Abstract:Recent research has shown that using spectral-spatial information can considerably improve the performance of hyperspectral image (HSI) classification. HSI data is typically presented in the format of 3D cubes. Thus, 3D spatial filtering naturally offers a simple and effective method for simultaneously extracting the spectral-spatial features within such images. In this paper, a 3D convolutional neural network (3D-CNN) framework is proposed for accurate HSI classification. The proposed method views the HSI cube data altogether without relying on any preprocessing or post-processing, extracting the deep spectral-spatial-combined features effectively. In addition, it requires fewer parameters than other deep learning-based methods. Thus, the model is lighter, less likely to over-fit, and easier to train. For comparison and validation, we test the proposed method along with three other deep learning-based HSI classification methods-namely, stacked autoencoder (SAE), deep brief network (DBN), and 2D-CNN-based methods-on three real-world HSI datasets captured by different sensors. Experimental results demonstrate that our 3D-CNN-based method outperforms these state-of-the-art methods and sets a new record.
Six mercury-resistant environmental proteobacterial isolates and one genetically modified mercury-resistant Pseudomonas putida strain were analyzed for physiological traits of adaptive relevance in an environment of packed-bed bioreactors designed for the decontamination of mercury-polluted chlor-alkali wastewater. The strains displayed characteristic differences in each trait (i.e., biofilm formation capability, growth rate in mercury contaminated wastewaters, and mercury reduction efficiency). Subsequently, they were immobilized either as a monoculture or as a mixed culture on porous carrier material in packed-bed bioreactors through which different batches of filter-sterilized industrial chlor-alkali wastewater were pumped. In monospecies bioreactors, the mercury retention efficiency was sensitive to rapidly increasing mercury concentrations in the wastewater. Mixed culture biofilms displayed a high mercury retention efficiency that was not affected by rapid increases in mercury or continuously high mercury concentrations. The dynamic in the community composition of the mixed culture bioreactors was determined by ribosomal intergenic spacer polymorphism analysis. Mercury-mediated selective pressure decreased the number of prevalent strains. Microbial diversity was completely restored after easing of the selective pressure. Microbial diversity provides a reservoir of strains with complementary ecological niches that results in a superior bioreactor performance under changing environmental conditions.Mercury cycles through the environment as a result of both natural and human activities. The human activities that are most responsible for mercury emissions are (i) the incineration of mercury-containing fuels and materials and (ii) industrial processes such as those utilized in the mercury cell chlor-alkali industry. Without appropriate retention devices, mercury is released into the environment in substantial amounts (6,19,31). Once mercury enters waters, either directly or through air deposition, inorganic mercury can be methylated abiotically or biotically to its most toxic form, methylmercury (1, 24). Methylmercury biomagnifies readily in the food chain, endangering ecosystems and public health. In the United States it is estimated that ca. 60,000 babies per year are born with neurological damage caused by mercury poisoning of their mothers upon consuming mercury-contaminated fish during pregnancy (29). In freshwater ecosystems, methylmercury bioaccumulation is more common than in salinic environments (4, 13). Hence, it is of great importance for environment and public health to stop mercury dumping into river ecosystems.In previous experiments we demonstrated a new, cost-effective, and environmentally friendly end-of-pipe technology: the efficient retention of mercury from chemical wastewater by mercury-resistant bacteria in packed-bed bioreactors in laboratory and technical scale (37, 40). The basic principle of this process is the enzymatic reduction of ionic mercury Hg(II) to metallic mercury Hg(0) by mer...
The enzymatic reduction of Hg(II) to water insoluble Hg(0) by mercury resistant bacteria has been used for removal of mercury from wastewater in technical scale. Pure cultures of seven mercury resistant strains of Pseudomonas were immobilized on carrier material inside a 700 L packed bed bioreactor. Neutralized chloralkali electrolysis wastewater with a mercury concentration of 3−10 mg/L was continuously fed into the bioreactor (0.7 m3/h up to 1.2 m3/h). A mercury retention efficiency of 97% was obtained within 10 h of inoculation of the bioreactor. At optimum performance, bioreactor outflow concentrations were below 50 μg Hg/L, which fulfill the discharge limit for industrial wastewater. In combination with an activated carbon filter, outflow concentrations below 10 μg Hg/L were always obtained. The retention efficiency of the bioreactor was not affected by fluctuations in inflow conductivity (between 20 and 105 mS/cm), pH (between 6.5 and 7.5), or mercury concentration (between 3 and 10 mg/L) and was between 95% and 99%. Temperature increases up to 47 °C did not impair bioreactor performance. Standby periods up to 6 h could be tolerated without loss in activity. A simple, effective, and robust biotechnology for remediation of mercury polluted wastewater is thus demonstrated.
Mercury-contaminated chemical wastewater of a mercury cell chloralkali plant was cleaned on site by a technical-scale bioremediation system. Microbial mercury reduction of soluble Hg(II) to precipitating Hg(0) decreased the mercury load of the wastewater during its flow through the bioremediation system by up to 99%. The system consisted of a packed-bed bioreactor, where most of the wastewater's mercury load was retained, and an activated carbon filter, where residual mercury was removed from the bioreactor effluent by both physical adsorption and biological reduction. In response to the oscillation of the mercury concentration in the bioreactor inflow, the zone of maximum mercury reduction oscillated regularly between the lower and the upper bioreactor horizons or the carbon filter. At low mercury concentrations, maximum mercury reduction occurred near the inflow at the bottom of the bioreactor. At high concentrations, the zone of maximum activity moved to the upper horizons. The composition of the bioreactor and carbon filter biofilms was investigated by 16S-23S ribosomal DNA intergenic spacer polymorphism analysis. Analysis of spatial biofilm variation showed an increasing microbial diversity along a gradient of decreasing mercury concentrations. Temporal analysis of the bioreactor community revealed a stable abundance of two prevalent strains and a succession of several invading mercury-resistant strains which was driven by the selection pressure of high mercury concentrations. In the activated carbon filter, a lower selection pressure permitted a steady increase in diversity during 240 days of operation and the establishment of one mercury-sensitive invader.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.