Improving farm productivity is essential for increasing farm profitability and meeting the rapidly growing demand for food that is fuelled by rapid population growth across the world. Farm productivity can be increased by understanding and forecasting crop performance in a variety of environmental conditions. Crop recommendation is currently based on data collected in field-based agricultural studies that capture crop performance under a variety of conditions (e.g., soil quality and environmental conditions). However, crop performance data collection is currently slow, as such crop studies are often undertaken in remote and distributed locations, and such data are typically collected manually. Furthermore, the quality of manually collected crop performance data is very low, because it does not take into account earlier conditions that have not been observed by the human operators but is essential to filter out collected data that will lead to invalid conclusions (e.g., solar radiation readings in the afternoon after even a short rain or overcast in the morning are invalid, and should not be used in assessing crop performance). Emerging Internet of Things (IoT) technologies, such as IoT devices (e.g., wireless sensor networks, network-connected weather stations, cameras, and smart phones) can be used to collate vast amount of environmental and crop performance data, ranging from time series data from sensors, to spatial data from cameras, to human observations collected and recorded via mobile smart phone applications. Such data can then be analysed to filter out invalid data and compute personalised crop recommendations for any specific farm. In this paper, we present the design of SmartFarmNet, an IoT-based platform that can automate the collection of environmental, soil, fertilisation, and irrigation data; automatically correlate such data and filter-out invalid data from the perspective of assessing crop performance; and compute crop forecasts and personalised crop recommendations for any particular farm. SmartFarmNet can integrate virtually any IoT device, including commercially available sensors, cameras, weather stations, etc., and store their data in the cloud for performance analysis and recommendations. An evaluation of the SmartFarmNet platform and our experiences and lessons learnt in developing this system concludes the paper. SmartFarmNet is the first and currently largest system in the world (in terms of the number of sensors attached, crops assessed, and users it supports) that provides crop performance analysis and recommendations.

Emerging availability (and varying complexity and types) of Internet of Things (IoT) devices, along with large data volumes that such devices (can potentially) generate, can have a significant impact on our lives, fuelling the development of critical next-generation services and applications in a variety of application domains (e.g. healthcare, smart grids, finance, disaster management, agriculture, transportation and water management). Deep learning technology, which has in the past been used successfully in computer vision and language modelling is now finding application in new domains driven by availability of diverse and large datasets. One such example is the advances in medical diagnostics and prediction by using Deep Learning technologies to improve human health. However, transferring large data streams (a requirement of Deep Learning technologies for achieving high accuracy) to centralised locations such as Cloud datacentre environments, in a timely and reliable manner, is being seen as a key limitation of expanding the application horizons of such technologies. To this end, various paradigms, including Osmotic Computing, have been proposed that promotes distribution of data analysis tasks across Cloud and Edge computing environments. However, these existing paradigms fail to provide a detailed account of how technologies such as deep learning can be orchestrated and take advantage of the cloud, edge and mobile edge environments in a holistic manner. In other words, the focus of this Blue Skies piece is to analyze the research challenges involved with developing a new class of holistic distributed deep learning algorithms that are “resource and data aware”, and which are able to account for underlying heterogeneous data and data models, resource (cloud vs. edge vs. mobile edge) models and data availability while executing – trading accuracy for execution time, etc.