Leveraging Cloud Computing and IoT to Improve Research Solutions for Ecological Modelling

Developing strategies for conservation and sustainable use of the environment and natural resources is mandatory nowadays, as the effects of global change are affecting populations worldwide and economic crises are threatening even well-known pro-environmental societies. Leveraging powerful technological resources such as the ones provided by cloud computing and internet of things (IoT) may help to build cost- effective solutions to keep improving research outcomes in ecological modelling, even under a financially- challenging scenario. Cloud computing allows the on-demand delivery of configurable computing resources (e.g., networks, servers, storage, applications and services). Different combinations of resources can be delivered under different models, being IaaS (Infrastructure-as-a-Service), PaaS (Platform-as-a-Service), and SaaS (Software-as-a-Service) the most common ones. Public clouds such as Amazon Web Services (AWS), Microsoft Azure and Google Cloud Platform offer cloud services based on the pay-as-you-go pricing model. If properly used, they allow the provision of secure, reliable, and performance-efficient solutions which are also cost-optimised. The pay-as-you-go model reduces considerably the upfront investments, so a researcher may be able to develop demos and proofs-of-concept with little funding. Community clouds and virtual laboratories represent technological-efficient and cost-effective solutions to support collective research. For example, the Australian National Collaborative Research Infrastructure Strategy (NCRIS) supports both the Biodiversity and Climate Change Virtual Lab (http://bccvl.org.au/) and the EcoCloud (http://www.ecocloud.org.au/) projects, which provide different cloud-based solutions for ecological modelling. IoT can be seen as a gigantic network of connected devices (called things). The things contain embedded technology to collect data (such as sensors and cameras) and/or interact with the external environment, including people and species. Examples of things would be mobiles, drones, robots, coffee makers, washing machines, and wearable devices. Intelligent things are things that are not only interconnected but also deliver the power of Artificial Intelligence (AI)-enabled systems. This work describes an architectural solution to connect things to a cloud-based platform, leveraging cloud computing and IoT to improve the current processes and state-of-art research in Ecological Modelling. The things, in this case, are robots, drones, sensors, and cameras that are being used to collect species data in the field. The data collected is used as input to an AI-cloud-based system, which remotely controls the things in the field, turning them into intelligent things to improve their data collection capability. Challenges in data acquisition, communication, security, interoperability, integration, big data, performance, latency, and AI-algorithms are discussed, as well as the main pillars to successfully deploy cloud-based IoT solutions