Artificial Intelligence for Digital Agriculture at Scale: Techniques, Policies, and Challenges

Digital agriculture has the promise to transform agricultural throughput. It can do this by applying data science and engineering for mapping input factors to crop throughput, while bounding the available resources. In addition, as the data volumes and varieties increase with the increase in sensor deployment in agricultural fields, data engineering techniques will also be instrumental in collection of distributed data as well as distributed processing of the data. These have to be done such that the latency requirements of the end users and applications are satisfied. Understanding how farm technology and big data can improve farm productivity can significantly increase the world's food production by 2050 in the face of constrained arable land and with the water levels receding. While much has been written about digital agriculture's potential, little is known about the economic costs and benefits of these emergent systems. In particular, the on-farm decision making processes, both in terms of adoption and optimal implementation, have not been adequately addressed. For example, if some algorithm needs data from multiple data owners to be pooled together, that raises the question of data ownership. This paper is the first one to bring together the important questions that will guide the end-to-end pipeline for the evolution of a new generation of digital agricultural solutions, driving the next revolution in agriculture and sustainability under one umbrella.

Abstract 

The biggest promise of digital agriculture is the ability to evaluate the system on a holistic basis at multiple levels (individual, local, regional, and global) and generate tools that allow for improved decision making in every sub-process. Recent advances in the Internet of Things (IoT) hardware and software makes it possible to collect data from diverse sources in a so called "smart farm". By interconnecting these IoT devices, it is possible to collect data from a large connected area at different time scales, including in near real-time (i.e., delays of a few tens of seconds). IoT devices can connect with each other in a wireless sensor network (WSN) setting and are capable of sensing different kinds of information. In row crop systems, data is generated from a variety of sources. Field operations are a large generator of data. In most systems, the majority of the data is generated in six operations, namely, soil sampling, fertilizer application, planting, scouting, spraying, and harvesting.