An adaptive framework for spectral-spatial classification based on a combination of pixel-based and object-based scenarios

Remotely sensed image analysis using spectral-spatial information plays a key role in modern remote sensing applications. This article presents a new semi-automatic framework for spectral-spatial classification of hyperspectral images. The proposed framework benefits from a combination of pixel-based and object-based classification scenarios in which the main parameters are adaptively tuned. In order to reduce the complexity of the method, an unsupervised band selection technique is used as well. Meanwhile, the wavelet thresholding is applied in order to smooth the selected bands. The classification results after applying the proposed method to well-known standard hyperspectral datasets are better than those of the most of the other state-of-the-art approaches. As an example, the overall classification accuracy achieved by applying the proposed semi-automatic spectral-spatial classification framework to the Salinas dataset is more than 99% for 10% training samples per class. Moreover, the vital parameters are adaptively set in our approach.     

Geologic hazards along part of Al-sayl–Alkabeir Al-Jammum road in Saudi Arabia

 The geological hazards along part of Al-Sayl Alkabeir Al-Jammum road, western Saudi Arabia, were studied by the use of the sterographic projection to define the types of possible failures and the magnitude of safety factor on each slope face. The studied area consists of granite and granodiorite rocks that were cut by acidic and basic dikes. There are four sets of structural discontinuities which, besides a few strike slip faults, constitute the planes of weakness that lead to a variety of possible mode failures. The stability analysis indicates that sections of the road are unstable as their cut slopes exceed the maximum safe slope angles which range between 65° and 73°. Received: 16 June 1998 · Accepted: 2 March 1999     

On analysis and prediction of tides on the west coast of Great Britain

Summary. Long-period tidal records from eight ports on the west coast of Great Britain are analysed, using both the harmonic method and the response function. Time series up to 9.5 yr were used so that fine structure of certain regions of high energy in the tidal residual spectrum may be examined. This also assisted in accurate separation of tides from surges. According to the currently accepted formulation of M₁, its composition is not compatible with its actual composition in the real tide and, as such, has no useful purpose to serve in computation of predictions. Constituents Sa, Ssa, MA, and MB, are adversly affected by weather and long records are essential for their accurate separation. It has been observed that annual perturbations of S₂, similar to those confirmed in recent years for M₂, also exist but these are not readily recognisable because their speeds are the same as those of constituents T₂ and R₂. These perturbations, being highly sensitive to meteorological forces, are mainly responsible for cusps or humps in the vicinity of major tidal constituents in tidal residual spectra. The relationship of radiational and gravitational tides is found to be in very good agreement with theoretical results. In summer months non-predictable variance reduces to about half of the annual variance, reflecting the regional weather conditions of summer and winter.     

Biosorption of 4-chlorophenol by dried anaerobic digested sludge: artificial neural network modeling,equilibrium isotherm,and kinetic study

In this study, dried anaerobic digested sludge (DADS) was utilized to remove 4-chlorophenol (4-CP) from aqueous solutions. Batch biosorption experiments were carried out to investigate the effects of physicochemical parameters such as pH, contact time, biosorbent dosage, and initial concentration. Artificial neural network (ANN) was then used to predict the removal efficiency of the process. The comparison between predicted and experimental results provided a high degree of determination coefficient (R² = 0.98), indicating that the model could predict the biosorption efficiency with reasonable accuracy. Biosorption data were successfully described by the Freundlich isotherm and pseudofirst-order model. The Weber–Morris kinetic model indicated that intraparticle diffusion was not the only rate-controlling step, and other mechanisms may be involved in the biosorption process. The optimum pH was detected to be 3 for DADS. By increasing contact time and biosorbent dosage, the removal efficiency of 4-CP increased. Also, a decreasing trend was observed when initial concentrations were increased. The findings suggested that the results predicted by ANN are very close to the experimental values, and DADS as an available adsorbent can efficiently remove 4-CP from aqueous solutions.     

Removal of cadmium and humic acid from aqueous solutions using surface modified nanozeolite A

The sorption of cadmium and humic acids from aqueous solutions using surface-modified nanozeolite A has been investigated under various examination conditions. The morphology of untreated and treated nanozeolite was studied under scanning electron microscope and transmission electron microscope. Isotherms of cadmium adsorption onto surface-modified nanozeolite A were studied at different pH, solid to liquid ratio, adsorbate concentration and interaction time. Kinetic and equilibrium studies were conducted and the equilibrium data have been analyzed using Langmuir and Freundlich isotherm models. The study revealed that experimental results were in agreement with the Freundlich model. The Langmuir monolayer adsorption capacity was found to be 1666.67 g cadmium and 6.75 g humic acid per gram of modified nanozeolite A, which is higher than that of reported value for other zeolites. The sorption ability was enhanced by surface modification and reduction in size and enabled the zeolite to adsorb cadmium. The adsorption of cadmium and humic acid on nanozeolite was found to be the highest at pH 6 and 3, respectively. Results showed that solid to liquid ratio and pH are the most important factors for cadmium and humic acid removal, respectively. Effect of competitive ions was studied and results showed that there is no competition between cadmium and humic acid sorption and presence of these ions.     

Time dependent chemical study of contracting interstellar clouds. III. the charge distribution in interstellar clouds

We have constructed a chemical reaction model in a contracting interstellar cloud including 104 species which are involved in a network of 557 reactions. The chemical kinetic equations were integrated as a function of time by using gear package. The evolution of the system was followed in the density range 10–10⁷ particles cm^-3.The calculated fractional abundances of the charged species are in good agreement with those given by other investigators. The charge density has been followed in diffuse, intermediate and dense regions. The most dominant ionic species are metallic ions, HCO⁺ and H ₃ ⁺ in the shielded regions and atomic ions H⁺, C⁺, Si⁺, He⁺, S⁺ and metal ions in the diffuse and intermediate regions. The abundances of negatively charged ions were found to be negligible. The results of the calculations on the different metallic ions are interpreted.     

Seasonal Short‐Term Prediction of Dissolved Oxygen in Rivers via Nature‐Inspired Algorithms

This study challenges the use of three nature‐inspired algorithms as learning frameworks of the adaptive‐neuro‐fuzzy inference system (ANFIS) machine learning model for short‐term modeling of dissolved oxygen (DO) concentrations. Particle swarm optimization (PSO), butterfly optimization algorithm (BOA), and biogeography‐based optimization (BBO) are employed for developing predictive ANFIS models using seasonal 15 min data collected from the Rock Creek River in Washington, DC. Four independent variables are used as model inputs including water temperature (T), river discharge (Q), specific conductance (SC), and pH. The Mallow's Cp and R² parameters are used for choosing the best input parameters for the models. The models are assessed by several statistics such as the coefficient of determination (R²), root‐mean‐square error (RMSE), Nash–Sutcliffe efficiency, mean absolute error, and the percent bias. The results indicate that the performance of all‐nature‐inspired algorithms is close to each other. However, based on the calculated RMSE, they enhance the accuracy of standard ANFIS in the spring, summer, fall, and winter around 13.79%, 15.94%, 6.25%, and 12.74%, respectively. Overall, the ANFIS‐PSO and ANFIS‐BOA provide slightly better results than the other ANFIS models.     

An approach to the problem of coastal erosion in quaternary sediments

Approximately 40 per cent of the shorelines of the lower Great Lakes are backed by relatively weak Quaternary sediments, and similar shorelines are found on many middle and high-latitude coasts. The high rates of bluff recession which are characteristic of these areas lead to economic losses through erosion of land and damage to buildings, and may prompt a wide range of measures designed to reduce erosion and protect property. Assessment of the physical problem and of possible solutions to it can best be achieved through a sediment budget approach. This is illustrated through a case study of an area near Grimsby, Ontario. The volume of sediment supply to the beach was calculated from measurements of bluff height and annual recession rates. The potential volume of longshore sediment transport was determined from the wave climate of the area and computer modelling of wave refraction. The relationship between sediment supply and potential transport rate can be used to assess the magnitude of the sediment deficit or surplus at points along the shoreline, and this provides an insight into the controls on alongshore variations in recession rates.     

Time dependent chemical study of contracting interstellar clouds. I. Abundances of nitrogen- and carbon-bearing molecules

We have constructed a reaction system containing the chemical families of H, C, O, N, S, Si, Cl, metals (Me) and grains. A total of 104 species have been included and a network of 557 reactions has been studied. The chemical kinetic equations were integrated as a function of time by using gear program. The chemical reaction system was followed at low, intermediate and high cloud densities i.e. from 10–10⁷ particles cm^-3. The calculated fractional abundances of N₂, CN, HCN, and CH which are in good agreement with the results of observations and with those of previous theoretical studies.