The problem of Small Area Estimation (SAE) is complex because of various information sources and ... more The problem of Small Area Estimation (SAE) is complex because of various information sources and insufficient data. In this paper, an approach for SAE is presented for decision-making at national, regional and local level. We propose an Empirical Best Linear Unbiased Predictor (EBLUP) as an estimator in order to combine several information sources to evaluate various indicators. First, we present the urban audit project and its environmental, social and economic indicators. Secondly, we propose an approach for decision making in order to estimate indicators. An application is used to validate the theoretical proposal. Finally, a decision support system is presented based on open-source environment.
Payments for ecosystem services (PES) have increasingly been applied as economic incentives for i... more Payments for ecosystem services (PES) have increasingly been applied as economic incentives for improving ecosystem services around the world. However, due to difficulties in measuring and attributing ecosystem services provisioning, a land-based approach has been popularly adopted as a proxy for the desired ecosystem services. In this study, we demonstrate the impact mechanism and outcomes of locally financed PES programs on conservation-based land use in a developed area of China. We present this work using a PES-land use proxy framework that is examined empirically through a variety of qualitative assessments. Our framework illustrates that, within the ecological, socioeconomic, and institutional conditions of developed areas, land use class, pattern and function would be impacted by (a) conservation effect, (b) stakeholder response, and (c) institutional adaptation mechanisms of local PES programs, with multiple land use trends as potential outcomes. We examine the framework using materials from Suzhou, China, which has implemented a top-down, partly involuntary (ecosystem services supply side), land based PES program. Our results show that, expected land use class, land use pattern and land use function are observed in areas where the PES programs were implemented. We also find that the conditions of developed areas and locally financed payments mechanism indeed played a crucial role in promoting conservation-based land use in Suzhou.
Abstract This study introduces a novel framework for land change simulation that combines the tra... more Abstract This study introduces a novel framework for land change simulation that combines the traditional Land Transformation Model (LTM) with data clustering tools for the purposes of conducting land change simulations of large areas (e.g., continental scale) and over multiple time steps. This framework, called “LTM-cluster”, subsets massive land use datasets which are presented to the artificial neural network-based LTM. LTM-cluster uses the k-means clustering algorithm implemented within the Spark high-performance compute environment. To illustrate the framework, we use three case studies in the United States which vary in simulation extents, cell size, time intervals, number of inputs, and quantity of urban change. Findings indicate consistent and substantial improvements in accuracy performance for all three case studies compared to the traditional LTM model implemented without input clustering. Specifically, the percent correct match, the area under the operating characteristics curve, and the error rate improved on average of 9%, 11%, and 4%. These results confirm that LTM-cluster has high reliability when handling large datasets. Future studies should expand on the framework by exploring other clustering methods and algorithms.
2009 International Conference on Computers & Industrial Engineering, 2009
Abstract In the current state, where the impacts of the pollution and the congestion of cities ar... more Abstract In the current state, where the impacts of the pollution and the congestion of cities are increasingly acute, the public services like the car-sharing service can be an attractive complement for the other means of transportation. This type of service can reduce a part of traffic problems. To be efficient, the car-sharing service must ensure a high level of temporal and spatial availability. Car-sharing systems are most successful there where is sufficient economic and social activity and when that activity has a strong relationship to public ...
ABSTRACT Identifying and evaluating the driving forces that are behind land use and land cover ch... more ABSTRACT Identifying and evaluating the driving forces that are behind land use and land cover changes remains one of the most difficult exercises that geographers and environmental scientists must continually address. The difficulty emerges from the fact that in land use and land cover systems, multiple actions and interactions between different factors (e.g., economic, political, environmental, biophysical, institutional, and cultural) come into play and make it difficult to understand how the processes behind the changes function. Using advanced methods, such as Cellular Automata (CA) and Artificial Neural Networks (ANNs), the results highlight that these tools are adequate in formalising knowledge regarding land use systems in cross-border regions. Moreover, because modelling land use changes using big data is gaining increasing popularity, ANN techniques could contribute to improving the calibration of cellular automata-based land use models.
Abstract: In this paper, we propose an algorithm for a fast training and accurate prediction for ... more Abstract: In this paper, we propose an algorithm for a fast training and accurate prediction for Feedforward Neural Network (FNN). In this algorithm OMBP, we combine Optic Backpropagation (OBP) with the Modified Backpropagation algorithm (MBP). The weights are initialized using Yam and Chow algorithm to insure the stability of OMBP and to reduce its sensitivity against initial settings. The proposed algorithm had shown an upper hand over three different algorithms in terms of number of iterations, time needed to reach the ...
This paper presents an approach integrating machine learning techniques in cellular automata (CA)... more This paper presents an approach integrating machine learning techniques in cellular automata (CA) model to simulate land use changes in Luxembourg and the areas adjacent to its borders. The machine learning methods are used as a base of CA model transition rule. The proposed approach shows promising results for prediction of land use change over time. We validated the various models using cross-validation technique and Receiver Operating Characteristic (ROC) curve analysis, and compare the results with ...
Abstract: When we take the time to observe nature, we often are surprised by the complex forms an... more Abstract: When we take the time to observe nature, we often are surprised by the complex forms and behaviours that may emerge, surprised by the self reproduction and the self organisation phenomena that we notice, and we are compelled to acknowledge how difficult it is to understand this complex nature in perpetual state of evolution. By analogy to this nature, this paper deals with possible spatial evolution by combining two spatial systems: land use and the transport systems. However, underlying this evolution, there are ...
The problem of Small Area Estimation (SAE) is complex because of various information sources and ... more The problem of Small Area Estimation (SAE) is complex because of various information sources and insufficient data. In this paper, an approach for SAE is presented for decision-making at national, regional and local level. We propose an Empirical Best Linear Unbiased Predictor (EBLUP) as an estimator in order to combine several information sources to evaluate various indicators. First, we present the urban audit project and its environmental, social and economic indicators. Secondly, we propose an approach for decision making in order to estimate indicators. An application is used to validate the theoretical proposal. Finally, a decision support system is presented based on open-source environment.
Payments for ecosystem services (PES) have increasingly been applied as economic incentives for i... more Payments for ecosystem services (PES) have increasingly been applied as economic incentives for improving ecosystem services around the world. However, due to difficulties in measuring and attributing ecosystem services provisioning, a land-based approach has been popularly adopted as a proxy for the desired ecosystem services. In this study, we demonstrate the impact mechanism and outcomes of locally financed PES programs on conservation-based land use in a developed area of China. We present this work using a PES-land use proxy framework that is examined empirically through a variety of qualitative assessments. Our framework illustrates that, within the ecological, socioeconomic, and institutional conditions of developed areas, land use class, pattern and function would be impacted by (a) conservation effect, (b) stakeholder response, and (c) institutional adaptation mechanisms of local PES programs, with multiple land use trends as potential outcomes. We examine the framework using materials from Suzhou, China, which has implemented a top-down, partly involuntary (ecosystem services supply side), land based PES program. Our results show that, expected land use class, land use pattern and land use function are observed in areas where the PES programs were implemented. We also find that the conditions of developed areas and locally financed payments mechanism indeed played a crucial role in promoting conservation-based land use in Suzhou.
Abstract This study introduces a novel framework for land change simulation that combines the tra... more Abstract This study introduces a novel framework for land change simulation that combines the traditional Land Transformation Model (LTM) with data clustering tools for the purposes of conducting land change simulations of large areas (e.g., continental scale) and over multiple time steps. This framework, called “LTM-cluster”, subsets massive land use datasets which are presented to the artificial neural network-based LTM. LTM-cluster uses the k-means clustering algorithm implemented within the Spark high-performance compute environment. To illustrate the framework, we use three case studies in the United States which vary in simulation extents, cell size, time intervals, number of inputs, and quantity of urban change. Findings indicate consistent and substantial improvements in accuracy performance for all three case studies compared to the traditional LTM model implemented without input clustering. Specifically, the percent correct match, the area under the operating characteristics curve, and the error rate improved on average of 9%, 11%, and 4%. These results confirm that LTM-cluster has high reliability when handling large datasets. Future studies should expand on the framework by exploring other clustering methods and algorithms.
2009 International Conference on Computers & Industrial Engineering, 2009
Abstract In the current state, where the impacts of the pollution and the congestion of cities ar... more Abstract In the current state, where the impacts of the pollution and the congestion of cities are increasingly acute, the public services like the car-sharing service can be an attractive complement for the other means of transportation. This type of service can reduce a part of traffic problems. To be efficient, the car-sharing service must ensure a high level of temporal and spatial availability. Car-sharing systems are most successful there where is sufficient economic and social activity and when that activity has a strong relationship to public ...
ABSTRACT Identifying and evaluating the driving forces that are behind land use and land cover ch... more ABSTRACT Identifying and evaluating the driving forces that are behind land use and land cover changes remains one of the most difficult exercises that geographers and environmental scientists must continually address. The difficulty emerges from the fact that in land use and land cover systems, multiple actions and interactions between different factors (e.g., economic, political, environmental, biophysical, institutional, and cultural) come into play and make it difficult to understand how the processes behind the changes function. Using advanced methods, such as Cellular Automata (CA) and Artificial Neural Networks (ANNs), the results highlight that these tools are adequate in formalising knowledge regarding land use systems in cross-border regions. Moreover, because modelling land use changes using big data is gaining increasing popularity, ANN techniques could contribute to improving the calibration of cellular automata-based land use models.
Abstract: In this paper, we propose an algorithm for a fast training and accurate prediction for ... more Abstract: In this paper, we propose an algorithm for a fast training and accurate prediction for Feedforward Neural Network (FNN). In this algorithm OMBP, we combine Optic Backpropagation (OBP) with the Modified Backpropagation algorithm (MBP). The weights are initialized using Yam and Chow algorithm to insure the stability of OMBP and to reduce its sensitivity against initial settings. The proposed algorithm had shown an upper hand over three different algorithms in terms of number of iterations, time needed to reach the ...
This paper presents an approach integrating machine learning techniques in cellular automata (CA)... more This paper presents an approach integrating machine learning techniques in cellular automata (CA) model to simulate land use changes in Luxembourg and the areas adjacent to its borders. The machine learning methods are used as a base of CA model transition rule. The proposed approach shows promising results for prediction of land use change over time. We validated the various models using cross-validation technique and Receiver Operating Characteristic (ROC) curve analysis, and compare the results with ...
Abstract: When we take the time to observe nature, we often are surprised by the complex forms an... more Abstract: When we take the time to observe nature, we often are surprised by the complex forms and behaviours that may emerge, surprised by the self reproduction and the self organisation phenomena that we notice, and we are compelled to acknowledge how difficult it is to understand this complex nature in perpetual state of evolution. By analogy to this nature, this paper deals with possible spatial evolution by combining two spatial systems: land use and the transport systems. However, underlying this evolution, there are ...
Uploads
Papers by Hichem Omrani