Leaf area index estimation of pergola-trained vineyards in arid regions using classical and deep learning methods based on UAV-based RGB images

Ilniyaz, Osman; Du, Qingyun; Shen, Huanfeng; He, Wei; Liao, Feng; Azadi, Hossein; Kurban, Alishir; Chen, Xi

doi:10.1016/j.compag.2023.107723

Cited by 21 publications

(8 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These findings aligns with studies like Han, et al (Han et al, 2022), who pointed out that vegetation indices had excellent performance for LAI estimation. However, the results of this study differ from those of earlier studies (Ilniyaz et al, 2023;Fan et al, 2023). These discrepancies may be attributed to the sensitivity of texture features to factors such as vegetation type and image resolution.…”

Section: Comparison Of Lai Inversion Using Vegetation Index and Textu...contrasting

confidence: 99%

“…Texture features were extracted using the gray level co-occurrence matrix (GLCM), a powerful spatial analysis technique that captures the relationship between pixels, and has demonstrated effectiveness in extracting crop-related information in numerous studies ( Ilniyaz et al., 2023 ). In this study, ENVI software was employed to extract 8 GLCM texture features from each of the 5 multispectral bands, including dissimilarity (dis), variance (var), entropy (ent), mean (mean), synergism (hom), second moment (sec), correlation (cor) and contrast (con).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Inversion of winter wheat leaf area index from UAV multispectral images: classical vs. deep learning approaches

Zu,

Yang,

Wang

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

Precise and timely leaf area index (LAI) estimation for winter wheat is crucial for precision agriculture. The emergence of high-resolution unmanned aerial vehicle (UAV) data and machine learning techniques offers a revolutionary approach for fine-scale estimation of wheat LAI at the low cost. While machine learning has proven valuable for LAI estimation, there are still model limitations and variations that impede accurate and efficient LAI inversion. This study explores the potential of classical machine learning models and deep learning model for estimating winter wheat LAI using multispectral images acquired by drones. Initially, the texture features and vegetation indices served as inputs for the partial least squares regression (PLSR) model and random forest (RF) model. Then, the ground-measured LAI data were combined to invert winter wheat LAI. In contrast, this study also employed a convolutional neural network (CNN) model that solely utilizes the cropped original image for LAI estimation. The results show that vegetation indices outperform the texture features in terms of correlation analysis with LAI and estimation accuracy. However, the highest accuracy is achieved by combining both vegetation indices and texture features to invert LAI in both conventional machine learning methods. Among the three models, the CNN approach yielded the highest LAI estimation accuracy (R2 = 0.83), followed by the RF model (R2 = 0.82), with the PLSR model exhibited the lowest accuracy (R2 = 0.78). The spatial distribution and values of the estimated results for the RF and CNN models are similar, whereas the PLSR model differs significantly from the first two models. This study achieves rapid and accurate winter wheat LAI estimation using classical machine learning and deep learning methods. The findings can serve as a reference for real-time wheat growth monitoring and field management practices.

show abstract

Section: Comparison Of Lai Inversion Using Vegetation Index and Textu...contrasting

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Inversion of winter wheat leaf area index from UAV multispectral images: classical vs. deep learning approaches

Zu,

Yang,

Wang

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…Numerous studies indicate that deep learning can better explore the latent deep features in images. However, most studies tend to investigate the combined effects of deep learning models with original data imagery for estimating crop parameters [40,61,[63][64][65][66]. Overlooking the contribution of the deep information contained in texture images.…”

Section: Impact Of Different Features and Models On Lcc And Fvc Estim...mentioning

confidence: 99%

Pretrained Deep Learning Networks and Multispectral Imagery Enhance Maize LCC, FVC, and Maturity Estimation

Hu,

Feng,

Wang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Crop leaf chlorophyll content (LCC) and fractional vegetation cover (FVC) are crucial indicators for assessing crop health, growth development, and maturity. In contrast to the traditional manual collection of crop trait parameters, unmanned aerial vehicle (UAV) technology rapidly generates LCC and FVC maps for breeding materials, facilitating prompt assessments of maturity information. This study addresses the following research questions: (1) Can image features based on pretrained deep learning networks and ensemble learning enhance the estimation of remote sensing LCC and FVC? (2) Can the proposed adaptive normal maturity detection (ANMD) algorithm effectively monitor maize maturity based on LCC and FVC maps? We conducted the following tasks: (1) Seven phases (tassel initiation to maturity) of maize canopy orthoimages and corresponding ground-truth data for LCC and six phases of FVC using UAVs were collected. (2) Three features, namely vegetation indices (VI), texture features (TF) based on Gray Level Co-occurrence Matrix, and deep features (DF), were evaluated for LCC and FVC estimation. Moreover, the potential of four single-machine learning models and three ensemble models for LCC and FVC estimation was evaluated. (3) The estimated LCC and FVC were combined with the proposed ANMD to monitor maize maturity. The research findings indicate that (1) image features extracted from pretrained deep learning networks more accurately describe crop canopy structure information, effectively eliminating saturation effects and enhancing LCC and FVC estimation accuracy. (2) Ensemble models outperform single-machine learning models in estimating LCC and FVC, providing greater precision. Remarkably, the stacking + DF strategy achieved optimal performance in estimating LCC (coefficient of determination (R2): 0.930; root mean square error (RMSE): 3.974; average absolute error (MAE): 3.096); and FVC (R2: 0.716; RMSE: 0.057; and MAE: 0.044). (3) The proposed ANMD algorithm combined with LCC and FVC maps can be used to effectively monitor maize maturity. Establishing the maturity threshold for LCC based on the wax ripening period (P5) and successfully applying it to the wax ripening-mature period (P5–P7) achieved high monitoring accuracy (overall accuracy (OA): 0.9625–0.9875; user’s accuracy: 0.9583–0.9933; and producer’s accuracy: 0.9634–1). Similarly, utilizing the ANMD algorithm with FVC also attained elevated monitoring accuracy during P5–P7 (OA: 0.9125–0.9750; UA: 0.878–0.9778; and PA: 0.9362–0.9934). This study offers robust insights for future agricultural production and breeding, offering valuable insights for the further exploration of crop monitoring technologies and methodologies.

show abstract

“…Very few studies have been carried out on tree crops, mainly on vineyards using higher spatial resolution remote sensing. This species is trained with the vertical shoot position trellis system or pergola system with horizontal shoot position [21,22], while hazelnut plant has a unique plant architecture with bush growth habit and dense foliage, three or four main branches, and canopy shape similar to the cylinder; all of this makes it more difficult to implement LAI models using UAV. For these reasons, in the present study, data determined using UAV referred only to canopy characteristics such as tree height.…”

Section: Manual Measurementsmentioning

confidence: 99%

Assessment of the Midseason Crop Coefficient for the Evaluation of the Water Demand of Young, Grafted Hazelnut Trees in High-Density Orchards

Vinci

Traini

Portarena

et al. 2023

Water

View full text Add to dashboard Cite

Knowledge of crop water requirements is important in supporting irrigation management. Evapotranspiration (ET) is commonly measured with a variety of instruments and field procedures, but it is also typically computed or modeled using the FAO56 or FAO66 methods. The adoption of this approach requires the assessment of the crop coefficients. Some data are available for own-rooted hazelnut trees, but no data have been reported for young and grafted hazelnut trees. There is a need to update nut–tree crop coefficients, especially considering modern cultivars and production systems, such as those with a high tree density per ha−1. In this paper, the FAO66 crop transpiration coefficient Kc,Tr and the FAO56 dual crop coefficients Kcb were assessed for the mid-growing season of a young grafted hazelnut orchard. The field data were acquired manually and using UAV. The coefficients were determined for three tree densities and for two growing seasons. The crop coefficients, obtained using the FAO66 method, agreed with the literature data referring to low densities, while the FAO56 method could allow us to better define the crop coefficients for high-density hazelnut orchards.

show abstract

Leaf area index estimation of pergola-trained vineyards in arid regions using classical and deep learning methods based on UAV-based RGB images

Cited by 21 publications

References 54 publications

Inversion of winter wheat leaf area index from UAV multispectral images: classical vs. deep learning approaches

Inversion of winter wheat leaf area index from UAV multispectral images: classical vs. deep learning approaches

Pretrained Deep Learning Networks and Multispectral Imagery Enhance Maize LCC, FVC, and Maturity Estimation

Assessment of the Midseason Crop Coefficient for the Evaluation of the Water Demand of Young, Grafted Hazelnut Trees in High-Density Orchards

Contact Info

Product

Resources

About