Edel O'Connor

A Neural Network Approach to Smarter Sensor Networks for Water Quality Monitoring

Environmental monitoring is evolving towards large-scale and low-cost sensor networks operating reliability and autonomously over extended periods of time. Sophisticated analytical instrumentation such as chemo-bio sensors present inherent limitations because of the number of samples that they can take. In order to maximize their deployment lifetime, we propose the coordination of multiple heterogeneous information sources. We use rainfall radar images and information from a water depth sensor as input to a neural network (NN) to dictate the sampling frequency of a phosphate analyzer at the River Lee in Cork, Ireland. This approach shows varied performance for different times of the year but overall produces output that is very satisfactory for the application context in question. Our study demonstrates that even with limited training data, a system for controlling the sampling rate of the nutrient sensor can be set up and can improve the efficiency of the more sophisticated nodes of the sensor network.

Environmental monitoring of Galway Bay: fusing data from remote and in-situ sources

Changes in sea surface temperature can be used as an indicator of water quality. In-situ sensors are being used for continuous autonomous monitoring. However these sensors have limited spatial resolution as they are in effect single point sensors. Satellite remote sensing can be used to provide better spatial coverage at good temporal scales. However in-situ sensors have a richer temporal scale for a particular point of interest. Work carried out in Galway Bay has combined data from multiple satellite sources and in-situ sensors and investigated the benefits and drawbacks of using multiple sensing modalities for monitoring a marine location.

Integrating multiple sensor modalities for environmental monitoring of marine locations

In this paper we present preliminary work on integrating visual sensing with the more traditional sensing modalities for marine locations. We have deployed visual sensing at one of the Smart Coast WSN sites in Ireland and have built a software platform for gathering and synchronizing all sensed data. We describe how the analysis of a range of different sensor modalities can reinforce readings from a given noisy, unreliable sensor.

Multimedia information retrieval and environmental monitoring: Shared perspectives on data fusion

Computer-based remote monitoring of our environment is increasingly based on combining data derived from in-situ-sensors with data derived from remote sources, such as satellite images or CCTV. In such deployments it is necessary to continuously monitor the accuracy of each of the sensor data streams so that we can account for sudden failures of sensors, or errors due to calibration drive or biofouling. In multimedia information retrieval (MMIR), we search through archives of multimedia artefacts like video programs, by implementing several independent retrieval systems or agents, and we combine the outputs of each retrieval agent in order to generate an overall ranking. In this paper we draw parallels between these seemingly very different applications and show how they share several similarities. In the case of environmental monitoring we also need some mechanism by which we can establish the trust and reputation of each contributing sensor, though this is something we do not need in MMIR. In this paper we present an outline of a trust and reputation framework we have developed and deployed for monitoring the performance of sensors in a heterogeneous sensor network.

Smart multi-modal marine monitoring via visual analysis and data fusion

Estuaries and coastal areas contain increasingly exploited resources that need to be monitored, managed and protected efficiently and effectively. This requires access to reliable and timely data and management decisions must be based on analysis of collected data to avoid or limit negative impacts. Visually supported multi-modal sensing and data fusion offer attractive possibilities for such arduous tasks. In this paper, we demonstrate how an in-situ sensor network can be enhanced with the use of contextual image data. We assimilate and alter a state-of-the-art background modelling technique from the image processing domain in order to detect turbidity spikes in water quality sensor measurements automatically. We then combine this with visual sensing to identify abnormal events that are not caused by local activities. The system can potentially assist those charged with monitoring large scale ecosystems, combining real-time analytics with improved efficiency and effectiveness.

Multi-modal sensor networks for more effective sensing in Irish coastal and freshwater environments

The worlds oceans represent a vital resource to global economies and there exists huge economic opportunity that remains unexploited. However along with this huge potential there rests a responsibility into understanding the effects various developments may have on our natural ecosystem. This along with a variety of other issues necessitates a need for continuous and reliable monitoring of the marine and freshwater environment. The potential for innovative technology development for marine and freshwater monitoring and knowledge generation is huge and recent years have seen huge leaps forward in relation to the development of sensor technology for such purposes. However despite the advancements there are still a number of issues. In our research we advocate a multi-modal approach to create smarter more efficient monitoring networks, while enhancing the use of in-situ wireless sensor networks (WSNs). In particular we focus on the use of visual sensors, modelled outputs and context information to support a conventional in-situ wireless sensor network creating a multi-modal environmental monitoring network. Here we provide an overview of a selection of our work in relation to the use of visual sensing through networked cameras or satellite imagers in three very diverse test sites - a river catchment, a busy port and a coastal environment.

Investigation Into the Use of Satellite Remote Sensing Data Products as Part of a Multi-Modal Marine Environmental Monitoring Network

In this paper it is investigated how conventional in-situ sensor networks can be complemented by the satellite data streams available through numerous platforms orbiting the earth and the combined analyses products available through services such as MyOcean. Despite the numerous benefits associated with the use of satellite remote sensing data products, there are a number of limitations with their use in coastal zones. Here the ability of these data sources to provide contextual awareness, redundancy and increased efficiency to an in-situ sensor network is investigated. The potential use of a variety of chlorophyll and SST data products as additional data sources in the SmartBay monitoring network in Galway Bay, Ireland is analysed. The ultimate goal is to investigate the ability of these products to create a smarter marine monitoring network with increased efficiency. Overall it was found that while care needs to be taken in choosing these products, there was extremely promising performance from a number of these products that would be suitable in the context of a number of applications especially in relation to SST. It was more difficult to come to conclusive results for the chlorophyll analysis.

Image processing for smarter browsing of ocean color data products: investigating algal blooms

Remote sensing technology continues to play a significant role in the understanding of our environment and the investigation of the Earth. Ocean color is the water hue due to the presence of tiny plants containing the pigment chlorophyll, sediments, and colored dissolved organic material and so can provide valuable information on coastal ecosystems. We propose to make the browsing of Ocean Color data more efficient for users by using image processing techniques to extract useful information which can be accessible through browser searching. Image processing is applied to chlorophyll and sea surface temperature images. The automatic image processing of the visual level 1 and level 2 data allow us to investigate the occurrence of algal blooms. Images with colors in a certain range (red, orange etc.) are used to address possible algal blooms and allow us to examine the seasonal variation of algal blooms in Europe (around Ireland and in the Baltic Sea). Yearly seasonal variation of algal blooms in Europe based on image processing for smarter browsing of Ocean Color are presented.