Artificial Intelligence Techniques in Grapevine Research: A Comparative Study with an Extensive Review of Datasets, Diseases, and Techniques Evaluation

Abstract

In the last few years, the agricultural field has undergone a digital transformation, incorporating artificial intelligence systems to make good employment of the growing volume of data from various sources and derive value from it. Within artificial intelligence, Machine Learning is a powerful tool for confronting the numerous challenges of developing knowledge-based farming systems. This study aims to comprehensively review the current scientific literature from 2017 to 2023, emphasizing Machine Learning in agriculture, especially viticulture, to detect and predict grape infections. Most of these studies (88%) were conducted within the last five years. A variety of Machine Learning algorithms were used, with those belonging to the Neural Networks (especially Convolutional Neural Networks) standing out as having the best results most of the time. Out of the list of diseases, the ones most researched were Grapevine Yellow, Flavescence Dorée, Esca, Downy mildew, Leafroll, Pierce's, and Root Rot. Also, some other fields were studied, namely Water Management, plant deficiencies, and classification. Because of the difficulty of the topic, we collected all datasets that were available about grapevines, and we described each dataset with the type of data (e.g., statistical, images, type of images), along with the number of images where they were mentioned. This work provides a unique source of information for a general audience comprising AI researchers, agricultural scientists, wine grape growers, and policymakers. Among others, its outcomes could be effective in curbing diseases in viticulture, which in turn will drive sustainable gains and boost success. Additionally, it could help build resilience in related farming industries such as winemaking.

Keywords: artificial intelligence; diseases; grapevine; machine learning; smart agriculture; smart sensors; vineyards.

Figure 1

Full network visualization of the scientific literacy topic areas.

Figure 2

Density visualization of the scientific literacy topic areas.

Figure 3

Machine learning process in agriculture (adapted from [8], used under CC BY 4.0, accessed on 11 August 2024).

Figure 4

Schematic diagram of supervised learning.

Figure 5

Schematic diagram of Unsupervised Learning.

Figure 6

Schematic diagram of reinforcement learning.

Figure 7

Grapevine Yellow disease (cropped from [18], used under CC BY 4.0).

Figure 8

Flavescence Dorée disease (reproduced from [20], used under CC BY 4.0).

Figure 9

Esca disease (reproduced from [22], used under CC BY 4.0).

Figure 10

Downy mildew disease (cropped from [24], used under CC BY 4.0).

Figure 11

Leafroll disease (cropped from [18], used under CC BY 4.0).

Figure 12

Pierce’s disease (cropped from [29], used under CC BY 4.0).

Figure 13

Armillaria Root Rot disease (reproduced from [31], used under CC BY 4.0).

Figure 14

Number of publications identifying each Machine Learning technique as superior.

Figure 15

An overview of the reviewed papers according to the field of application.

Figure 16

Map of research conducted on vineyards per country.