Evaluation of Geographic Locations for River Bridge Construction: A Multi-Criteria Decision Analysis with Evidential Reasoning Approach Nasrin Sultana Department of Computer Science & Engineering University of Chittagong, Bangladesh Email: nasrin_cse@cu.ac.bd Risul Islam Rasel Department of Computer Science & Engineering International Islamic University Chittagong, Bangladesh Email: risul-islam@cse.iiuc.ac.bd Abstract—Geographic location selection for river bridge construction is one of the most challenging tasks because it has to deal with both numerical data and qualitative information with uncertainty. Organizational self-assessment, ensuring safety, risk measurement, supplier appraisal and many other things depend on a proper Geo-location selection. River bridge site selection is such an example in which multiple attributes; both qualitative and quantitative criteria have to be analyzed for selecting a proper bridge location. This paper demonstrates the application of a novel method named Evidential Reasoning (ER), which is a Multi Criteria Decision Analysis method applied for decision making where many criteria have to be explicitly considered for making decision. ER approach is capable for addressing the uncertainty of multi-criteria decision problem, where there exist factors of both subjective and quantitative nature. It handles uncertainties by using a degree belief structure. The evidential reasoning approach helps in aggregating degree of belief from lower level attributes to higher level attributes. To conduct the experiments of this work, Geo-location selection for The Padma Bridge construction in Bangladesh is taken as research domain and the experiment results and analysis are discussed in this paper. Keywords— Assessment, Evidential Reasoning, Multi Criteria Decision Analysis, Numerical data and Qualitative information, Uncertainty, Degree of belief I. INTRODUCTION Rivers are natural flow of water. But sometimes it mires our usual flow of movements. Transportations and freight across the river by ferries, launches or manually-operated boats are time consuming and tedious process. But a bridge can eradicate that persecution. However selecting the most suitable site for bridge construction is a critical problem. Large numbers of criteria have to be considered and evaluated. Several criteria are correlated to one another in a complex way. Consequently, step up in one often consequences in refuse to another. Besides some criteria are qualitative (river stream, River training Works, Bank Erosion etc.) and some are quantitative (Bridge length, Traffic demand, Land Acquisition, estimated cost). So decision-makers have to scrutinize the both quantitative data and Quantitative data to make a decision. Quantitative data can be measured but the qualitative data is descriptive in nature only. As an example, nature of bank erosion can’t be measured. It can only be described as the river bank erosion is favorable, unfavorable, no erosion (excellent) or severe erosion (worst). As a result, qualitative data occupies uncertainty since it is difficult to measure concepts or characteristics or quality of a thing with 100% conviction. So, the qualitative criteria which are involved in selecting suitable site for bridge construction face lots of uncertainties and those should be treated with apt methodology. There are many techniques to select suitable geographical site for river bridge construction. GIS and Remote sensing approaches have been using to evaluate suitable site for river bridge construction based on river bank erosion and deposition [1]. That approaches handle only two criteria but selecting suitable and sustainable geo-location is a multi-criteria problem. AHP method also able to handle multiple criteria decision making problem [2],[3]. These approaches uses a pair wise comparison matrix in order to identify the significance between two attributes or data [4],[5]. But it can not address the uncertainty such as incompleteness or vagueness. Moreover, when another alternative will add, it can be seen that the ranking of the alternatives in terms of their importance will be changed. These types of problems associated with AHP causes serious problems in decision making. If a belief structure is used for taking account the evaluation grade of the attributes, this incompleteness may be addressed and hence the uncertainty is also being addressed [6]. The issues are mentioned in prior can be addressed by using Evidential Reasoning Approach (ER) also, which is a multi-criteria decision analysis (MCDA) method [7],[8]. The ER approach is developed based on decision theory; in particular utility theory [9],[10] and artificial intelligence; in particular the theory of evidence [6][11]. This approach deals with MCDA problems, consisting of both quantitative and qualitative criteria under various uncertainties, such as incomplete information, vagueness, ambiguity etc. This approach has addressed uncertainty by proposing a belief structure which assigns degree of belief in the various evaluation grades of the attributes, which is not the case in AHP or other multi- criterions decision techniques. Due to the capability of ER approach in managing and representing uncertainty, it has been applied to many areas, such as environmental impact assessment [12], pipeline leak detection [13], and system reliability prediction [14]. It also applied to conduct safety analysis [9]. In this research ER approach is applied to identify sustainable geographical location for river bridge construction.