A knowledge discovery process for spatiotemporal data: Application to river water quality monitoring

Abstract

Rapid population growth, and human activities (such as agriculture, industry, transports,...) development have increased vulnerability risk for water resources. Due to the complexity of natural processes and the numerous interactions between hydro-systems and human pressures, water quality is difficult to be quantified. In this context, we present a knowledge discovery process applied to hydrological data. To achieve this objective, we combine successive methods to extract knowledge on data collected at stations located along several rivers. Firstly, data is pre-processed in order to obtain different spatial proximities. Later, we apply a standard algorithm to extract sequential patterns. Finally we propose a combination of two techniques (1) to filter patterns based on interest measure, and; (2) to group and present them graphically, to help the experts. Such elements can be used to assess spatialized indicators to assist the interpretation of ecological and river monitoring pressure data.

Surface Water Monitoring Systems—The Importance of Integrating Information Sources for Sustainable Watershed Management

“…The integration of data incorporated different types of monitoring systems to support water quality policy with aggregation problem [81]. In Knowledge Discovery in Databases (KDD), information is extracted over five stages, namely selection, pre-processing, transformation, data mining, evaluation and knowledge [82]. The use of data quantity has been related to data quality to achieve high-level information from data monitoring with regard to site location [18].…”

Analysis of spatiotemporal data relationship using information granules

“…We have been witnessing a slew of approaches originating from studies developed within the setting of analysis and processing of spatiotemporal data. Some studies focus on mining knowledge from the data [1,2], some try to build a model using spatiotemporal data [3], and some others determine the relationship of spatiotemporal data [4]. The need for a concise, highly interpretable, and accurate descriptors of data is highly visible so that such descriptions reveal and describe an essence of the main relationships and associations among variables of the systems.…”

Knowledge discovery in task-oriented dialogue

“…KDD has been used in a broad range of applications across a variety of domains, such as to improve the analysis of marketing and business databases (Orriols-Puig, Martínez-López, Casillas, & Lee, 2013), extract knowledge from structural medical data (Esfandiary, Babavalian, Moghadam, & Tabar, 2014), and to monitor water quality using hydrological data (Alatrista-Salas et al, 2014). Due to the rapidly growing amounts of digital data, there is a pressing need for theories and tools that can support the extraction of useful information (knowledge) from them.…”