Estimation of Above-Ground Biomass of Winter Wheat Based on Consumer-Grade Multi-Spectral UAV

Wang, Falv; Yang, Mao; Ma, Longfei; Zhang, Tong; Qin, Weilong; Li, Wei; Zhang, Yinghua; Sun, Zhigao; Wang, Zhimin; Li, Fēi; Yu, Kang

doi:10.3390/rs14051251

Cited by 51 publications

(42 citation statements)

References 114 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Previous studies have shown that preprocessing of spectra can effectively eliminate noise and baseline drift and highlight the location of spectral feature bands (Arneberg et al, 2007). The accuracy of the models built using relevant studies (Nguyen and Lee, 2006;Li et al, 2016;Wang et al, 2020;Li et al, 2020b) using different forms of spectral transformations is higher than the models built using the original spectra. Feature screening mainly solves the collinearity problem of the spectrum, and wavelengths with less redundant information are selected for direct model construction, which is a simple, fast, and intuitive method easy to implement (Bai et al, 2018;Jia et al, 2019).…”

Section: Discussionmentioning

confidence: 98%

Study on the nitrogen content estimation model of cotton leaves based on “image-spectrum-fluorescence” data fusion

et al. 2023

View full text Add to dashboard Cite

ObjectivePrecise monitoring of cotton leaves’ nitrogen content is important for increasing yield and reducing fertilizer application. Spectra and images are used to monitor crop nitrogen information. However, the information expressed using nitrogen monitoring based on a single data source is limited and cannot consider the expression of various phenotypic and physiological parameters simultaneously, which can affect the accuracy of inversion. Introducing a multi-source data-fusion mechanism can improve the accuracy and stability of cotton nitrogen content monitoring from the perspective of information complementarity.MethodsFive nitrogen treatments were applied to the test crop, Xinluzao No. 53 cotton, grown indoors. Cotton leaf hyperspectral, chlorophyll fluorescence, and digital image data were collected and screened. A multilevel data-fusion model combining multiple machine learning and stacking integration learning was built from three dimensions: feature-level fusion, decision-level fusion, and hybrid fusion.ResultsThe determination coefficients (R2) of the feature-level fusion, decision-level fusion, and hybrid-fusion models were 0.752, 0.771, and 0.848, and the root-mean-square errors (RMSE) were 3.806, 3.558, and 2.898, respectively. Compared with the nitrogen estimation models of the three single data sources, R2 increased by 5.0%, 6.8%, and 14.6%, and the RMSE decreased by 3.2%, 9.5%, and 26.3%, respectively.ConclusionThe multilevel fusion model can improve accuracy to varying degrees, and the accuracy and stability were highest with the hybrid-fusion model; these results provide theoretical and technical support for optimizing an accurate method of monitoring cotton leaf nitrogen content.

show abstract

Section: Discussionmentioning

confidence: 98%

Study on the nitrogen content estimation model of cotton leaves based on “image-spectrum-fluorescence” data fusion

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The multiple types of VIs can make more extensive use of waveband information and provide more complementary predictors for the NC model construction. Thus, the machine learning algorithms have the ability to integrate and utilize the spectral information contained in VIs, which could be the explanation for the great performance achieved for the combined use of VIs (Wang et al, 2022a). However, probably due to the contrasting correlation patterns observed here - VIs and TF were correlated positively and negatively with NC respectively, the combined use of both types of variables did not improve the predictions of NC.…”

Section: Discussionmentioning

confidence: 99%

“…The spectral resolution of the monochromatic sensors includes: a blue band with 450 nm center and 16 nm bandwidth, a green band with 560 nm center and 16 nm bandwidth, a red band with 650 nm center and 16 nm bandwidth, a red-edge band with 730 nm and 16 nm bandwidth and a near-infrared band with 840 nm and 26 nm bandwidth. More specific parameters of the UAV and the camera are demonstrated in (Wang et al, 2022a).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Characterization of N distribution in different organs of winter wheat using UAV-based remote sensing

Wang

Liu

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Although unmanned aerial vehicle (UAV) remote sensing is widely used for high-throughput crop monitoring, few attempts have been made to assess nitrogen content (NC) at the organ level and its impact on nitrogen use efficiency (NUE). Also, little is known about the performance of UAV-based image texture features in crop nitrogen and NUE monitoring. In this study, eight flying missions were carried out throughout different stages of winter wheat (from the jointing stage to the stage 25 days after flowering) to acquire multispectral images. Forty-three multispectral vegetation indices (VIs) and forty texture features (TFs) were calculated from images and fed into the partial least squares regression (PLSR) and random forest (RF) regression models for predicting nitrogen-related indicators. Our main purposes were to (1) evaluate the potential of UAV-based images to predict NC in different organs of winter wheat and nitrogen agronomic efficiency (NAE); (2) compare the performances of VIs, TFs and the combination of them for nitrogen monitoring. The results showed that the correlation between different features (VIs and TFs) and NC in different organs varied between the vegetative and reproductive phases. Most of VIs were found to be positively correlated with NC, while most of the TFs were negatively correlated with NC. PLSR latent variables extracted from VIs and TFs explained 80% of the variations in NAE. However, no significant differences were found between VIs and TFs in their performance in predicting NC in different organs. This study demonstrated the promise of applying UAV-based imaging to estimate NC and NAE in different organs of winter wheat.

show abstract

“…How to disentangle the individual contribution of the LAI and suppress the LCC signals in canopy reflectance is thus essential and indispensable for LAI estimation. Besides, spectral saturation issue often happens in the dense vegetated JSTARS-2022-01606 condition [15,16], and this further weaken the LAI estimating accuracy in large LAIs.…”

Section: Introductionmentioning

confidence: 99%

Improving Leaf Area Index Estimation With Chlorophyll Insensitive Multispectral Red-Edge Vegetation Indices

Sun

Wang

Zhang

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

As an essential vegetation biophysical trait that determines the plant's structure and photosynthetic capacity, characterizing of leaf area index (LAI) is important for vegetation growth and health monitoring. The empirical models based on vegetation indices (VIs) from remote sensing images is an effective method for deriving LAI. However, due to the coupled impacts of LAI and leaf chlorophyll content (LCC) on canopy reflectance and saturation effect, most VIs cannot achieve a good accuracy of LAI estimation. The remotely sensed red-edge reflectance can provide valuable information to delineate the LAI, therefore a series of leaf chlorophyll insensitive red-edge VIs by using the Sentinel-2 and GF-6 multispectral images are developed in this work to improve the LAI estimation accuracy. The potentials of reflecting LAI variations and sensitivity to LCC changes for each Sentinel-2 and GF-6 red-edge band are comprehensively analyzed based on the PROSAIL model to select the optimal band in VIs design. The proposed VIs are then evaluated in multiple ways, including with PROSAIL simulated datasets, ground measured LAI with canopy spectra and real satellite images. The evaluation results based on field LAI measurements indicate that the proposed red-edge VIs can effectively improve crop LAI estimation accuracy with the best regression coefficient (R 2 =0.81 for Sentinel-2 and R 2 =0.65 for GF-6) among all comparative VIs. Our work showcases incorporating red-edge bands with suitable formula is promising for improving VI-based LAI retrieval, and they offer a practicable solution to fast achieve decameter LAI maps by using the Sentinel-2 or GF-6 images.

show abstract

Estimation of Above-Ground Biomass of Winter Wheat Based on Consumer-Grade Multi-Spectral UAV

Cited by 51 publications

References 114 publications

Study on the nitrogen content estimation model of cotton leaves based on “image-spectrum-fluorescence” data fusion

Study on the nitrogen content estimation model of cotton leaves based on “image-spectrum-fluorescence” data fusion

Characterization of N distribution in different organs of winter wheat using UAV-based remote sensing

Improving Leaf Area Index Estimation With Chlorophyll Insensitive Multispectral Red-Edge Vegetation Indices

Contact Info

Product

Resources

About