Integrating water quality crowdsourcing into hydrological modelling and prediction

The importance of ensuring good water quality is important for many ecosystem services. Despite the vast infrastructure of sensory systems and remote observation technology, there are still gaps in reporting fine-grained details about water quality due to sparsity of observations and dynamic nature of water ecosystems. Crowd observations or citizen science in general contribute to fill in this gap by enabling random users to act as a supplementary sensor with a variety of information ranging from selected images of the scene, template-like reporting, to free textual description of the observations. Crowdsourcing apps can be implemented through simple mobile app or interned-enable device using existing plug-in platforms. Nevertheless, crowdsourcing data is subject to high noise ratio due to subjectivity in user’s reporting and sometimes deliberate trend to bias the results. This opens up the research question of how to effectively devise, implement and integrate crowdsourcing data into existing hydrological model (s) and monitoring pipeline in a way that eases the effects of crowdsourcing noise and contributes towards enhancing the quality of the monitoring and prediction.

This PhD position focus on water quality monitoring. By combining available in-situ observations about water quality held at Finnish observation stations, freely available satellite data and crowdsourcing data, it is expected to reduce uncertainty pervading crowdsourcing reporting. On the other hand, the emergence of theoretical frameworks that integrate multi-modal data (image, free text, sensor measurement) expects to shed light on the development of hybrid models that enable integrating the crowdsourcing observations into conventional hydrological models to enhance the prediction and monitoring capabilities. The project will develop a crowdsourcing mobile app that enables users to friendly communicate their observations regarding water quality and transmit the information to a cloud infrastructure where further preprocessing will be carried out. The candidate is expected to collaborate with both computer science and hydrology research teams to advance in this field. This collaboration offers access to various pilot sites where extensive in-situ observations are available and enable access to relevant practitioners that build bridge to effective and friendly implementations that can impact the research in this field. This position offers a unique opportunity to contribute to a critical area of environmental research, with significant implications for disaster preparedness, and sustainable development.

The ideal candidate for this PhD project will possess a comprehensive academic background in fields of computer science, Artificial Intelligence, remote sensing and environmental science Essential qualifications include advanced programming skills in languages like Python, R, or MATLAB, crucial for data analysis and environmental modelling. Additionally, extensive experience with Geographic Information Systems (GIS) and familiarity with Google Earth Engine are required for the processing and analysis of large-scale geospatial datasets. Candidates should also demonstrate proficiency in communication and collaboration skills are vital as the project demands active participation in interdisciplinary research efforts, aiming to innovate and push the boundaries of scientific understanding in environmental monitoring.

FMI

Centre for Machine Vision and Signal Processing, Faculty of ITEE, University of Oulu

Mourad Oussalah

Ali Torabi Haghighi

Kari Luojus FMI