied. [ABSTRACT FROM AUTHOR]

This paper mainly focuses on the optimal design of a grid-dependent and off-grid hybrid renewable energy system (RES). This system consists of Photovoltaic (PV), Wind Turbine (WT) as well as Fuel Cell (FC) with hydrogen gas tank for storing the energy in the chemical form. The optimal components sizes of the proposed hybrid generating system are achieved using a novel metaheuristic optimization technique. This optimization technique, called Improved Artificial Ecosystem Optimization (IAEO), is proposed for enhancing the performance of the conventional Artificial Ecosystem Optimization (AEO) algorithm. The IAEO improves the convergence trends of the original AEO, gives the best minimum objective function, reaches the optimal solution after a few iterations numbers as well as reduces the falling into the local optima. The proposed IAEO algorithm for solving the multiobjective optimization problem of minimizing the Cost of Energy (COE), the reliability index presented by the Loss of Power Supply Probability (LPSP), and excess energy under the constraints are considered. The hybrid system is suggested to be located in Ataka region, Suez Gulf (latitude 30.0, longitude 32.5), Egypt, and the whole lifetime of the suggested case study is 25 years. To ensure the accurateness, stability, and robustness of the proposed optimization algorithm, it is examined on six different configurations, representing on-grid and off-grid hybrid RES. For all the studied cases the proposed IAEO algorithm outperforms the original AEO and generates the minimum value of the fitness function in less execution time. Furthermore, comprehensive statistical measurements are demonstrated to prove the effectiveness of the proposed algorithm. Also, the results obtained by the conventional AEO and IAEO are compared with those obtained by several well-known optimization algorithms, Particle Swarm Optimization (PSO), Salp Swarm Algorithm (SSA), and Grey Wolf Optimizer (GWO). Based on the obtained simulation results, the proposed IAEO has the best performance among other algorithms and it has successfully positioned itself as a competitor to novel algorithms for tackling the most complicated engineering problems. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSN) are the backbone in various modern Internet of Things (IoT) smart applications ranging from automated control, surveillance, forest fire detection, etc. One of the most important applications is the smart agriculture. The deployment of WSN in agricultural processes can predict crop yield, soil temperature, air quality, water level, crop price, and the appropriate time for market delivery which will help to increase productivity. In this paper, an enhanced metaheuristic algorithm called multi-verse optimizer with overlapping detection phase (DMVO) is introduced for optimizing the area coverage percentage of WSN. The proposed algorithm is tested on many datasets with different criterions and is compared with other algorithms including the original MVO, particle swarm optimization, and flower pollination algorithm. The experimental results are analyzed with one-way ANOVA test. In addition, DMVO is applied to IoT smart agriculture in East Oweinat area in Egypt and compared with Krill Herd algorithm. In addition, the experimental results are analyzed with Wilcoxon signed-rank test. The experimental results and the statistical analysis prove the prosperity and consistency of the proposed algorithm. [ABSTRACT FROM AUTHOR]

• Proposing an improved Archimedes optimization algorithm and comparing it with other known algorithms. • Applying the IAOA on 23 benchmarking functions to prove the ability of the new algorithm. • Applying the IAOA to design a hybrid renewable energy system based on several configurations. • The case study in Farafra showed that PV and wind turbines could give the lowest cost of energy and efficient system. The Improved Archimedes Optimization Algorithm (IAOA) is presented and applied to design a hybrid renewable energy system (HRES) for a microgrid system in the Farafra region of Egypt. The studied microgrid consists of three scenarios based on PV panels, wind turbine systems, diesel generators, and a battery energy storage system (BESS). The objective is to minimize the design function of the net present cost (NPC) that englobes all expenses during the project lifetime, respecting three constraints: the renewable fraction index, loss of power supply probability, and availability. The simulation results are compared with several known algorithms, such as the original Archimedes optimization algorithm (AOA), artificial electric field algorithm (AEFA), Equilibrium optimizer (EO), Grey Wolf optimizer (GWO), and Harris Hawks Optimization (HHO) algorithms. The results prove the ability of the proposed algorithm to solve the problem design, and they also demonstrate its superior efficiency to competing algorithms. The best-found HRES is the PV panel/wind turbine/diesel generator/battery storage system HRES, the NPC is $187,181, equivalent to cost energy (LCOE) of 0.213 $/kWh. The constraints are respected, the reliability is approximately 5%, the renewable fraction index is close to 90%, and the availability is approximately 100%. From the results, it is observed that the synergy of PV and wind systems is mandatory in such areas, and the battery also plays an important role in managing and arranging the energetic flow in HRES systems. The benchmark functions are tested using 23 functions, which proved that the IAOA performed better than the original AOA algorithm. [ABSTRACT FROM AUTHOR]

In this work, we backtest and compare, under the VaR risk measure, the fitting performances of three classes of density distributions (Gaussian, Stable and Pareto) with respect to three different types of emerging markets: Egypt, Qatar and Mexico. We also propose a new technique for the estimation of the Pareto tail index by means of the Threshold Accepting (TAVaR) and the Hybrid Particle Swarm Optimization algorithm (H-PSOVaR). Furthermore, we test the accuracy and robustness of our estimates demonstrating the effectiveness of the proposed approach. • We test the Normal, Stable and Pareto fitting properties over three emerging markets. • We propose two metaheuristic VaR based algorithms, i.e., the TAVaR and the H-PSOVaR. • We run a Monte Carlo simulation to assess the performances of the proposed algorithms. • We test the estimates robustness by measuring their sensitivity to data contamination. [ABSTRACT FROM AUTHOR]

[Display omitted] • Optimal sizing of hydrogen-based renewable microgrid at three different regions. • Hybridizing metaheuristic optimizers to maximize renewables and hydrogen share. • Economic viability and technical effectiveness of integrating hydrogen technology. • Considering the greenhouse gas emissions reduction of hydrogen-based microgrids. • Investigating hydrogen maturity and risk analysis through readiness levels. The paper proposes a hybrid microgrid (HMG) system with solar modules and wind turbines as primary energy sources and a diesel engine as backup. Meanwhile, the hydrogen energy storage system (HySS) is utilized as energy storage. Firstly, by reducing the levelized cost of energy (COE), this study presents the optimal size and configuration of various renewable and distributed energy resources in HMG systems. Secondly, two novel modified hybridized particle swarm optimization (PSO) and ant colony optimization (ACO) are developed, namely, ACO initialized PSO and ACO updated PSO. The optimal simulation results using PSO and ACO metaheuristic technique either individually or hybridized are compared in terms of primarily minimizing the levelized COE and achieving short execution time. Thirdly, to verify the geographical-independency of the integration of HySS for producing onsite green hydrogen locally, the estimation performance is examined for three different locations in Egypt, Mozambique and Denmark respectively using hourly meteorological and load data in 2019. Sensitivity and effectiveness analysis are carried out to highlight the major parameters that impact HySS incorporation. Finally, the system readiness level together with the different hydrogen, economy barriers constraints, limitations and risks are investigated based on the technology readiness level and the integration readiness level indices. The simulation results demonstrate the superiority of the ACO updated PSO optimization algorithm towards minimizing the levelized COE in the different regions. In the developing countries, the salvage market supports HySS integration. At system readiness levels range between 0.65 and 0.94, versatile HySS integration is verified. [ABSTRACT FROM AUTHOR]

The paper proposes four hybrid storage options: battery-supercapacitor, battery-flywheel, battery-pumped hydro storage, and battery-fuel cell. A probabilistic approach based on the artificial neural network is implemented to cover the weather uncertainty. The developed options and the approach are combined with comprehensive eco-techno-economic optimization study. Multi-objective optimization scenarios are investigated to reduce either/both total cost or/and greenhouse gas (GHG) emissions considering Utopia point approach. Two new hybrid particle swarm optimization - grasshopper optimization algorithm (PSO-GOA) methods are developed: GOA updated PSO and GOA initialized PSO algorithms. The effectiveness of the developed optimizers and the Utopia point approach are validated. Sensitivity analysis is performed to demonstrate the variable parameters that majorly influence the investment costs and GHG emissions. Through numerical simulations via Matlab™, PV modules rating power, number of wind turbines, and the load demand are the key factors that impact the eco-techno-economic at Qusair city, Egypt. Through the Utopia point solution, supercapacitor integrated battery demonstrates enhancements by 42.48% and 12.92% in the GHG and levelized cost of energy (LCOE) compared to the economic and environmental solutions. The salvage market fosters the hybrid flywheel and pump hydro storage integrated battery options by reducing the LCOE by 44% and 51%, respectively. [ABSTRACT FROM AUTHOR]