Spatially-explicit modelling with support of hyperspectral data can improve prediction of plant traits

Rocha, Alby Duarte; Groen, T.A.; Skidmore, A.K.

doi:10.1016/j.rse.2019.05.019

Cited by 19 publications

(19 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because this study is unique in this regard, there is a lack of literature to compare with. Still, the accuracy found here is similar to or even higher than those obtained by modeling different stresses effects in plants [21,[24][25][26][27].…”

Section: Discussionsupporting

confidence: 77%

“…Recently, machine learning approaches have been used in modeling the hyperspectral response of different conditions associated with vegetation [21]. The popular techniques used for analyzing data include regression analysis, vegetation indices, linear polarizations, wavelet-based filtering, and, currently, machine learning algorithms like random forest, decision tree, support vector machine (SVM), k-nearest neighbor (kNN), artificial neural networks (ANN), naïve Bayes (NB), and others [22][23][24][25].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modeling Hyperspectral Response of Water-Stress Induced Lettuce Plants Using Artificial Neural Networks

et al. 2019

View full text Add to dashboard Cite

Modeling the hyperspectral response of vegetables is important for estimating water stress through a noninvasive approach. This article evaluates the hyperspectral response of water-stress induced lettuce (Lactuca sativa L.) using artificial neural networks (ANN). We evenly split 36 lettuce pots into three groups: control, stress, and bacteria. Hyperspectral response was measured four times, during 14 days of stress induction, with an ASD Fieldspec HandHeld spectroradiometer (325–1075 nm). Both reflectance and absorbance measurements were calculated. Different biophysical parameters were also evaluated. The performance of the ANN approach was compared against other machine learning algorithms. Our results show that the ANN approach could separate the water-stressed lettuce from the non-stressed group with up to 80% accuracy at the beginning of the experiment. Additionally, this accuracy improved at the end of the experiment, reaching an accuracy of up to 93%. Absorbance data offered better accuracy than reflectance data to model it. This study demonstrated that it is possible to detect early stages of water stress in lettuce plants with high accuracy based on an ANN approach applied to hyperspectral data. The methodology has the potential to be applied to other species and cultivars in agricultural fields.

show abstract

Section: Discussionsupporting

confidence: 77%

Section: Introductionmentioning

confidence: 99%

Modeling Hyperspectral Response of Water-Stress Induced Lettuce Plants Using Artificial Neural Networks

et al. 2019

View full text Add to dashboard Cite

show abstract

“…RF is one of the most powerful methods in the current literature related to machine learning tasks [57][58][59][60][61][62]. The increase in data dimensionality is often seen as a problem for most traditional methods.…”

Section: Discussionmentioning

confidence: 99%

Leaf Nitrogen Concentration and Plant Height Prediction for Maize Using UAV-Based Multispectral Imagery and Machine Learning Techniques

et al. 2020

View full text Add to dashboard Cite

Under ideal conditions of nitrogen (N), maize (Zea mays L.) can grow to its full potential, reaching maximum plant height (PH). As a rapid and nondestructive approach, the analysis of unmanned aerial vehicles (UAV)-based imagery may be of assistance to estimate N and height. The main objective of this study is to present an approach to predict leaf nitrogen concentration (LNC, g kg−1) and PH (m) with machine learning techniques and UAV-based multispectral imagery in maize plants. An experiment with 11 maize cultivars under two rates of N fertilization was carried during the 2017/2018 and 2018/2019 crop seasons. The spectral vegetation indices (VI) normalized difference vegetation index (NDVI), normalized difference red-edge index (NDRE), green normalized difference vegetation (GNDVI), and the soil adjusted vegetation index (SAVI) were extracted from the images and, in a computational system, used alongside the spectral bands as input parameters for different machine learning models. A randomized 10-fold cross-validation strategy, with a total of 100 replicates, was used to evaluate the performance of 9 supervised machine learning (ML) models using the Pearson’s correlation coefficient (r), mean absolute error (MAE), coefficient of regression (R²), and root mean square error (RMSE) metrics. The results indicated that the random forest (RF) algorithm performed better, with r and RMSE, respectively, of 0.91 and 1.9 g.kg−¹ for LNC, and 0.86 and 0.17 m for PH. It was also demonstrated that VIs contributed more to the algorithm’s performances than individual spectral bands. This study concludes that the RF model is appropriate to predict both agronomic variables in maize and may help farmers to monitor their plants based upon their LNC and PH diagnosis and use this knowledge to improve their production rates in the subsequent seasons.

show abstract

“…The plant spectral signature provides a powerful and reduced cost alternative to field measurements to quantify the biochemical composition and functionality of vegetation over large areas (Homolová et al, 2013;Rocha et al, 2019). Remote sensing is a fundamental tool for the spatio-temporal analysis of vegetation's physiological status using different PT indicators and allowing us to consider not only the effects of late stages of disease (e.g.…”

Section: Current Strategies To Improve the Retrieval Of Physiological Indicatorsmentioning

confidence: 99%

“…Changes in plant traits (PTs) may alert managers to biotic and abiotic stressors and thus enable timely management interventions (Cunniffe et al, 2016). Hyperspectral signatures of plants provide an efficient alternative to standard field surveys by enabling monitoring of vegetation status (including biochemical and functional assessments) over large areas at a reduced cost (Homolová et al, 2013;Rocha et al, 2019). Recent studies provide evidence that the quantification of PT from hyperspectral and thermal images can successfully detect pre-visual symptoms of harmful crop pathogens, such as Xylella fastidiosa (Xf) infection in olive trees (Zarco-Tejada et al, 2018a).…”

Section: Introductionmentioning

confidence: 99%

Quantitative estimation of vegetation traits and temporal dynamics using 3-D radiative transfer models, high-resolution hyperspectral images and satellite imagery

Hornero¹

View full text Add to dashboard Cite

Large-scale monitoring of vegetation dynamics by remote sensing is key to detecting early signs of vegetation decline. Spectral-based indicators of phys-iological plant traits (PTs) have the potential to quantify variations in pho-tosynthetic pigments, chlorophyll fluorescence emission, and structural changes of vegetation as a function of stress. However, the specific response of PTs to disease-induced decline in heterogeneous canopies remains largely unknown, which is critical for the early detection of irreversible damage at different scales. Four specific objectives were defined in this research: i) to assess the feasibility of modelling the incidence and severity of Phytophthora cinnamomi and Xylella fastidiosa based on PTs and biophysical properties of vegetation; ii) to assess non-visual early indicators, iii) to retrieve PT using radiative transfer models (RTM), high-resolution imagery and satellite observations; and iv) to establish the basis for scaling up PTs at different spatial resolutions using RTM for their retrieval in different vegetation co-vers. This thesis integrates different approaches combining field data, air- and space-borne imagery, and physical and empirical models that allow the retrieval of indicators and the evaluation of each component’s contribution to understanding temporal variations of disease-induced symptoms in heter-ogeneous canopies. Furthermore, the effects associated with the understory are introduced, showing not only their impact but also providing a compre-hensive model to account for it. Consequently, a new methodology has been established to detect vegetation health processes and the influence of biotic and abiotic factors, considering different components of the canopy and their impact on the aggregated signal. It is expected that, using the presented methods, existing remote sensors and future developments, the ability to detect and assess vegetation health globally will have a substantial impact not only on socio-economic factors, but also on the preservation of our eco-system as a whole.

show abstract

Spatially-explicit modelling with support of hyperspectral data can improve prediction of plant traits

Cited by 19 publications

References 73 publications

Modeling Hyperspectral Response of Water-Stress Induced Lettuce Plants Using Artificial Neural Networks

Modeling Hyperspectral Response of Water-Stress Induced Lettuce Plants Using Artificial Neural Networks

Leaf Nitrogen Concentration and Plant Height Prediction for Maize Using UAV-Based Multispectral Imagery and Machine Learning Techniques

Quantitative estimation of vegetation traits and temporal dynamics using 3-D radiative transfer models, high-resolution hyperspectral images and satellite imagery

Contact Info

Product

Resources

About