Multi-crop early detection of spider mite damage using hyperspectral data and XGBoost

Abstract

• XGBoost classified healthy and spider mite–infested leaves of cucumber and strawberry • Classification accuracy remained above 70% even with a reduced set of wavelengths • A combined model detected spider mite infestations across two crop species effectively The two-spotted spider mite is a globally significant pest affecting over 150 crop species, including cucumbers and strawberries. Its feeding activity leads to chlorophyll degradation and physiological changes in leaf tissue, which alter spectral reflectance properties and enable image-based detection. In this study, hyperspectral imaging (HSI) under controlled conditions was used to classify healthy and spider mite-infested leaves of cucumber and strawberry plants, including asymptomatic infested leaves. Spectral data were analyzed and classified with three supervised machine learning algorithms built on extreme gradient boosting (XGBoost) models. The study had three objectives: (1) to assess the ability of XGBoost to classify multiple infestation states, (2) to evaluate model performance with a reduced set of effective wavelengths, and (3) to determine whether infestation across both crops can be classified using a single, merged model. Using all wavelengths, results showed that classification accuracy was 93% for cucumber leaves, 84% for strawberry leaves, and 87% when combined. With five most effective wavelengths, classification accuracy reached 70% for cucumber leaves, 65% for strawberry leaves, and 65% for cucumber and strawberry leaves combined. The most effective wavelengths were consistently selected from the red-edge and near-infrared (NIR) spectral regions, which highlights their importance for early detection. To the best of our knowledge, this is the first known study to successfully apply a combined machine learning model for early spider mite detection across two different crop species using hyperspectral data under controlled conditions. The results show the potential of machine learning for multi-crop pest detection and could lay the groundwork for practical, sensor-based tools in precision agriculture.

Plant phenotyping relevance

ハイパースペクトル画像とXGBoostにより、植物葉のダニ感染状態を直接推定し、波長削減と作物間モデル性能を評価しているため、病害・害虫状態のフェノタイピング手法が中心である。

Code and data availability

公開論文であることは確認できましたが、現在の公式API・許可済み取得経路では本文を自動取得できませんでした。

No evidence-backed public reproduction asset is currently recorded.