Abstract—This work is investigating the use of a multi-modal sensor network where visual sensors such as cameras and satellite imagers, along with context information can be used to complement and enhance the usefulness of a traditional in-situ sensor network in measuring and tracking some feature of a river or coastal location. This paper focuses on our work in relation to the use of an off the shelf camera as part of a multi-modal sensor network for monitoring a river environment. It outlines our results in relation to the estimation of water level using a visual sensor. It also outlines the benefits of a multi-modal sensor network for marine environmental monitoring and how this can lead to a smarter, more efficient sensing network.