Fifty Years of Advances in Hyperspectral Remote Sensing of Agriculture and Vegetation—Summary, Insights, and Highlights of Volume II

Thenkabail, Prasad S.; Lyon, J. G.; Huete, Alfredo

doi:10.1201/9781315159331-10

Cited by 7 publications

(10 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, we expect the mixture residual to impact different retrieval approaches in different ways. There is good theoretical justification to expect a significant difference in result for approaches that only use a subset of the spectral information, for example, narrowband spectral indexes (Thenkabail et al., 2018). An example using the mixture residual as a pretreatment for spectral indices is shown in Figure 10.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

The Spectral Mixture Residual: A Source of Low‐Variance Information to Enhance the Explainability and Accuracy of Surface Biology and Geology Retrievals

et al. 2022

View full text Add to dashboard Cite

Surface Biology and Geology (SBG) is an essential component of NASA's Earth System Observatory (Margetta, 2021) and a Designated Observable in the 2018 Decadal Survey (DS), with a candidate measurement approach of "hyperspectral imagery in the visible and shortwave infrared (IR), multi-or hyperspectral imagery in the thermal IR" (National Academies of Sciences, Engineering & Medicine, 2018). Photos collected by traditional digital cameras collect light in three broad wavelength intervals or bands-visible red, green, and blue.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Common tools include narrowband spectral indices (e.g. (Thenkabail et al., 2018)) and regression approaches like Partial Least Squares (Asner & Martin, 2009; Smith et al., 2002; Townsend et al., 2003), often focusing on brightly lit closed canopies at high spatial resolution.…”

Section: Introductionmentioning

confidence: 99%

The Spectral Mixture Residual: A Source of Low‐Variance Information to Enhance the Explainability and Accuracy of Surface Biology and Geology Retrievals

et al. 2022

View full text Add to dashboard Cite

show abstract

“…RGRI values measured for Quercus agrifolia depend on leaf age in the range of 0.5 - 1.5. SR values mainly fall into the range of 0 - 20 as observed for paddy rice fields in Italy and 10 - 20 for clonal Populus (Thenkabail et al, 2018). By contrast, the influence of chloroplast positioning is negligible for chlorophyll-dependent indices characterized by more complex formulae, such as the Enhanced Vegetation Index (EVI) and Atmospherically Resistant Vegetation Index (ARVI).…”

Section: Discussionmentioning

confidence: 88%

“…the content of water, nitrogen, lignin, cellulose, and pigments: chlorophyll, carotenoids, anthocyanins) and physiological traits (e.g. stress, changes in xanthophyll cycle pigments, fluorescence, leaf moisture) (Thenkabail et al, 2018). In particular, a large group of vegetation indices based on the visible or NIR reflectance (formulae in Supplementary Table S1) is used to assess the chlorophyll content, consisting of the classical NDVI (Rouse et al, 1974), but also SR (Rouse et al, 1974), EVI (Huete et al, 1997), ARVI (Kaufman & Tanre, 1995), RENDVI (Gitelson & Merzlyak, 1994), mRESR (Sims & Gamon, 2002), and a sum green index, (Behmann et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral imaging for chloroplast movement detection

Hermanowicz,

Łabuz

2024

Preprint

View full text Add to dashboard Cite

We employed hyperspectral imaging to assess chloroplast positions in Nicotiana benthamiana and Arabidopsis thaliana leaves. In low light, chloroplasts move to cell walls perpendicular to the direction of the incident light. In high light, they move to cell walls parallel to the light direction. Chloroplast movements result in significant changes in leaf transmittance and reflectance. The changes in leaf reflectance offer a way to examine chloroplast positioning in a non-contact way, however, they may confound remote sensing of other physiological traits. The shape of reflectance spectra recorded on irradiated and non-irradiated parts of N. benthamiana and A. thaliana leaves indicated the specific position of chloroplasts. Low blue light resulted in a decrease in differential leaf reflectance in the green-yellow region of the spectrum. High blue light irradiation caused a characteristic saddle in the green-yellow region and a peak at around 695 nm. The obtained curves were then used for training and validation using machine learning methods, including convolutional neural networks. Low levels of misclassification in both conditions, when the same or different species were used for training, serve as a proof-of-concept for this method. We also propose a Chloroplast Movement Index for validation of chloroplast positions in leaves. Moreover, the analysis of commonly used vegetation indices shows that their values may be altered due to chloroplast rearrangements. Our work indicates that changes in leaf reflectance due to chloroplast movements may be substantial and should be taken into account in remote sensing studies.

show abstract

“…Since the 1960s, using satellite imagery to measure reflectance of surfaces at a scale of tens of metres has been utilised to monitor vegetation health and to attempt to estimate and forecast changes in vegetation cover and condition (Thenkabail et al, 2019). More recently, these imagery methods have been deployed in more proximal sensors (planes, drones, vehicles) that allow analysis of vegetation at higher resolutions (to sub-centimetre scales) in a research field that is sometimes referred to as 'high-throughput phenotyping' (HTP) (Chapman et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Integration of APSIM and PROSAIL models to develop more precise radiometric estimation of crop traits using deep learning

Chen

Zheng

et al. 2021

Preprint

View full text Add to dashboard Cite

A major challenge for the estimation of crop traits (biophysical variables) from canopy reflectance is the creation of a high-quality training dataset. This can be addressed by using radiative transfer models (RTMs) to generate training dataset representing "real-world" data in situations with varying crop types and growth status as well as various observation configurations. However, this approach can lead to "ill-posed" problems related to assumptions in the sampling strategy and due to uncertainty in the model, resulting in unsatisfactory inversion results for retrieval of target variables. In order to address this problem, this research investigates a practical way to generate higher quality "synthetic" training data by integrating a crop growth model (CGM, in this case APSIM) with an RTM (in this case PROSAIL). This allows control of uncertainties of the RTM by imposing biological constraints on distribution and co-distribution of related variables. Subsequently, the method was theoretically validated on two types of synthetic dataset generated by PROSAIL or the coupling of APSIM and PROSAIL through comparing estimation precision for leaf area index (LAI), leaf chlorophyll content (Cab), leaf dry matter (Cm) and leaf water content (Cw). Additionally, the capabilities of current deep learning techniques using high spectral resolution hyperspectral data were investigated. The main findings include: (1) Feedforward neural network (FFNN) provided with appropriate configuration is a promising technique to retrieve crop traits from input features consisting of 1 nm-wide hyperspectral bands across 400-2500 nm range and observation configuration (solar and viewing angles), leading to a precise joint estimation for LAI (RMSE=0.061 m2 m-2), Cab (RMSE=1.42 μg cm-2), Cm (RMSE=0.000176 g cm-2) and Cw (RMSE=0.000319 g cm-2); (2) For the aim of model simplification, a narrower range in 400-1100 nm without observation configuration in input of FFNN model provided less precise estimation for LAI (RMSE=0.087 m2 m-2), Cab (RMSE=1.92 μg cm-2), Cm (RMSE=0.000299 g cm-2) and Cw (RMSE=0.001271 g cm-2); (3) The introduction of biological constraints in training datasets improved FFNN model performance in both average precision and stability, resulting in a much accurate estimation for LAI (RMSE=0.006 m2 m-2), Cab (RMSE=0.45 μg cm-2), Cm (RMSE=0.000039 g cm-2) and Cw (RMSE=0.000072 g cm-2), and this improvement could be further increased by enriching sample diversity in training dataset.

show abstract

Fifty Years of Advances in Hyperspectral Remote Sensing of Agriculture and Vegetation—Summary, Insights, and Highlights of Volume II

Cited by 7 publications

References 1 publication

The Spectral Mixture Residual: A Source of Low‐Variance Information to Enhance the Explainability and Accuracy of Surface Biology and Geology Retrievals

The Spectral Mixture Residual: A Source of Low‐Variance Information to Enhance the Explainability and Accuracy of Surface Biology and Geology Retrievals

Hyperspectral imaging for chloroplast movement detection

Integration of APSIM and PROSAIL models to develop more precise radiometric estimation of crop traits using deep learning

Contact Info

Product

Resources

About