Algorithms for Plant Monitoring Applications: A Comprehensive Review

Abstract

Many sciences exploit algorithms in a large variety of applications. In agronomy, large amounts of agricultural data are handled by adopting procedures for optimization, clustering, or automatic learning. In this particular field, the number of scientific papers has significantly increased in recent years, triggered by scientists using artificial intelligence, comprising deep learning and machine learning methods or bots, to process field, crop, plant, or leaf images. Moreover, many other examples can be found, with different algorithms applied to plant diseases and phenology. This paper reviews the publications which have appeared in the past three years, analyzing the algorithms used and classifying the agronomic aims and the crops to which the methods are applied. Starting from a broad selection of 6060 papers, we subsequently refined the search, reducing the number to 358 research articles and 30 comprehensive reviews. By summarizing the advantages of applying algorithms to agronomic analyses, we propose a guide to farming practitioners, agronomists, researchers, and policymakers regarding best practices, challenges, and visions to counteract the effects of climate change, promoting a transition towards more sustainable, productive, and cost-effective farming and encouraging the introduction of smart technologies.

Plant phenotyping relevance

植物・葉画像、植物病害、フェノロジーに適用されるアルゴリズムを体系的に整理するレビューであり、植物状態の取得・推定手法のレビューが中心的です。

Code and data availability

This is a literature review of algorithms for plant monitoring. The supplied blocks contain no authors' phenotype datasets, images, code, models, or supplements; the only URLs (AppEEARS, PEP725, WoS, etc.) are external databases/tools cited as references, not paper-specific assets reproducing this paper's measurements.

No evidence-backed public reproduction asset is currently recorded.