The present study aimed to investigate the possibility of using hyperspectral imaging data to identify the invasive and weed species in agrocenoses ecosystem. The most common weeds in grain agrocenoses, i.e., Ambrosia artemisiifolia L., Euphorbia seguieriana Neck., Atriplex tatarica L., Glycyrrhiza glabra L., Setaria pumila (Poir.) Roem. and Schult, served as objects. The population of weeds, especially Ambrosia artemisiifolia is invasive for the selected region of study. Therefore, the shooting of objects was carried out with a hyperspectral camera, Cubert UHD185, and the values of 100 spectral channels were obtained from hyperspectral images. The values of 80 vegetation indices (VIs) were calculated. The material was processed using mathematical statistics (analysis of variance, t-test) and search methods of data analysis (principal component analysis, decision tree, and random forest). Using statistical methods, the simultaneous use of several VIs differentiated between species more deliberately and precisely. The combination of VIs Derivative index (D1), Chlorophyll content index (Datt3), and Pigment specific normalized difference (PSND) can be used for weeds identification. Using the decision tree method, VIs established a good division of weeds into groups; (1) perennial rhizomatous weeds (Euphorbia seguieriana, and Glycyrrhiza glabra), and (2) annual weeds (A. artemisiifolia, A. tatarica, and S. pumila); These Vis are Chlorophyll index (CI), D1, and Datt3. Using the random forest method, the VIs that have the greatest impact on Mean Decrease Accuracy and Mean Decrease Gini are D1, Datt3, PSND, and Double Peak Index (DPI). The use of spectral channel values for the identification of plant species using the principal component analysis, decision tree, and random forest methods showed worse results than when using VIs. A great similarity of the results was obtained with the help of statistical and search methods of data analysis.

Hyperspectral plant phenotyping is a method that has a wide range of applications in various fields, including agriculture, forestry, food processing, medicine and plant breeding. It can be used to obtain a large amount of spectral and spatial information about an object. However, it is important to acknowledge the inherent limitations of this approach, which include the presence of noise and the redundancy of information. The present study aims to assess a novel approach to hyperspectral data preprocessing, namely Random Reflectance (RR), for the classification of plant species. This study employs machine learning (ML) algorithms, specifically Random Forest (RF) and Gradient Boosting (GB), to analyse the performance of RR in comparison to Min–Max Normalisation (MMN) and Principal Component Analysis (PCA). The testing process was conducted on data derived from the proximal hyperspectral imaging (HSI) of leaves from three different maple species, which were sampled from trees at 7–10-day intervals between 2021 and 2024. The RF algorithm demonstrated a relative increase of 8.8% in the F1-score in 2021, 9.7% in 2022, 11.3% in 2023 and 11.8% in 2024. The GB algorithm exhibited a similar trend: 6.5% in 2021, 13.2% in 2022, 16.5% in 2023 and 17.4% in 2024. It has been demonstrated that hyperspectral data preprocessing with the MMN and PCA methods does not result in enhanced accuracy when classifying species using ML algorithms. The impact of preprocessing spectral profiles using the RR method may be associated with the observation that the synthesised set of spectral profiles exhibits a stronger reflection of the general parameters of spectral reflectance compared to the set of actual profiles. Subsequent research endeavours are anticipated to elucidate a mechanistic rationale for the RR method in conjunction with the RF and GB algorithms. Furthermore, the efficacy of this method will be evaluated through its application in deep machine learning algorithms.

Conifers are a common type of plant used in ornamental horticulture. The prompt diagnosis of the phenological state of coniferous plants using remote sensing is crucial for forecasting the consequences of extreme weather events. This is the first study to identify the “Vegetation” and “Dormancy” states in coniferous plants by analyzing their annual time series of spectral characteristics. The study analyzed Platycladus orientalis, Thuja occidentalis and T. plicata using time series values of 81 vegetation indices and 125 spectral bands. Linear discriminant analysis (LDA) was used to identify “Vegetation” and “Dormancy” states. The model contained three to four independent variables and achieved a high level of correctness (92.3 to 96.1%) and test accuracy (92.1 to 96.0%). The LDA model assigns the highest weight to vegetation indices that are sensitive to photosynthetic pigments, such as the photochemical reflectance index (PRI), normalized PRI (PRI_norm), the ratio of PRI to coloration index 2 (PRI/CI2), and derivative index 2 (D2). The random forest method also diagnoses the “Vegetation” and “Dormancy” states with high accuracy (97.3%). The vegetation indices chlorophyll/carotenoid index (CCI), PRI, PRI_norm and PRI/CI2 contribute the most to the mean decrease accuracy and mean decrease Gini. Diagnosing the phenological state of conifers throughout the annual cycle will allow for the effective planning of management measures in conifer plantations.

Hyperspectral imaging techniques are widely used to remotely assess the vegetation and physiological condition of plants. Usually, such studies are carried out without taking into account the light history of the objects (for example, direct sunlight or light scattered by clouds), including light-stress conditions (photoinhibition). In addition, strong photoinhibitory lighting itself can cause stress. Until now, it is unknown how light history influences the physiologically meaningful spectral indices of reflected light. In the present work, shifts in the spectral reflectance characteristics of Ficus elastica leaves caused by 10 h exposure to photoinhibitory white LED light, 200 μmol photons m⁻² s⁻¹ (light stress), and moderate natural light, 50 μmol photons m⁻² s⁻¹ (shade) are compared to dark-adapted plants. Measurements were performed with a Cubert UHD-185 hyperspectral camera in discrete spectral bands centred on wavelengths from 450 to 950 nm with a 4 nm step. It was shown that light stress leads to an increase in reflection in the range of 522–594 nm and a decrease in reflection at 666–682 nm. The physiological causes of the observed spectral shifts are discussed. Based on empirical data, the light-stress index (LSI) = mean(R_666:682)/mean(R_552:594) was calculated and tested. The data obtained suggest the possibility of identifying plant light stress using spectral sensors that remotely fix passive reflection with the need to take light history into account when analysing hyperspectral data.

The development of methods to detect plant stress is not only a scientific challenge, but is also of great importance for agriculture and forestry. However, at present, stress diagnostics based on plant spectral characteristics has several limitations: (1) the high dependence of stress assessment on plant species identity; (2) the poor differentiation of different types of stress; and (3) the difficulty of detecting stress before visible symptoms appear. In this regard, the development of plant spectral metrics represents a significant area of research. Ficus elastica plants were exposed under the photosynthetic photon flux density (PPFD) from 0 to 1200 μmol photons m⁻²s⁻¹. Exposure of F. elastica leaves to excess light (EL) (≥400 μmol photons m⁻²s⁻¹) resulted in an increase in reflectance in the yellow-green region (522–594 nm) and a decrease in reflectance in the red region (666–682 nm) of the spectrum, accompanied by a shift of the red edge point toward the longer wavelength. These changes were revealed using the previously proposed light stress index (LSI = mean(R_666:682)/mean(R_522:594)). Based on the results obtained, two new vegetation indices (VIs) were proposed: LSI_Red = R₆₇₄/R₆₅₄ and LSI_Norm = (R₆₇₄ − R₆₅₄)/(R₆₇₄ + R₆₅₄), indicating light stress by changes in the red region of the spectrum. The results of the study showed that LSI, LSI_Red, and LSI_Norm have a high degree of coupling strength with maximal quantum yields of photosystem II values. The plant response to EL exposure, as assessed by the values of these three VIs, was well expressed regardless of the PPFD levels. The effect of EL at non-stressful PPFDs (50–200 μmol photons m⁻²s⁻¹) was found to disappear within one hour after cessation of exposure. In contrast, the effect of the stressful PPFD (800 μmol photons m⁻²s⁻¹) was found to persist for at least 80 h after cessation of exposure. The results of the study indicate the need to consider light history in spectral monitoring of vegetation.