Objective
Objectives and content
River water plays an essential role in the hydrological
cycle. Quality of river water will affect the quality of
receiving water bodies (other rivers, streams, lakes,
ocean, and aquifers) and will make a direct impact on the
greater surrounding environment. The nature of mineral
extraction operations and subsequent waste disposal and
discharge activities create a potential pollution hazard
for water resources around such activities.
Due to the significance that it takes in the global
ecosystem and complex, multiple interrelationships of
hydrological, hydrochemical and hydrobiological
determinants involved, the control of river water quality
necessitates dedicated environmental management systems.
These systems should embrace the implementation of
continuous monitoring, creation of databases for the
management of spatially and temporally distributed water
quality data and the development of simulation and
predictive systems using the measured information, for
the early detection and assessment of possible
risks/hazards so that protection measures could be
implemented.
In general environmental attributes are characterised by
very high variability. Consequently, the relation
between variables involved exhibits a high degree of nonlinearity and in order to model them effectively,
appropriate non-linear modelling methods become a
prerequisite. At present, there are various methods for
analysing and modelling environmental variables and
predicting impacts. However, notwithstanding the
advances and achievements of most models, they all rely
on very strict assumptions. Most of these techniques
tend to simplify the problem by ignoring its spatial or
temporal dimensions. Additional difficulties with
spatio-temporal phenomena occur as a result of incomplete
and imprecise knowledge about the problem, lack of
monitoring and measurement standards and the use of
observational rather than data from designed experiments.
The main objective of the proposed project is to develop
an Artificial Intelligence based Neural Network (ANN)
model for the prediction of river water quality, using
historical and real-time monitored data. ANN techniques
as a modelling method are distribution free, hence they
do not require making assumptions about the statistical
properties of the underlying population. ANN algorithms
are generally data-driven (model-free) as opposed to
classical model-driven algorithms and capable of directly
dealing with input data. Additionally, the appeal of ANN
to environmental modelling is increased through their
robustness to imperfect data and their capability of
modelling complex or open systems, such as the river
water system. Tasks requiring fault tolerance or coping
with noise, or involving pattern recognition, various
diagnoses, abstraction and generalisation like those
involved in river water quality modelling are all good
candidates for a neural network approach.
The main objectives of the proposed system are:
The development of a standard system to assess river
water quality based on the chemical/biological
characteristics of Natural River water and the mine
effluent added to it. The system will be based on:
The design and implementation of an Artificial Neural
Network model for the prediction of the behaviour of
river water quality indicators. There are three separate
elements in this task:
The validation and final utilisation of the above
system, initially by the industrial partners of the
consortium to optimise the existing monitoring programme
and to prevent any deterioration in river water quality
downstream of the effluent discharge points.
The main achievement expected is the development of a
short-term river quality prediction software which will
use monitored historical river quality data from a number
of stations and predict river water quality, on the basis
of planned effluent discharge and receiving river water
chemistry and flow quantity. The proposed model will
cope with both spatial and temporal variability in rivers
and enable prediction on a day by day basis, dependent on
effluent properties, allowing discharge quantity and
quality control thus preventing pollution. The
predictive system could be used to optimise the number
and location of river quality monitoring stations to be
used at any one time, resulting in savings in capital
investment and human resources allocated to monitoring
programmes. This aspect will make a significant
contribution to environmental management in an era where
more and more comprehensive monitoring systems are
required by legislation yet, without the ability to
optimise resources.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
- natural sciences computer and information sciences databases
- natural sciences earth and related environmental sciences hydrology
- natural sciences earth and related environmental sciences environmental sciences pollution
- natural sciences computer and information sciences artificial intelligence pattern recognition
- natural sciences computer and information sciences artificial intelligence computational intelligence
You need to log in or register to use this function
Programme(s)
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
Topic(s)
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Call for proposal
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
Data not available
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
Funding Scheme
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
Coordinator
SW7 2BP London
United Kingdom
The total costs incurred by this organisation to participate in the project, including direct and indirect costs. This amount is a subset of the overall project budget.