Mathematical, statistical, and computational models have been a key component of crop sciences, contributing to fundamental and applied agriculture research. Models and modeling approaches can be classified into several categories, depending on the user-defined goals and objectives. They may be grouped based on: i) application scope (e.g., applied, hypothesis generation or test), ii) methodologies (e.g., deterministic, stochastic, simulation), and iii) dependence of underlying biological processes (e.g., black-box, mechanistic, pattern recognition). It should be noted, however, that this is a continuum rather than a clear, discrete separation. Examples of the application of modeling to aid decision-making are the development of models predicting real-time risks of pest and disease outbreaks, primarily based on climatic conditions and levels of current pest infestation and pathogen inoculum. On the other hand, complex differential/difference models have been developed to understand spatial and temporal dynamics of pests and pathogens to predict the effect of different crop management strategies on pest and pathogen dynamics.

Until recently, most models were of the mechanistic type, describing and studying underlying biological processes of a specific system under consideration within a framework of mathematical relationships (including stochastic variability in the system) to understand and predict system behaviors in relation to external conditions/perturbations (scenario studies). For instance, many crop growth models have been developed to assess the impact of crop management (e.g., nitrogen input) and future predicted climate change scenarios on yield and pest abundance. More recently, because of the availability of big data (e.g., genomic sequences, transcriptomic data, images) and improved computing power, data-driven modeling approaches have been rapidly expanding, aiming to find common patterns/characteristics in the big (sometimes messy) data set. These approaches center around the development of rapid yet accurate mathematical algorithms and their implementation for pattern recognition commonly referred to as AI (or artificial Intelligence). Examples of the use of this modeling approach include the identification of candidate pathogen virulence genes, signaling networks, identification of pests and diseases from images, and estimation of crop yield).

The implementation of digital technology and artificial intelligence (AI) has been trending in different agricultural research areas to support growers and agricultural industries from the detrimental effects of climate change. These effects can directly affect horticultural growth, productivity, and quality of produces. Furthermore, climatic anomalies have been increasing in number and severity and pose a threat to horticultural production that can be addressed by developing and implementing new and emerging digital technologies. This research topic invites authors to submit high-quality and original research articles or reviews for publication related to the use or integration of digital technologies and artificial intelligence for future horticultural production, specifically for viticulture, pomology, and soft fruits research and applications.

Articles to be considered for this Research Topic should be based on original experimental data, not published elsewhere in different forms. Research based on surveys or interviews is outside the scope of this research topic.

Specifically, authors are encouraged to submit research articles based, but limited, to digital technologies implemented in agriculture, such as:

• Remote sensing is based on platforms such as airborne or unmanned aerial/terrestrial vehicles (UAV, UTV) and satellite imagery
• Sensor technology, sensor networks, data transmission, and analysis
• Implementation of machine/deep learning for modeling
• Image analysis using computer vision algorithms
• New and integrated sensor technology for agricultural applications
• Digital tools to assess growth, composition, and quality traits of produces
• Digital technologies to assess biotic or abiotic plant stresses such as infrared thermography, hyperspectral and multispectral imagery, near-infrared spectroscopy, and fluorescence, among others
• Automated robotics for phenology assessment and harvesting
• Digital twins for agricultural applications

Submit your idea

Impact

Frontiers in Horticulture

Submit your idea

Impact