Analysis of crop leaf area index, leaf chlorophyll content, and canopy chlorophyll content based on deep learning and hyperspectral remote sensing

Abstract

Canopy chlorophyll content (CCC) is a critical indicator for assessing crop photosynthetic capacity, nitrogen status, and the occurrence of diseases. Accurate estimation of CCC holds significant importance for precision agriculture, providing a scientific basis for crop management, yield prediction, and stress detection. CCC is commonly defined as the product of leaf area index (LAI) and leaf chlorophyll content (LCC). Traditional methods of acquiring CCC rely on destructive sampling, which limits large-scale application. Hyperspectral remote sensing enables non-destructive acquisition of rich spectral information from the crop canopy across the visible to near-infrared spectrum, offering a promising approach for CCC estimation. This study proposes a convolutional neural network-based model, CanopyChlNet, to jointly estimate LAI and LCC, thereby deriving CCC. The model utilizes a one-dimensional CNN structure to effectively extract deep spectral features from hyperspectral data, improving estimation accuracy. Field-measured canopy hyperspectral reflectance and corresponding LAI and LCC data from winter wheat and potato were used to train and validate the model. The CanopyChlNet model outperformed both Random Forest (RF) and Partial Least Squares Regression (PLSR) in estimating LAI, LCC, and CCC, achieving R2 values of 0.709, 0.775, and 0.718, with RMSE values of 0.803 m2 ·m−2, 5.288 µg·cm− 2, and 34.938 µg·cm− 2, respectively. In comparison, RF yielded R2 values of 0.636, 0.685, and 0.667, and RMSE values of 0.896 m2 ·m− 2, 6.396 µg·cm− 2, and 37.901 µg·cm− 2. PLSR achieved R2 values of 0.522, 0.709, and 0.586, with RMSE values of 1.029 m2 ·m− 2, 6.042 µg·cm− 2, and 42.332 µg·cm− 2.These results demonstrate that CanopyChlNet is a high-precision model for estimating crop LCC and CCC. This study demonstrates that integrating deep learning with hyperspectral remote sensing significantly enhances the estimation accuracy of key crop parameters, providing an effective tool for crop growth monitoring.

Plant phenotyping relevance

作物キャノピーのLAI・LCC・CCCという植物形質を、ハイパースペクトルデータとCNNで推定する手法を開発・検証しており、フェノタイピング手法が研究の中心である。

Code and data availability

公開本文の所在を確認できませんでした。非公開または購読が必要な可能性があります。

No evidence-backed public reproduction asset is currently recorded.