Unveiling the transferability of PLSR models for leaf trait estimation: lessons from a comprehensive analysis with a novel global dataset.

Leaf traits are essential for understanding many physiological and ecological processes. Partial least squares regression (PLSR) models with leaf spectroscopy are widely applied for trait estimation, but their transferability across space, time, and plant functional types (PFTs) remains unclear. We compiled a novel dataset of paired leaf traits and spectra, with 47 393 records for > 700 species and eight PFTs at 101 globally distributed locations across multiple seasons. Using this dataset, we conducted an unprecedented comprehensive analysis to assess the transferability of PLSR models in estimating leaf traits. While PLSR models demonstrate commendable performance in predicting chlorophyll content, carotenoid, leaf water, and leaf mass per area prediction within their training data space, their efficacy diminishes when extrapolating to new contexts. Specifically, extrapolating to locations, seasons, and PFTs beyond the training data leads to reduced R2 (0.12-0.49, 0.15-0.42, and 0.25-0.56) and increased NRMSE (3.58-18.24%, 6.27-11.55%, and 7.0-33.12%) compared with nonspatial random cross-validation. The results underscore the importance of incorporating greater spectral diversity in model training to boost its transferability. These findings highlight potential errors in estimating leaf traits across large spatial domains, diverse PFTs, and time due to biased validation schemes, and provide guidance for future field sampling strategies and remote sensing applications.

Postprandial Plasma and Whole Blood Amino Acids Are Largely Indicative of Dietary Amino Acids in Adult Dogs Consuming Diets with Increasing Whole Pulse Ingredient Inclusion.

BACKGROUND: Pulse ingredients often replace grains in grain-free dog diets owing to their high-protein content. However, research to ascertain the benefit of this modification is limited. OBJECTIVES: This study aimed to correlate food compounds in 1 corn-inclusive control diet and 3 grain-free diets with increasing inclusions of whole pulses (≤45%; Pulse15, Pulse30, and Pulse45), formulated to meet similar macronutrient and micronutrient targets with postprandial amino acids (AAs) in healthy dogs >20 wk. METHODS: Diets were analyzed for biochemical compounds using tandem mass spectrometry. Twenty-eight outdoor-housed, healthy, adult Siberian Huskies were allocated to diet, and meal responses were analyzed at baseline and weeks 2, 4, 8, 16, and 20 with samples collected at fasted and 15, 30, 60, 90, 120, and 180 min after meal presentation. Blood AAs were analyzed by ultra performance liquid chromatography and differences across week, treatment, and time postmeal were analyzed in SAS Studio. Partial least squares regression was performed in SAS Studio using biochemical compounds in the diet as predictor variables and blood AAs as response variables. RESULTS: In plasma, Pulse45 had ∼32% greater postprandial Asn than Pulse15, and the control diet had ∼34% greater postprandial Leu and ∼35% greater Pro than Pulse15 (P < 0.05). In whole blood, Pulse30 had ∼23% greater postprandial Lys than the control diet, and the control diet had ∼21% greater postprandial Met and ∼18% greater Pro than Pulse45 and Pulse30, respectively (P < 0.05). Several phospholipids were correlated with postprandial AAs. Compounds in the urea cycle and glycine and serine metabolism were more enriched (P < 0.05) in plasma and whole blood, respectively. CONCLUSIONS: In macronutrient-balanced and micronutrient-balanced canine diets that differ in their inclusion of corn-derived compared with pulse-derived ingredients, postprandial changes in circulating AAs are largely indicative of the dietary AAs. This helps further our understanding of AA metabolism in healthy dogs fed grain-free diets.

Development and Validation of SCACOMS, a Composite Scale for Assessing Disease Progression and Treatment Effects in Spinocerebellar Ataxia.

Spinocerebellar ataxias (SCA) are rare inherited neurodegenerative disorders characterized by a progressive impairment of gait, balance, limb coordination, and speech. There is currently no composite scale that includes multiple aspects of the SCA experience to assess disease progression and treatment effects. Applying the method of partial least squares (PLS) regression, we developed the Spinocerebellar Ataxia Composite Scale (SCACOMS) from two SCA natural history datasets (NCT01060371, NCT02440763). PLS regression selected items based on their ability to detect clinical decline, with optimized weights based on the item's degree of progression. Following model validation, SCACOMS was leveraged to examine disease progression and treatment effects in a 48-week SCA clinical trial cohort (NCT03701399). Items from the Clinical Global Impression-Global Improvement Scale (CGI-I), the Friedreich Ataxia Rating Scale (FARS) - functional stage, and the Modified Functional Scale for the Assessment and Rating of Ataxia (f-SARA) were objectively selected with weightings based on their sensitivity to clinical decline. The resulting SCACOMS exhibited improved sensitivity to disease progression and greater treatment effects (compared to the original scales from which they were derived) in a 48-week clinical trial of a novel therapeutic agent. The trial analyses also provided a SCACOMS-derived estimate of the temporal delay in SCA disease progression. SCACOMS is a useful composite measure, effectively capturing disease progression and highlighting treatment effects in patients with SCA. SCACOMS will be a powerful tool in future studies given its sensitivity to clinical decline and ability to detect a meaningful clinical impact of disease-modifying treatments.

Hybrid 2D/3D-quantitative structure-activity relationship studies on the bioactivities and molecular mechanism of antibacterial peptides.

Antimicrobial peptide (AMP) is the polypeptide, which protects the organism avoiding attack from pathogenic bacteria. Studies have shown that there were some antimicrobial peptides with molecular action mechanism involved in crossing the cell membrane without inducing severe membrane collapse, then interacting with cytoplasmic target-nucleic acid, and exerting antibacterial activity by interfacing the transmission of genetic information of pathogenic microorganisms. However, the relationship between the antibacterial activities and peptide structures was still unclear. Therefore, in the present work, a series of AMPs with a sequence of 20 amino acids was extracted from DBAASP database, then, quantitative structure-activity relationship (QSAR) methods were conducted on these peptides. In addition, novel antimicrobial peptides with  stronger antimicrobial activities were designed according to the information originated from the constructed models. Hence, the outcome of this study would lay a solid foundation for the in-silico design and exploration of novel antibacterial peptides with improved activity activities.

In Situ Eutectic Formation in a Polymeric Matrix via Hot-Melt Reactive Extrusion and the Use of Partial Least Squares Regression Modeling for Reaction Yield Determination.

There has been a significant volume of work investigating the design and synthesis of new crystalline multicomponent systems via examining complementary functional groups that can reliably interact through the formation of noncovalent bonds, such as hydrogen bonds (H-bonds). Crystalline multicomponent molecular adducts formed using this approach, such as cocrystals, salts, and eutectics, have emerged as drug product intermediates that can lead to effective drug property modifications. Recent advancement in the production for these multicomponent molecular adducts has moved from batch techniques that rely upon intensive solvent use to those that are solvent-free, continuous, and industry-ready, such as reactive extrusion. In this study, a novel eutectic system was found when processing albendazole and maleic acid at a 1:2 molar ratio and successfully prepared using mechanochemical methods including liquid-assisted grinding and hot-melt reactive extrusion. The produced eutectic was characterized to exhibit a 100 °C reduction in melting temperature and enhanced dissolution performance (>12-fold increase at 2 h point), when compared to the native drug compound. To remove handling of the eutectic as a formulation intermediate, an end-to-end continuous-manufacturing-ready process enables feeding of the raw parent reagents in their respective natural forms along with a chosen polymeric excipient, Eudragit EPO. The formation of the eutectic was confirmed to have taken place in situ in the presence of the polymer, with the reaction yield determined using a multivariate calibration model constructed by combining spectroscopic analysis with partial least-squares regression modeling. The ternary extrudates exhibited a dissolution profile similar to that of the 1:2 prepared eutectic, suggesting a physical distribution (or suspension) of the in situ synthesized eutectic contents within the polymeric matrix.

Machine Learning Demonstrates Dominance of Physical Characteristics over Particle Composition in Coal Dust Toxicity.

Mine dust has been linked to the development of pneumoconiotic diseases such as silicosis and coal workers' pneumoconiosis. Currently, it is understood that the physicochemical and mineralogical characteristics drive the toxic nature of dust particles; however, it remains unclear which parameter(s) account for the differential toxicity of coal dust. This study aims to address this issue by demonstrating the use of the partial least squares regression (PLSR) machine learning approach to compare the influence of D50 sub 10 µm coal particle characteristics against markers of cellular damage. The resulting analysis of 72 particle characteristics against cytotoxicity and lipid peroxidation reflects the power of PLSR as a tool to elucidate complex particle-cell relationships. By comparing the relative influence of each characteristic within the model, the results reflect that physical characteristics such as shape and particle roughness may have a greater impact on cytotoxicity and lipid peroxidation than composition-based parameters. These results present the first multivariate assessment of a broad-spectrum data set of coal dust characteristics using latent structures to assess the relative influence of particle characteristics on cellular damage.

Cortical thickness differences are associated with cellular component morphogenesis of astrocytes and excitatory neurons in nonsuicidal self-injuring youth.

Nonsuicidal self-injury (NSSI) generally occurs in youth and probably progresses to suicide. An examination of cortical thickness differences (ΔCT) between NSSI individuals and controls is crucial to investigate potential neurobiological correlates. Notably, ΔCT are influenced by specific genetic factors, and a large proportion of cortical thinning is associated with the expression of genes that overlap in astrocytes and pyramidal cells. However, in NSSI youth, the mechanisms underlying the relations between the genetic and cell type-specific transcriptional signatures to ΔCT are unclear. Here, we studied the genetic association of ΔCT in NSSI youth by performing a partial least-squares regression (PLSR) analysis of gene expression data and 3D-T1 brain images of 45 NSSI youth and 75 controls. We extracted the top-10 Gene Ontology terms for the enrichment results of upregulated PLS component 1 genes related to ΔCT to conduct the cell-type classification and enrichment analysis. Enrichment of cell type-specific genes shows that cellular component morphogenesis of astrocytes and excitatory neurons accounts for the observed NSSI-specific ΔCT. We validated the main results in independent datasets to verify the robustness and specificity. We concluded that the brain ΔCT is associated with cellular component morphogenesis of astrocytes and excitatory neurons in NSSI youth.

SERS-based Ag NCs@PDMS flexible substrate combined with chemometrics for rapid detection of foodborne pathogens on egg surface.

An innovative method is introduced based on the combination of label-free surface-enhanced Raman scattering with advanced multivariate analysis. This technique allows both quantitative and qualitative assessment of Salmonella typhimurium and Escherichia coli on eggshells. Using silver nanocubes embedded in polydimethylsiloxane, we consistently achieved Raman spectra of bacteria. The stability of the Ag NCs@PDMS substrate is confirmed using rhodamine 6G over 30 days under standard conditions. Principal component analysis (PCA) effectively distinguishes between S. typhimurium and E. coli spectra. Partial least squares regression (PLS) models were developed for quantitative determination of bacteria on egg surfaces, yielding accurate results with minimal error. The S. typhimurium model achieves Rc2 = 0.9563 and RMSEC = 0.601 in calibration, and Rv2 = 0.9113 and RMSEV = 0.907 in validation. Similarly, the E. coli model achieves Rc2 = 0.9877 and RMSEC = 0.322 in calibration, and Rv2 = 0.9606 and RMSEV = 0.579 in validation. Recoveries validate PLS predictions by inoculating egg surfaces with varying bacterial amounts. Our study demonstrates the feasibility of SERS-PLS for quantitative determination of S. typhimurium and E. coli on eggshells, promising enhanced food safety protocols.

Comparative chemometric modeling of fresh and dry cannabis inflorescences using FT-NIR spectroscopy: Quantification and classification insights.

INTRODUCTION: Cannabis sativa L. inflorescences are rich in cannabinoids and terpenes. Traditional chemical analysis methods for cannabinoids and terpenes, such as liquid and gas chromatography (using UV or MS detectors), are expensive and time-consuming. OBJECTIVES: This study explores the use of Fourier transform near-infrared (FT-NIR) spectroscopy combined with chemometric approaches for classifying cannabis chemovars and predicting cannabinoid and terpene concentrations for the first time in freshly harvested (wet) cannabis inflorescence. The study also compares the performance of FT-NIR spectroscopy on wet versus dry cannabis inflorescences. MATERIALS AND METHODS: Spectral data from 187 samples across seven cannabis chemovars were analyzed using partial least squares-discriminant analysis (PLS-DA) and partial least squares-regression (PLS-R) models. RESULTS: The PLS-DA models effectively classified chemovars and major classes using only two latent variables (LVs) with minimal overfitting risk, with sensitivity, specificity, and accuracy values approaching 1. Despite the high water content in wet cannabis inflorescence, the PLS-R models demonstrated good to excellent predictive capabilities for nine cannabinoids and eight terpenes using FT-NIR spectra for the first time, achieving cross-validation and prediction R-squared values greater than 0.7, ratio of performance to interquartile range (RPIQ) exceeding 2, and a RMSECV/RMSEC ratio below 1.24. However, the low-cannabidiolic acid submodel and (-)-Δ9-trans-tetrahydrocannabinol model showed poor predictive performance. Some cannabinoid and terpene prediction models in wet cannabis inflorescence exhibited lower predictive capabilities compared with previously published models for dry cannabis inflorescence. CONCLUSIONS: These findings suggest that FT-NIR spectroscopy can be a viable rapid on-site analytical tool for growers during the inflorescence flowering stage.

Prediction of Soluble-Solid Content in Citrus Fruit Using Visible-Near-Infrared Hyperspectral Imaging Based on Effective-Wavelength Selection Algorithm.

Citrus fruits were sorted based on external qualities, such as size, weight, and color, and internal qualities, such as soluble solid content (SSC), acidity, and firmness. Visible and near-infrared (VNIR) hyperspectral imaging techniques were used as rapid and nondestructive techniques for determining the internal quality of fruits. The applicability of the VNIR hyperspectral imaging technique for predicting the SSC in citrus fruits was evaluated in this study. A VNIR hyperspectral imaging system with a wavelength range of 400-1000 nm and 100 W light source was used to acquire hyperspectral images from citrus fruits in two orientations (i.e., stem and calyx ends). The SSC prediction model was developed using partial least-squares regression (PLSR). Spectrum preprocessing, effective wavelength selection through competitive adaptive reweighted sampling (CARS), and outlier detection were used to improve the model performance. The performance of each model was evaluated using the coefficient of determination (R2) and root mean square error (RMSE). In the present study, the PLSR model was developed using only a citrus cultivar. The SSC prediction CARS-PLSR model with outliers removed exhibited R2 and RMSE values of approximatively 0.75 and 0.56 °Brix, respectively. The results of this study are expected to be useful in similar fields such as agricultural and food post-harvest management, as well as in the development of an online system for determining the SSC of citrus fruits.

Predicting Soil Organic Matter, Available Nitrogen, Available Phosphorus and Available Potassium in a Black Soil Using a Nearby Hyperspectral Sensor System.

Black soils, which play an important role in agricultural production and food security, are well known for their relatively high content of soil organic matter (SOM). SOM has a significant impact on the sustainability of farmland and provides nutrients for plants. Hyperspectral imaging (HSI) in the visible and near-infrared region has shown the potential to detect soil nutrient levels in the laboratory. However, using portable spectrometers directly in the field remains challenging due to variations in soil moisture (SM). The current study used spectral data captured by a handheld spectrometer outdoors to predict SOM, available nitrogen (AN), available phosphorus (AP) and available potassium (AK) with different SM levels. Partial least squares regression (PLSR) models were established to compare the predictive performance of air-dried soil samples with SMs around 20%, 30% and 40%. The results showed that the model established using dry sample data had the best performance (RMSE = 4.47 g/kg) for the prediction of SOM, followed by AN (RMSE = 20.92 mg/kg) and AK (RMSE = 22.67 mg/kg). The AP was better predicted by the model based on 30% SM (RMSE = 8.04 mg/kg). In general, model performance deteriorated with an increase in SM, except for the case of AP. Feature wavelengths for predicting four kinds of soil properties were recommended based on variable importance in the projection (VIP), which offered useful guidance for the development of portable hyperspectral sensors based on discrete wavebands to reduce cost and save time for on-site data collection.

Rapid Detection of Cleanliness on Direct Bonded Copper Substrate by Using UV Hyperspectral Imaging.

In the manufacturing process of electrical devices, ensuring the cleanliness of technical surfaces, such as direct bonded copper substrates, is crucial. An in-line monitoring system for quality checking must provide sufficiently resolved lateral data in a short time. UV hyperspectral imaging is a promising in-line method for rapid, contactless, and large-scale detection of contamination; thus, UV hyperspectral imaging (225-400 nm) was utilized to characterize the cleanliness of direct bonded copper in a non-destructive way. In total, 11 levels of cleanliness were prepared, and a total of 44 samples were measured to develop multivariate models for characterizing and predicting the cleanliness levels. The setup included a pushbroom imager, a deuterium lamp, and a conveyor belt for laterally resolved measurements of copper surfaces. A principal component analysis (PCA) model effectively differentiated among the sample types based on the first two principal components with approximately 100.0% explained variance. A partial least squares regression (PLS-R) model to determine the optimal sonication time showed reliable performance, with R2cv = 0.928 and RMSECV = 0.849. This model was able to predict the cleanliness of each pixel in a testing sample set, exemplifying a step in the manufacturing process of direct bonded copper substrates. Combined with multivariate data modeling, the in-line UV prototype system demonstrates a significant potential for further advancement towards its application in real-world, large-scale processes.

Performance Improvement of Partial Least Squares Regression Soluble Solid Content Prediction Model Based on Adjusting Distance between Light Source and Spectral Sensor according to Apple Size.

Apples are widely cultivated in the Republic of Korea and are preferred by consumers for their sweetness. Soluble solid content (SSC) is measured non-destructively using near-infrared (NIR) spectroscopy; however, the SSC measurement error increases with the change in apple size since the distance between the light source and the near-infrared sensor is fixed. In this study, spectral characteristics caused by the differences in apple size were investigated. An optimal SSC prediction model applying partial least squares regression (PLSR) to three measurement conditions based on apple size was developed. The three optimal measurement conditions under which the Vis/NIR spectrum is less affected by six apple size levels (Levels I-VI) were selected. The distance from the apple center to the light source and that to the sensor were 125 and 75 mm (Distance 1), 123 and 75 mm (Distance 2), and 135 and 80 mm (Distance 3). The PLSR model applying multiplicative scatter correction pretreatment under Distance 3 measurement conditions showed the best performance for Level IV-sized apples (Rpre2 = 0.91, RMSEP = 0.508 °Brix). This study shows the possibility of improving the SSC prediction performance of apples by adjusting the distance between the light source and the NIR sensor according to fruit size.

Fluorescence and Hyperspectral Sensors for Nondestructive Analysis and Prediction of Biophysical Compounds in the Green and Purple Leaves of Tradescantia Plants.

The application of non-imaging hyperspectral sensors has significantly enhanced the study of leaf optical properties across different plant species. In this study, chlorophyll fluorescence (ChlF) and hyperspectral non-imaging sensors using ultraviolet-visible-near-infrared shortwave infrared (UV-VIS-NIR-SWIR) bands were used to evaluate leaf biophysical parameters. For analyses, principal component analysis (PCA) and partial least squares regression (PLSR) were used to predict eight structural and ultrastructural (biophysical) traits in green and purple Tradescantia leaves. The main results demonstrate that specific hyperspectral vegetation indices (HVIs) markedly improve the precision of partial least squares regression (PLSR) models, enabling reliable and nondestructive evaluations of plant biophysical attributes. PCA revealed unique spectral signatures, with the first principal component accounting for more than 90% of the variation in sensor data. High predictive accuracy was achieved for variables such as the thickness of the adaxial and abaxial hypodermis layers (R2 = 0.94) and total leaf thickness, although challenges remain in predicting parameters such as the thickness of the parenchyma and granum layers within the thylakoid membrane. The effectiveness of integrating ChlF and hyperspectral technologies, along with spectroradiometers and fluorescence sensors, in advancing plant physiological research and improving optical spectroscopy for environmental monitoring and assessment. These methods offer a good strategy for promoting sustainability in future agricultural practices across a broad range of plant species, supporting cell biology and material analyses.

Quantitative analysis of solid dosage forms of Atenolol by Raman spectroscopy.

OBJECTIVE: To develop a Raman spectroscopy-based analytical model for quantification of solid dosage forms of active pharmaceutical ingredient (API) of Atenolol.Significance: For the quantitative analysis of pharmaceutical drugs, Raman Spectroscopy is a reliable and fast detection method. As part of this study, Raman Spectroscopy is explored for the quantitative analysis of different concentrations of Atenolol. METHODS: Various solid-dosage forms of Atenolol were prepared by mixing API with excipients to form different solid-dosage formulations of Atenolol. Multivariate data analysis techniques, such as Principal Component Analysis (PCA) and Partial least square regression (PLSR) were used for the qualitative and quantitative analysis, respectively. RESULTS: As the concentration of the drug increased in formulation, the peak intensities of the distinctive Raman spectral characteristics associated with the API (Atenolol) gradually increased. Raman spectral data sets were classified using PCA due to their distinctive spectral characteristics. Additionally, a prediction model was built using PLSR analysis to assess the quantitative relationship between various API (Atenolol) concentrations and spectral features. With a goodness of fit value of 0.99, the root mean square errors of calibration (RMSEC) and prediction (RMSEP) were determined to be 1.0036 and 2.83 mg, respectively. The API content in the blind/unknown Atenolol formulation was determined as well using the PLSR model. CONCLUSIONS: Based on these results, Raman spectroscopy may be used to quickly and accurately analyze pharmaceutical samples and for their quantitative determination.

Quantitative analysis of cephalexin in solid dosage form by Raman spectroscopy and chemometric tools.

OBJECTIVE: To use Raman Spectroscopy for qualitative and quantitative evaluation of pharmaceutical formulations of active pharmaceutical ingredient (API) of Cephalexin. SIGNIFICANCE: Raman Spectroscopy is a noninvasive, nondestructive, reliable and rapid detection technique used for various pharmaceutical drugs quantification. The present study explores the potential of Raman Spectroscopy for quantitative analysis of pharmaceutical drugs. METHOD: For qualitative and quantitative analysis of Cephalexin API, various standard samples containing less and more concentration of API than commercial tablet was prepared. To study spectral differences, the mean plot of all the samples was prepared. For qualitative analysis, Principal Component Analysis (PCA) and for quantitative analysis Partial Least Square Regression analysis (PLSR) was used. Both of these are Multivariate data analysis techniques and give reliable results as published in previous literature. RESULTS: PCA model distinguished all the Raman Spectral data related to the various Cephalexin solid dosage formulations whereas the PLSR model was used to calculate the concentration of different unknown formulations. For the PLSR model, RMSEC and RMSEP were determined to be 3.3953 and 3.8972, respectively. The prediction efficiency of this built PLSR model was found to be very good with a goodness of the model value (R2) of 0.98. The PLSR model also predicted the concentrations of Cephalexin formulations in the blind or unknown sample. CONCLUSION: These findings demonstrate that the Raman spectroscopy coupled to PLSR analysis could be regarded as a fast and effectively reliable tool for quantitative analysis of pharmaceutical drugs.

Statistical Characterization of Food-Derived α-Amylase Inhibitory Peptides: Computer Simulation and Partial Least Squares Regression Analysis.

α-Amylase inhibitory peptides are used to treat diabetes, but few studies have statistically characterized their interaction with α-amylase. This study performed the molecular docking of α-amylase with inhibitory peptides from published papers. The key sites, side chain chargeability, and hydrogen bond distribution characteristics were analyzed. Molecular dynamics simulated the role of key sites in complex stability. Moreover, partial least squares regression (PLSR) was used to analyze the contribution of different amino acids in the peptides to inhibition. The results showed that, for the α-amylase molecule, His201 and Gln63, with the highest interaction numbers (INs, 15, 15) and hydrogen bond values (HBVs, 11.50, 10.33), are the key sites on α-amylase, and amino acids with positively charged side chains were important for inhibitory activity. For the inhibitory peptides, Asp and Arg had the highest HBVs, and amino acids with charged side chains were more likely to form hydrogen bonds and exert inhibitory activity. In molecular dynamics simulations, peptides involving key binding sites formed more stable complexes with α-amylase than α-amylase alone, suggesting enhanced inhibitory effects. Further, PLSR results showed that amino acids close to the N-terminus of the inhibitory peptide, located in the third and fifth positions, were significantly correlated with its inhibitory activity. In conclusion, this study provides a new approach to developing and screening α-amylase inhibitors.

Recent exposure to environmental stochasticity does not determine the demographic resilience of natural populations.

Escalating climatic and anthropogenic pressures expose ecosystems worldwide to increasingly stochastic environments. Yet, our ability to forecast the responses of natural populations to this increased environmental stochasticity is impeded by a limited understanding of how exposure to stochastic environments shapes demographic resilience. Here, we test the association between local environmental stochasticity and the resilience attributes (e.g. resistance, recovery) of 2242 natural populations across 369 animal and plant species. Contrary to the assumption that past exposure to frequent environmental shifts confers a greater ability to cope with current and future global change, we illustrate how recent environmental stochasticity regimes from the past 50 years do not predict the inherent resistance or recovery potential of natural populations. Instead, demographic resilience is strongly predicted by the phylogenetic relatedness among species, with survival and developmental investments shaping their responses to environmental stochasticity. Accordingly, our findings suggest that demographic resilience is a consequence of evolutionary processes and/or deep-time environmental regimes, rather than recent-past experiences.

Predicting leaf traits across functional groups using reflectance spectroscopy.

Plant ecologists use functional traits to describe how plants respond to and influence their environment. Reflectance spectroscopy can provide rapid, non-destructive estimates of leaf traits, but it remains unclear whether general trait-spectra models can yield accurate estimates across functional groups and ecosystems. We measured leaf spectra and 22 structural and chemical traits for nearly 2000 samples from 103 species. These samples span a large share of known trait variation and represent several functional groups and ecosystems, mainly in eastern Canada. We used partial least-squares regression (PLSR) to build empirical models for estimating traits from spectra. Within the dataset, our PLSR models predicted traits such as leaf mass per area (LMA) and leaf dry matter content (LDMC) with high accuracy (R2 > 0.85; %RMSE < 10). Models for most chemical traits, including pigments, carbon fractions, and major nutrients, showed intermediate accuracy (R2  = 0.55-0.85; %RMSE = 12.7-19.1). Micronutrients such as Cu and Fe showed the poorest accuracy. In validation on external datasets, models for traits such as LMA and LDMC performed relatively well, while carbon fractions showed steep declines in accuracy. We provide models that produce fast, reliable estimates of several functional traits from leaf spectra. Our results reinforce the potential uses of spectroscopy in monitoring plant function around the world.

A leaf-level spectral library to support high-throughput plant phenotyping: predictive accuracy and model transfer.

Leaf-level hyperspectral reflectance has become an effective tool for high-throughput phenotyping of plant leaf traits due to its rapid, low-cost, multi-sensing, and non-destructive nature. However, collecting samples for model calibration can still be expensive, and models show poor transferability among different datasets. This study had three specific objectives: first, to assemble a large library of leaf hyperspectral data (n=2460) from maize and sorghum; second, to evaluate two machine-learning approaches to estimate nine leaf properties (chlorophyll, thickness, water content, nitrogen, phosphorus, potassium, calcium, magnesium, and sulfur); and third, to investigate the usefulness of this spectral library for predicting external datasets (n=445) including soybean and camelina using extra-weighted spiking. Internal cross-validation showed satisfactory performance of the spectral library to estimate all nine traits (mean R2=0.688), with partial least-squares regression outperforming deep neural network models. Models calibrated solely using the spectral library showed degraded performance on external datasets (mean R2=0.159 for camelina, 0.337 for soybean). Models improved significantly when a small portion of external samples (n=20) was added to the library via extra-weighted spiking (mean R2=0.574 for camelina, 0.536 for soybean). The leaf-level spectral library greatly benefits plant physiological and biochemical phenotyping, whilst extra-weight spiking improves model transferability and extends its utility.