Adaptive neural-based fuzzy inference system (ANFIS) approach for modelling hydrological time series

Abstract

The main aim of this study is to develop a flow prediction method, based on the adaptive neural-based fuzzy inference system (ANFIS) coupled with stochastic hydrological models. An ANFIS methodology is applied to river flow prediction in Dim Stream in the southern part of Turkey. Application is given for hydrological time series modelling. Synthetic series, generated through autoregressinve moving-average (ARMA) models, are then used for training data sets of the ANFIS. It is seen that the extension of input and output data sets in the training stage improves the accuracy of forecasting by using ANFIS.     

The impact of subsurface conceptualization on land energy fluxes

There is a significant body of work demonstrating the importance of hydrologic control on land energy feedbacks. Yet, quantitative data on aquifer conductivity can be difficult to assemble. Furthermore, how subsurface uncertainty propagates into land-surface processes is not well understood. This study analyzes the impact of aquifer characterization on land energy fluxes, using a coupled hydrology–land-surface model. Four gridded subsurface conductivity fields are developed for the Upper Klamath basin using two data sources and different levels of imposed heterogeneity. Each model is forced with the same transient, observed meteorology for 3 years prior to the final year presented here. Results are analyzed to quantify the impact of subsurface heterogeneity on groundwater surface water interactions and spatial patterns in hydrologic variables. Analysis shows that heterogeneity does not fundamentally alter the connection between groundwater and land surface processes. However, differences between scenarios impact the extent and location of the critical zone.     

Optimizing artificial neural network-based indoor positioning system using genetic algorithm

Abstract

The Global Positioning System (GPS) is expected to play an integral role in the development of digital earth; however, the GPS cannot provide positioning information in regions where a majority of the population spends their time, that is, in urban and indoor environments. Hence, alternate positioning systems that work in indoor and urban environments should be developed to achieve the vision of digital earth. Wi-Fi-based positioning systems (WPS) stand out because of the near-ubiquitous presence of the associated infrastructure and signals in indoor environments. The WPS-based fingerprinting is the most widely adopted technique for position determination, but its accuracy is lower than that of techniques such as time of arrival and angle of arrival. Improving the accuracy is still a challenging task because of the complex nature of the propagation of Wi-Fi signals. Here, a novel server-based, genetic-algorithm-optimized, cascading artificial neural network-based positioning model is presented. The model is tested in 2D and 3D indoor environments under varying conditions. The model is thoroughly investigated on a real Wi-Fi network, and its accuracy is found to be better than that of other well-known techniques. A mean accuracy of 1.9 m is achieved with 87% of the distance error within the range of 0–3 m.     

Evaluation of environmental parameters in logistic regression models for landslide susceptibility mapping

Abstract

The aim of this study was to determine how well the landslide susceptibility parameters, obtained by data-dependent statistical models, matched with the parameters used in the literature. In order to achieve this goal, 20 different environmental parameters were mapped in a well-studied landslide-prone area, the Asarsuyu catchment in northwest Turkey. A total of 4400 seed cells were generated from 47 different landslides and merged with different attributes of 20 different environmental causative variables into a database. In order to run a series of logistic regression models, different random landslide-free sample sets were produced and combined with seed cells. Different susceptibility maps were created with an average success rate of nearly 80%. The coherence among the models showed spatial correlations greater than 90%. Models converged in the parameter selection peculiarly, in that the same nine of 20 were chosen by different logistic regression models. Among these nine parameters, lithology, geological structure (distance/density), landcover-landuse, and slope angle were common parameters selected by both the regression models and literature. Accuracy assessment of the logistic models was assessed by absolute methods. All models were field checked with the landslides resulting from the 12 November 1999, Kayna?li Earthquake (Ms = 7.2).     

An improved direction relation detection model for spatial objects

Direction is a common spatial concept that is used in our daily life. It is frequently used as a selection condition in spatial queries. As a result, it is important for spatial databases to provide a mechanism for modeling and processing direction queries and reasoning. Depending on the direction relation matrix, an inverted direction relation matrix and the concept of direction pre- dominance are proposed to improve the detection of direction relation between objects. Direction predicates of spatial systems are also extended. These techniques can improve the veracity of direction queries and reasoning. Experiments show excellent efficiency and performance in view of direction queries.     

A fast clonal selection algorithm for feature selection in hyperspectral imagery

Clonal selection feature selection algorithm (CSFS) based on clonal selection algorithm (CSA), a new computational intelligence approach, has been proposed to perform the task of dimensionality reduction in high-dimensional images, and has better performance than traditional feature selection algorithms with more computational costs. In this paper, a fast clonal selection feature selection algorithm (FCSFS) for hyperspectral imagery is proposed to improve the convergence rate by using Cauchy mutation instead of non-uniform mutation as the primary immune operator. Two experiments are performed to evaluate the performance of the proposed algorithm in comparison with CSFS using hyperspectral remote sensing imagery acquired by the pushbroom hyperspectral imager (PHI) and the airborne visible/infrared imaging spectrometer (AVIRIS), respectively. Experimental results demonstrate that the FCSFS converges faster than CSFS, hence providing an effective new option for dimensionality reduction of hyperspectral remote sensing imagery.     

Biophysical factors of remote sensing approach in urban green analysis

Greenery in an urban environment is an important consideration when studying temperature, and such enquiry can benefit human health. The purpose of this paper is to investigate how ambient temperature in urban areas is affected by forests and parks. The focus is on biophysical parameters related to these green areas, such as impervious surface percentages, albedo, areal coverage, elevation, and leaf area index (LAI). Geographic information systems and remote sensing were used to quantify green spaces using a pixel-based method. It was found that coverage area has little correlation with temperature. Factor analysis was used to determine the minimum number of independent factors, which explained 63% of the variance of that temperature. Only elevation, LAI and albedo were significant biophysical factors. Guidelines for greenery programmes should include these significant data-sets to understand the influence of green areas on heat reduction.     

Upscaling the resilience assessment through comparative analysis

Resilience is the capacity of any system to maintain its function, structure and identity despite disturbances. Assessing resilience has been elusive due to high levels of abstraction that are difficult to empirically test, or the lack of high quality data required once appropriate proxies are identified. Most resilience assessments are limited to specific situation arenas, making comparision one of the unresolved challenges. Here we show how leveraging comparative analysis can provide insights on how Arctic communities (N = 40) can best deal with social and environmental change. We found that the capacity to self-organize, and nurturing diversity are sufficient conditions for Arctic communities whose livelihoods have been resilient, or for communities whose livelihoods have been transformed. Our study provides an alternative perspective on how to assess resilience by leveraging comparsion across cases. It also identify governance patways to support adaptations and transformations in the Arctic, a geography with some of the most dramatic social and natural challenges to come.     

Understanding interlinkages between long-term trajectory of exposure and vulnerability,path dependency and cascading impacts of disasters in Saint-Martin (Caribbean)

This empirical and interdisciplinary study investigates the contribution of deeply enrooted social-political factors to the accumulation of exposure and vulnerability and amplification of cascading impacts of disasters, with implications on the creation and reinforcement of path dependency maintaining social-ecological systems on a maladaptive trajectory. Applying the Trajectory of Exposure and Vulnerability approach to Saint-Martin (Caribbean), we more specifically highlight how the causal chain linking historical geopolitical and political-institutional drivers to legal, economic, demographic, sociocultural, planning-related and environmental drivers, created the accumulation of exposure and vulnerability over time and contributed to the propagation and amplification of the impacts of tropical cyclones Irma and José in 2017. We find that historical social-political dynamics involving unsustainable development and settlement patterns, the weakness of local institutions, population mistrust in public authorities, high social inequalities and environmental degradation maintained Saint-Martin on a maladaptive trajectory through powerful reinforcing mechanisms operating both between and during cyclonic events. This study demonstrates that long-term interdisciplinary approaches are required for a better understanding of path dependency and the identification of levers to break it in risk-prone contexts. In Saint-Martin, breaking path dependency requires the alignment of local institutional capacities with national risk reduction policies, the promotion of social justice and involvement of local communities in decision making. This study therefore confirms the relevance of backward-looking approaches to support forward-looking climate adaptation.     

层序地层学研究进展:国际层序地层学研讨会综述

结合"国际层序地层学研讨会"的相关内容,阐述了层序地层学理论和技术方法研究的进展;内容包括碎屑岩层序地层学(涉及海相、湖相、河流相等)、碳酸盐岩层序地层学、煤和其他沉积物层序地层学、层序地层标准化等领域的重要研究成果及其在常规油气与非常规油气勘探中的应用。最后指出了层序地层学未来的发展趋势,主要为研究方法标准化及应用地区特殊化,尤其要加强深水层序、碳酸盐岩层序、层序模拟等方面的研究。