Random Regression Research Articles

Board Characteristics and Bank Stock Performance: Empirical Evidence from the MENA Region

This study examined the relationship between the board characteristics and stock performance of commercial banks. Our analysis is based on a sample of 65 banks across 10 MENA countries and their quantitative data extracted between 2013 and 2022. This research employed pooled OLS, and fixed and random effect regression to confirm the association between board size, board independence, number of board meetings, and CEO duality with stock performance measured by the bank’s share price and market-to-book ratio. Further, several control variables were utilized such as the bank’s capital adequacy, profitability, and size. The empirical findings reveal that board independence positively affects the bank stock performance while the board size shows a negative relationship. This suggests that banks with fewer board members and high independence levels have their shares outperforming others. However, we found that having frequent board meetings per year and separate roles for the CEO and chairman have no impact on bank stock performance. Moreover, the findings indicate that the bank’s capital adequacy, size, and profitability have a positive effect on the stock performance. To test the robustness of our analysis, we implemented a one-limit Tobit model, which enables lower-bound censoring, and obtained similar findings thus confirming our hypotheses. From a practical perspective, our findings highlight the importance of the board size and the directors’ independence to MENA regulators and policymakers in an effort to implement an effective corporate governance system. Specifically, MENA banks are advised to decrease the number of board members, and this should reduce the number of annual board meetings which, in turn, should maximize performance.

An evaluation of the impact of social and structural determinants of health on forgone care during the COVID-19 pandemic in Baltimore, Maryland.

Evidence suggests that reductions in healthcare utilization, including forgone care, during the COVID-19 pandemic may be contributing towards excess morbidity and mortality. The objective of this study was to describe individual and community-level correlates of forgone care during the COVID-19 pandemic. We conducted a cross-sectional, secondary data analysis of participants (n = 2,003) who reported needing healthcare in two population-representative surveys conducted in Baltimore, MD in 2021 and 2021-2022. Abstracted data included the experience of forgone care, socio-demographic data, comorbidities, financial strain, and community of residence. Participant's community of residence were linked with data acquired from the Baltimore Neighborhood Indicators Alliance relevant to healthcare access and utilization, including walkability and internet access, among others. The data were analyzed using weighted random effects logistic regression. Individual-level factors found to be associated with increased odds for forgone care included individuals age 35-49 (compared to 18-34), female sex, experiencing housing insecurity during the pandemic, and the presence of functional limitations and mental illness. Black/African American individuals were found to have reduced odds of forgone care, compared to any other race. No community-level factors were significant in the multilevel analyses. Moving forward, it will be critical that health systems identify ways to address any barriers to care that populations might be experiencing, such as the use of mobile health services or telemedicine platforms. Additionally, public health emergency preparedness planning efforts must account for the unique needs of communities during future crises, to ensure that their health needs can continue to be met. Finally, additional research is needed to better understand how healthcare access and utilization practices have changed during versus before the pandemic.

Predicting the properties of perovskite materials by improved compositionally restricted attention-based networks and explainable machine learning

Understanding the unique properties of perovskite materials is crucial in advancing solar energy technologies. Factors like heat of formation and bandgap significantly influence the light absorption capability and stability of perovskite solar cells. However, it is time-consuming and labor-intensive to obtain the properties of perovskites using traditional experimental or high-throughput computational methods. As a prospective method, machine learning can find regularities in the given training data and give accurate prediction results. In this article, we use deep learning models based on attention mechanisms and elemental features to predict the heat of formation and bandgap of perovskite materials. Random Forest and Gradient Boosted Regression Tree models have also been used for interpretable predictions of properties. The compositionally restricted attention-based network was improved by introducing a densely connected network and optimizing the network structure to increase data processing capabilities. The experiment results show that the mean absolute errors of the heat of formation and bandgap on the test sets are decreased by 5.77% and 3.37% respectively. The optimized model also shows better performance when used for classification tasks. In addition, we use the gradient boosting regression tree model and the shapley additive explanations tool to conduct an interpretable analysis, explaining the impact of different features on the predictions of the properties.

Prediction of energy consumption for manufacturing small and medium-sized enterprises (SMEs) considering industry characteristics

There has been a growing demand for energy consumption statistics in the manufacturing industry to establish national energy and greenhouse gas policies. Despite its importance, the Korean government faces significant challenges in collecting energy data at a facility level in a precise and timely manner. To address the lack of timely data, this paper employs machine-learning models to predict the annual total energy consumptions of each manufacturing facility. We first designed four prediction models that take into account the characteristics and energy consumption behaviors of industry sub-sectors. As input variables, these prediction models mainly included electricity consumption, employee size, energy types, gas consumption and other accessible data. Finally, we conducted numerical experiments on approximately 100,000 facilities and evaluated the prediction performance of various machine-learning algorithms such as linear regression, decision tree regression, random forest regression, gradient boost regression, and extreme gradient boosting regression. The numerical experiments provided insights into which model and algorithm offer the best prediction performance for each industry sub-sector. In addition, we identified the important variables for predicting total energy consumption, revealing that not only electricity but also various other energy sources and variables representing industry-specific characteristics play a crucial role in improving prediction performance.

Crop Phenology Estimation in Rice Fields Using Sentinel-1 GRD SAR Data and Machine Learning-Aided Particle Filtering Approach

Abstract. Monitoring crop phenology is essential for managing field disasters, protecting the environment, and making decisions about agricultural productivity. Because of its high timeliness, high resolution, great penetration, and sensitivity to specific structural elements, synthetic aperture radar (SAR) is a valuable technique for crop phenology estimation. Particle filtering (PF) belongs to the family of dynamical approach and has the ability to predict crop phenology with SAR data in real time. The observation equation is a key factor affecting the accuracy of particle filtering estimation and depends on fitting. Compared to the common polynomial fitting (POLY), machine learning methods can automatically learn features and handle complex data structures, offering greater flexibility and generalization capabilities. Therefore, incorporating two ensemble learning algorithms consisting of support vector machine regression (SVR), random forest regression (RFR), respectively, we proposed two machine learning-aided particle filtering approaches (PF-SVR, PF-RFR) to estimate crop phenology. One year of time-series Sentinel-1 GRD SAR data in 2017 covering rice fields in Sevilla region in Spain was used for establishing the observation and prediction equations, and the other year of data in 2018 was used for validating the prediction accuracy of PF methods. Four polarization features (VV, VH, VH/VV and Radar Vegetation Index (RVI)) were exploited as the observations in modeling. Experimental results reveals that the machine learning-aided methods are superior than the PF-POLY method. The PF-SVR exhibited better performance than the PF-RFR and PF-POLY methods. The optimal outcome from PF-SVR yielded a root-mean-square error (RMSE) of 7.79, compared to 7.94 for PF-RFR and 9.1 for PF-POLY. Moreover, the results suggest that the RVI is generally more sensitive than other features to crop phenology and the performance of polarization features presented consistent among all methods, i.e., RVI＞VV＞VH＞VH/VV. Our findings offer valuable references for real-time crop phenology monitoring with SAR data.

Forecasting oil futures returns with news

This paper aims to explore the extent to which text data contains valuable information for predicting oil futures returns. A novel mixed-frequency data sampling random forest regression (MIDAS-RF) approach is proposed to construct a textual indicator. This approach can extract nonlinearity and interaction information from news and allows us to better handle the mixed-frequency and high-dimensional data. Comparing it with traditional sentiment variables and financial factors, our indicator demonstrates better forecasting performance both statistically and economically, with a monthly out-of-sample R2 of 5.26% and an annualized certainty equivalent return gain of 3.08%, respectively. Further evidence suggests that the predictability of the textual indicator is primarily driven by words related to capital markets and macroeconomic topics.

Nomogram for predicting post-therapy recurrence in BCLC A/B hepatocellular carcinoma with Child-Pugh B cirrhosis.

This study conducts a retrospective analysis on patients with BCLC stage A/B hepatocellular carcinoma (HCC) accompanied by Child-Pugh B cirrhosis, who underwent transarterial chemoembolization (TACE) in combination with local ablation therapy. Our goal was to uncover risk factors contributing to post-treatment recurrence and to develop and validate an innovative 1-, 3-, and 5-year recurrence free survival (RFS) nomogram. Data from 255 BCLC A/B HCC patients with Child-Pugh B cirrhosis treated at Beijing You'an Hospital (January 2014 - January 2020) were analyzed using random survival forest (RSF), LASSO regression, and multivariate Cox regression to identify independent risk factors for RFS. The prognostic nomogram was then constructed and validated, categorizing patients into low, intermediate, and high-risk groups, with RFS assessed using Kaplan-Meier curves. The nomogram, integrating the albumin/globulin ratio, gender, tumor number, and size, showcased robust predictive performance. Harrell's concordance index (C-index) values for the training and validation cohorts were 0.744 (95% CI: 0.703-0.785) and 0.724 (95% CI: 0.644-0.804), respectively. The area under the curve (AUC) values for 1-, 3-, and 5-year RFS in the two cohorts were also promising. Calibration curves highlighted the nomogram's reliability and decision curve analysis (DCA) confirmed its practical clinical benefits. Through meticulous patient stratification, we also revealed the nomogram's efficacy in distinguishing varying recurrence risks. This study advances recurrence prediction in BCLC A/B HCC patients with Child-Pugh B cirrhosis following TACE combined with ablation. The established nomogram accurately predicts 1-, 3-, and 5-year RFS, facilitating timely identification of high-risk populations.

Interpretable Machine Learning for Geochemical Anomaly Delineation in the Yuanbo Nang District, Gansu Province, China

Machine learning (ML) has shown its effectiveness in handling multi-geoinformation. Yet, the black-box nature of ML algorithms has restricted their widespread adoption in the domain of mineral prospectivity mapping (MPM). In this paper, methods for interpreting ML model predictions are introduced to aid ML-based MPM, with the goal of extracting richer insights from the ML modeling of an exploration geochemical dataset. The partial dependence plot (PDP) and accumulated local effect (ALE) plot, along with the SHAP value analysis, were utilized to demonstrate the application of random forest (RF) modeling within both regression and classification frameworks. Initially, the random forest regression (RFR) model established the relationship between the concentrations of Au and those of elements such as As, Sb, and Hg in the study area, and from this model, the most important geochemical elements and their quantitative relationships with Au were revealed by their contributions in the modeling through PDP and ALE analyses. Secondly, the RF classification modeling established the relationships of mineralization occurrences (i.e., known mineral deposits) with geochemical elements (i.e., Au, As, Sb, Hg, Cu, Pb, Zn, and Ag), as did RFR modeling. The most important geochemical elements for indicating regional Au mineralization and the trajectories of PDP and ALE reached a consensus that As and Sb contributed the most, both in the regression and classification modeling, with regard to Au mineralization. Finally, the SHAP values illustrated the behavior of the training samples (i.e., known mineral deposits) in RF modeling, and the resulting prospectivity map was evaluated using receiver operating characteristics.

A culture-independent approach, supervised machine learning, and the characterization of the microbial community composition of coastal areas across the Bay of Bengal and the Arabian Sea

BackgroundCoastal areas are subject to various anthropogenic and natural influences. In this study, we investigated and compared the characteristics of two coastal regions, Andhra Pradesh (AP) and Goa (GA), focusing on pollution, anthropogenic activities, and recreational impacts. We explored three main factors influencing the differences between these coastlines: The Bay of Bengal’s shallower depth and lower salinity; upwelling phenomena due to the thermocline in the Arabian Sea; and high tides that can cause strong currents that transport pollutants and debris.ResultsThe microbial diversity in GA was significantly higher than that in AP, which might be attributed to differences in temperature, soil type, and vegetation cover. 16S rRNA amplicon sequencing and bioinformatics analysis indicated the presence of diverse microbial phyla, including candidate phyla radiation (CPR). Statistical analysis, random forest regression, and supervised machine learning models classification confirm the diversity of the microbiome accurately. Furthermore, we have identified 450 cultures of heterotrophic, biotechnologically important bacteria. Some strains were identified as novel taxa based on 16S rRNA gene sequencing, showing promising potential for further study.ConclusionThus, our study provides valuable insights into the microbial diversity and pollution levels of coastal areas in AP and GA. These findings contribute to a better understanding of the impact of anthropogenic activities and climate variations on biology of coastal ecosystems and biodiversity.

Photothermal Radiometry Data Analysis by Using Machine Learning.

Photothermal techniques are infrared remote sensing techniques that have been used for biomedical applications, as well as industrial non-destructive testing (NDT). Machine learning is a branch of artificial intelligence, which includes a set of algorithms for learning from past data and analyzing new data, without being explicitly programmed to do so. In this paper, we first review the latest development of machine learning and its applications in photothermal techniques. Next, we present our latest work on machine learning for data analysis in opto-thermal transient emission radiometry (OTTER), which is a type of photothermal technique that has been extensively used in skin hydration, skin hydration depth profiles, skin pigments, as well as topically applied substances and skin penetration measurements. We have investigated different algorithms, such as random forest regression, gradient boosting regression, support vector machine (SVM) regression, and partial least squares regression, as well as deep learning neural network regression. We first introduce the theoretical background, then illustrate its applications with experimental results.

Temporal dynamics of fecal microbiota community succession in broiler chickens, calves, and piglets under aerobic exposure.

Researchers have extensively studied the effect of oxygen on the growth and survival of bacteria. However, the impact of oxygen on bacterial community structure, particularly its ability to select for taxa within the context of a complex microbial community, is still unclear. In a 21-day microcosm experiment, we investigated the effect of aerobic exposure on the fecal community structure and succession pattern in broiler, calf, and piglet feces (n = 10 for each feces type). Bacterial diversity decreased and community structure changed rapidly in the broiler microbiome (P < 0.001), while the fecal community of calves and piglets, which have higher initial diversity, was stable after initial exposure but decreased in diversity after 3 days (P < 0.001). The response to aerobic exposure was host animal specific, but in all three animals, the change in community structure was driven by a decrease in anaerobic species, primarily belonging to Firmicutes and Bacteroidetes (except in broilers where Bacteroidetes increased), along with an increase in aerobic species belonging to Proteobacteria and Actinobacteria. Using random forest regression, we identified microbial features that predict aerobic exposure. In all three animals, host-beneficial Prevotella-related ASVs decreased after exposure, while ASVs belonging to Acinetobacter, Corynbacterium, and Tissierella were increased. The decrease of Prevotella was rapid in broilers but delayed in calves and piglets. Knowing when these pathobionts increase in abundance after aerobic exposure could inform farm sanitation practices and could be important in designing animal experiments that modulate the microbiome.IMPORTANCEThe fecal microbial community is contained within a dynamic ecosystem of interacting microbes that varies in biotic and abiotic components across different animal species. Although oxygen affects bacterial growth, its specific impact on the structure of complex communities, such as those found in feces, and how these effects vary between different animal species are poorly understood. In this study, we demonstrate that the effect of aerobic exposure on the fecal microbiota was host-animal-specific, primarily driven by a decrease in Firmicutes and Bacteroidetes, but accompanied by an increase in Actinobacteria, Proteobacteria, and other pathobionts. Interestingly, we observed that more complex communities from pig and cattle exhibited initial resilience, while a less diverse community from broilers displayed a rapid response to aerobic exposure. Our findings offer insights that can inform farm sanitation practices, as well as experimental design, sample collection, and processing protocols for microbiome studies across various animal species.

The spatial variation and drivers of soil δ13C in an alpine-gorge region on the eastern Qinghai-Tibetan Plateau

Soil stable carbon isotope (soil δ13C) can reflect soil carbon metabolic processes and record environmental and vegetation change information, so mapping the spatial distribution of soil δ13C (isoscapes of soil δ13C) can help us better understand the spatial variability of ecosystem carbon cycles. However, efficient approaches for obtaining the isoscapes of soil δ13C remain challenging, especially in mountainous areas with complex terrain. A total of 150 soil samples were collected and their soil δ13C was measured to investigate the spatial variation of soil δ13C in an alpine-gorge region on the eastern Qinghai-Tibetan Plateau which is characterized by complex terrain. Four prediction methods included ordinary kriging interpolation, multiple linear regression, random forest regression, and geographically weighted regression (GWR) were selected and compared to find the best prediction model for mapping the isoscapes of soil δ13C. The pathways of vegetation, topography, soil, and spatial factors influencing the spatial variability of soil δ13C were explored using variance partitioning analysis and structural equation model. The soil δ13C was significantly different among vegetation types, and ranged from −27.155‰ to −9.647‰. The spatial heterogeneity of soil δ13C showed moderate variation, and was dominated by spatial structural factors. The GWR model had higher prediction accuracy in the modeling soil δ13C in comparison to other models. Soil carbon to nitrogen ratio and normalized difference vegetation index were the main factors determining the spatial variability of soil δ13C, and other topographic and soil factors indirectly regulated the spatial distribution of soil δ13C by influencing these two factors. Our results provided a useful tool (GWR model) for mapping the isoscapes of soil δ13C and explored the factors controlling the spatial variability of soil δ13C in the alpine-gorge region on the eastern Qinghai-Tibetan Plateau, which are important for an in-depth understanding of soil carbon cycling in mountain ecosystems.

Acoustic impedance prediction based on extended seismic attributes using multilayer perceptron, random forest, and extra tree regressor algorithms

Acoustic impedance is the product of the density of a material and the speed at which an acoustic wave travels through it. Understanding this relationship is essential because low acoustic impedance values are closely associated with high porosity, facilitating the accumulation of more hydrocarbons. In this study, we estimate the acoustic impedance based on nine different inputs of seismic attributes in addition to depth and two-way travel time using three supervised machine learning models, namely extra tree regression (ETR), random forest regression, and a multilayer perceptron regression algorithm using the scikit-learn library. Our results show that the R2 of multilayer perceptron regression is 0.85, which is close to what has been reported in recent studies. However, the ETR method outperformed those reported in the literature in terms of the mean absolute error, mean squared error, and root-mean-squared error. The novelty of this study lies in achieving more accurate predictions of acoustic impedance for exploration.

Prediction of substantial closed-globe injuries in orbital wall fractures.

To determine risk factors for substantial closed-globe injuries in orbital fractures (SCGI) and to develop the best multivariate model for the prediction of SCGI. A retrospective study was performed on patients diagnosed with orbital fractures at Farabi Hospital between 2016 and 2022. Patients with a comprehensive ophthalmologic examination and orbital CT scan were included. Predictive signs or imaging findings for SCGI were identified by logistic regression (LR) analysis. Support vector machine (SVM), random forest regression (RFR), and extreme gradient boosting (XGBoost) were also trained using a fivefold cross-validation method. A total of 415 eyes from 403 patients were included. Factors associated with an increased risk of SCGI were reduced uncorrected visual acuity (UCVA), increased difference between UCVA of the traumatic eye from the contralateral eye, older age, male sex, grade of periorbital soft tissue trauma, trauma in the occupational setting, conjunctival hemorrhage, extraocular movement restriction, number of fractured walls, presence of medial wall fracture, size of fracture, intraorbital emphysema and retrobulbar hemorrhage. The area under the curve of the receiver operating characteristic for LR, SVM, RFR, and XGBoost for the prediction of SCGI was 57.2%, 68.8%, 63.7%, and 73.1%, respectively. Clinical and radiographic findings could be utilized to efficiently predict SCGI. XGBoost outperforms the logistic regression model in the prediction of SCGI and could be incorporated into clinical practice.

Does corporate governance moderate the impact of earnings management on capital structure of the listed corporations on Palestine and Amman Bourses

The purpose of this research is to investigate the moderating role of corporate governance on the relationship between earnings management and debt level in capital structure. The paper used a hypothesis-testing research approach to gather data from the annual reports of 13 industrial companies listed on Palestine Exchange and 25 Jordanian companies listed on Amman Stock Exchange from 2013 to 2020. Descriptive and inferential statistics were employed, along with correlation analysis to evaluate linear relationships between variables. The fixed and random effect regressions were utilized to develop the research model. In the case of Palestinian manufacturing firms, the results revealed that Earnings Management (EM) had a significant negative impact on debt level. According to the moderating role of Corporate Governance (CG), larger boards and the existence of female members on the board of directors causes an increase in the high-leverage impact of EM, whereas CEO duality mitigates the high-leverage impact. However, in the case of Jordanian manufacturing firms, EM showed an insignificant impact on debt level. Regarding the moderating role of CG, it was proved that the presence of female members on the board of directors increased the firm’s reliance on debt financing as a result of EM practices, while institutional investors mitigate the effect of EM on debt financing, leading to a decrease in reliance on debt. The findings of this research are suitable for the regulators while formulating policies on the Corporate Governance and the Impact of Earnings Management on Capital Structure. These findings have guided the policymakers that they should enhance their focus on Palestine and Jordan companies to test Corporate Governance Moderates the Impact of Earnings Management on Capital Structure. This study is also helpful for the new researcher while investigating this area in the future.

Melatonin promotes the recovery of apple plants after waterlogging by shaping the structure and function of the rhizosphere microbiome.

The dynamics of the physiological adaptability of plants and the rhizosphere soil environment after waterlogging remain unclear. Here we investigated the mechanisms regulating plant condition and shaping of the rhizosphere microbiome in a pot experiment. In the experiment, we added melatonin to waterlogged plants, which promoted waterlogging relief. The treatment significantly enhanced photosynthesis and the antioxidant capacity of apple plants, and significantly promoted nitrogen (N) utilization efficiency by upregulating genes related to N transport and metabolism. Multiperiod soil microbiome analysis showed the dynamic effects of melatonin on the diversity of the microbial community during waterlogging recovery. Random forest and linear regression analyses were used to screen for potential beneficial bacteria (e.g., Azoarcus, Pseudomonas and Nocardioides) specifically regulated by melatonin and revealed a positive correlation with soil nutrient levels and plant growth. Furthermore, metagenomic analyses revealed the regulatory effects of melatonin on genes involved in N cycling in soil. Melatonin positively contributed to the accumulation of plant dry weight by upregulating the expression of nifD and nifK (N fixation). In summary, melatonin positively regulates physiological functions in plants and the structure and function of the microbial community; it promoted the recovery of apple plants after waterlogging stress.

Investigating and modeling motorcycle crash rates at urban unsignalized intersections in India

Objective The present study focuses on understanding the behavior of motorized 2-wheeler (MTW) riders at urban unsignalized intersections in India. In the Indian context, over 60% of road crash fatalities are attributed to vulnerable road users, with MTWs serving as the predominant contributors, accounting for 44% of total fatalities. Notably, unsignalized intersections have emerged as critical sites for accidents involving vulnerable road users. Methods Postencroachment time is used to assess traffic conflicts of MTW users. Furthermore, the study employs the exceedance property of extreme value theory to calculate crash probabilities. Tobit and grouped random parameters Tobit regression models are developed to model crash probabilities, incorporating variables such as traffic volume, traffic composition, gap acceptance time, intersection characteristics, and intersection conflict area at 4 urban unsignalized intersections in Surat, India. Results MTW riders have the lowest gap acceptance time among vehicles in the traffic stream. Cars and other heavy vehicles readily accept gaps when MTWs are in the conflicting stream at unsignalized intersections, which increases traffic conflicts. MTWs have the highest crash rates in the traffic stream. Among the developed models, the grouped random parameters Tobit regression captures the spatial unobserved heterogeneity of the study sites and outperforms the simple Tobit regression model. The results also indicate that MTW riders are exposed to a higher risk of crashes while turning at unsignalized intersections. The presence of a central traffic island has varied implications; it raises crash rates at 3-legged intersections but lowers them at 4-legged intersections for 2-wheelers. Conclusion The study concludes that MTW crash rates are influenced by traffic and intersectional factors. Increased gap acceptance time correlates with lower crash rates. Countermeasure selections require detailed investigations, because it was observed that the presence of central traffic islands has varied effects on crash rates at 3-legged and 4-legged unsignalized intersections.

County-level intensity of carbon emissions from crop farming in China during 2000–2019

Agriculture is an important contributor to global carbon emissions. With the implementation of the Sustainable Development Goals of the United Nations and China’s carbon neutral strategy, accurate estimation of carbon emissions from crop farming is essential to reduce agricultural carbon emissions and promote sustainable food production systems in China. However, previous long-term time series estimates in China have mainly focused on the national and provincial levels, which are insufficient to characterize regional heterogeneity. Here, we selected the county-level administrative district as the basic geographical unit and then generated a county-level dataset on the intensity of carbon emissions from crop farming in China during 2000–2019, using random forest regression with multi-source data. This dataset can be used to delineate spatio-temporal changes in carbon emissions from crop farming in China, providing an important basis for decision makers and researchers to design agricultural carbon reduction strategies in China.

Mapping the Continuous Cover of Invasive Noxious Weed Species Using Sentinel-2 Imagery and a Novel Convolutional Neural Regression Network

Invasive noxious weed species (INWS) are typical poisonous plants and forbs that are considered an increasing threat to the native alpine grassland ecosystems in the Qinghai–Tibetan Plateau (QTP). Accurate knowledge of the continuous cover of INWS across complex alpine grassland ecosystems over a large scale is required for their control and management. However, the cooccurrence of INWS and native grass species results in highly heterogeneous grass communities and generates mixed pixels detected by remote sensors, which causes uncertainty in classification. The continuous coverage of INWS at the pixel level has not yet been achieved. In this study, objective 1 was to test the capability of Senginel-2 imagery at estimating continuous INWS cover across complex alpine grasslands over a large scale and objective 2 was to assess the performance of the state-of-the-art convolutional neural network-based regression (CNNR) model in estimating continuous INWS cover. Therefore, a novel CNNR model and a random forest regression (RFR) model were evaluated for estimating INWS continuous cover using Sentinel-2 imagery. INWS continuous cover was estimated directly from Sentinel-2 imagery with an R2 ranging from 0.88 to 0.93 using the CNNR model. The RFR model combined with multiple features had a comparable accuracy, which was slightly lower than that of the CNNR model, with an R2 of approximately 0.85. Twelve green band-, red-edge band-, and near-infrared band-related features had important contributions to the RFR model. Our results demonstrate that the CNNR model performs well when estimating INWS continuous cover directly from Sentinel-2 imagery, and the RFR model combined with multiple features derived from the Sentinel-2 imager can also be used for INWS continuous cover mapping. Sentinel-2 imagery is suitable for mapping continuous INWS cover across complex alpine grasslands over a large scale. Our research provides information for the advanced mapping of the continuous cover of invasive species across complex grassland ecosystems or, more widely, terrestrial ecosystems over large spatial areas using remote sensors such as Sentinel-2.

The cortical neurophysiological signature of amyotrophic lateral sclerosis.

The progressive loss of motor function characteristic of amyotrophic lateral sclerosis is associated with widespread cortical pathology extending beyond primary motor regions. Increasing muscle weakness reflects a dynamic, variably compensated brain network disorder. In the quest for biomarkers to accelerate therapeutic assessment, the high temporal resolution of magnetoencephalography is uniquely able to non-invasively capture micro-magnetic fields generated by neuronal activity across the entire cortex simultaneously. This study examined task-free magnetoencephalography to characterize the cortical oscillatory signature of amyotrophic lateral sclerosis for having potential as a pharmacodynamic biomarker. Eight to ten minutes of magnetoencephalography in the task-free, eyes-open state was recorded in amyotrophic lateral sclerosis (n = 36) and healthy age-matched controls (n = 51), followed by a structural MRI scan for co-registration. Extracted magnetoencephalography metrics from the delta, theta, alpha, beta, low-gamma, high-gamma frequency bands included oscillatory power (regional activity), 1/f exponent (complexity) and amplitude envelope correlation (connectivity). Groups were compared using a permutation-based general linear model with correction for multiple comparisons and confounders. To test whether the extracted metrics could predict disease severity, a random forest regression model was trained and evaluated using nested leave-one-out cross-validation. Amyotrophic lateral sclerosis was characterized by reduced sensorimotor beta band and increased high-gamma band power. Within the premotor cortex, increased disability was associated with a reduced 1/f exponent. Increased disability was more widely associated with increased global connectivity in the delta, theta and high-gamma bands. Intra-hemispherically, increased disability scores were particularly associated with increases in temporal connectivity and inter-hemispherically with increases in frontal and occipital connectivity. The random forest model achieved a coefficient of determination (R2) of 0.24. The combined reduction in cortical sensorimotor beta and rise in gamma power is compatible with the established hypothesis of loss of inhibitory, GABAergic interneuronal circuits in pathogenesis. A lower 1/f exponent potentially reflects a more excitable cortex and a pathology unique to amyotrophic lateral sclerosis when considered with the findings published in other neurodegenerative disorders. Power and complexity changes corroborate with the results from paired-pulse transcranial magnetic stimulation. Increased magnetoencephalography connectivity in worsening disability is thought to represent compensatory responses to a failing motor system. Restoration of cortical beta and gamma band power has significant potential to be tested in an experimental medicine setting. Magnetoencephalography-based measures have potential as sensitive outcome measures of therapeutic benefit in drug trials and may have a wider diagnostic value with further study, including as predictive markers in asymptomatic carriers of disease-causing genetic variants.