Rapid Detection of Soybean Nutrient Deficiencies Using YOLOv8s: Advancing Precision Agriculture

Abstract

Abstract Early detection of nutrient deficiencies is crucial for optimizing crop yields and ensuring sustainable agricultural practices. This study presents a novel application of the YOLOv8s object detection model for identifying nitrogen, phosphorus, and potassium deficiencies in soybean plants. Employing a unique dataset from a long-term nutrient-deficient field maintained for over 40 years, we trained and evaluated the model on 6,020 red, green, and blue images of soybean leaves exhibiting nutrient stress conditions. The YOLOv8s model achieved exceptional performance, with a mean average precision (mAP@0.5) of 99.18% during training and 98.51% for validation. Precision rates for individual nutrient deficiencies ranged from 90.03–96.54%, with highly accurate potassium deficiency detection. The model demonstrated robust generalization across diverse field conditions, processing images in 3.46 ms each, making it suitable for real-time applications. This research significantly advances the field of precision agriculture by providing a fast, accurate, and scalable method for detecting early nutrient deficiency in soybean crops, potentially revolutionizing fertilizer management practices and contributing to more sustainable farming systems.

Plant phenotyping relevance

大豆葉の栄養欠乏状態を画像とYOLOv8sで直接推定する手法を開発・評価しており、植物状態の取得が研究の中心である。

Code and data availability

The paper describes a 6,020-image soybean leaf RGB dataset and a YOLOv8s model, but no supplied block contains any public deposit, availability statement, or authors' URL for the dataset, images, annotations, code, or trained model. The only supplementary file listed is a PDF without stated contents containing data or;

No evidence-backed public reproduction asset is currently recorded.