Random Forest Machine Learning Approach Research Articles

High hypoxia status in pancreatic cancer is associated with multiple hallmarks of an immunosuppressive tumor microenvironment.

Pancreatic ductal adenocarcinoma (PDAC), the most common form of pancreatic cancer, is a particularly lethal disease that is often diagnosed late and is refractory to most forms of treatment. Tumour hypoxia is a key hallmark of PDAC and is purported to contribute to multiple facets of disease progression such as treatment resistance, increased invasiveness, metabolic reprogramming, and immunosuppression. We used the Buffa gene signature as a hypoxia score to profile transcriptomics datasets from PDAC cases. We performed cell-type deconvolution and gene expression profiling approaches to compare the immunological phenotypes of cases with low and high hypoxia scores. We further supported our findings by qPCR analyses in PDAC cell lines cultured in hypoxic conditions. First, we demonstrated that this hypoxia score is associated with increased tumour grade and reduced survival suggesting that this score is correlated to disease progression. Subsequently, we compared the immune phenotypes of cases with high versus low hypoxia score expression (HypoxiaHI vs. HypoxiaLOW) to show that high hypoxia is associated with reduced levels of T cells, NK cells and dendritic cells (DC), including the crucial cDC1 subset. Concomitantly, immune-related gene expression profiling revealed that compared to HypoxiaLOW tumours, mRNA levels for multiple immunosuppressive molecules were notably elevated in HypoxiaHI cases. Using a Random Forest machine learning approach for variable selection, we identified LGALS3 (Galectin-3) as the top gene associated with high hypoxia status and confirmed its expression in hypoxic PDAC cell lines. In summary, we demonstrated novel associations between hypoxia and multiple immunosuppressive mediators in PDAC, highlighting avenues for improving PDAC immunotherapy by targeting these immune molecules in combination with hypoxia-targeted drugs.

Environmental controls of winter soil carbon dioxide fluxes in boreal and tundra environments

Abstract. The carbon cycle in Arctic–boreal regions (ABRs) is an important component of the planetary carbon balance, with growing concerns about the consequences of ABR warming for the global climate system. The greatest uncertainty in annual carbon dioxide (CO2) budgets exists during winter, primarily due to challenges with data availability and limited spatial coverage in measurements. The goal of this study was to determine the main environmental controls of winter CO2 fluxes in ABRs over a latitudinal gradient (45∘ to 69∘ N) featuring four different ecosystem types: closed-crown coniferous boreal forest, open-crown coniferous boreal forest, erect-shrub tundra, and prostrate-shrub tundra. CO2 fluxes calculated using a snowpack diffusion gradient method (n=560) ranged from 0 to 1.05 g C m2 d−1. To assess the dominant environmental controls governing CO2 fluxes, a random forest machine learning approach was used. We identified soil temperature as the main control of winter CO2 fluxes with 68 % of relative model importance, except when soil liquid water occurred during 0 ∘C curtain conditions (i.e., Tsoil≈0 ∘C and liquid water coexist with ice in soil pores). Under zero-curtain conditions, liquid water content became the main control of CO2 fluxes with 87 % of relative model importance. We observed exponential regressions between CO2 fluxes and soil temperature in fully frozen soils (RMSE=0.024 gCm-2d-1; 70.3 % of mean FCO2) and soils around the freezing point (RMSE=0.286 gCm-2d-1; 112.4 % of mean FCO2). FCO2 increases more rapidly with Tsoil around the freezing point than at Tsoil<5 ∘C. In zero-curtain conditions, the strongest regression was found with soil liquid water content (RMSE=0.137 gCm-2d-1; 49.1 % of mean FCO2). This study shows the role of several variables in the spatio-temporal variability in CO2 fluxes in ABRs during winter and highlights that the complex vegetation–snow–soil interactions in northern environments must be considered when studying what drives the spatial variability in soil carbon emissions during winter.

EduChat: An AI-Based Chatbot for University-Related Information Using a Hybrid Approach

The digital transformation has created an environment that fosters the development of effective chatbots. Through the fusion of artificial intelligence and data, these chatbots have the capability to provide automated services, optimize customer experiences, and reduce workloads for employees. These chatbots can offer 24/7 support, answer questions, perform transactions, and provide rapid information, contributing significantly to the sustainable development processes of businesses and organizations. ChatGPT has already been applied in various fields. However, to ensure that there is a chatbot providing accurate and useful information in a narrow domain, it is necessary to build, train, and fine-tune the model based on specific data. In this paper, we introduce EduChat, a chatbot system for university-related questions. EduChat is an effective artificial intelligence application designed by combining rule-based methods, an innovative improved random forest machine learning approach, and ChatGPT to automatically answer common questions related to universities, academic programs, admission procedures, student life, and other related topics. This chatbot system helps provide quick and easy information to users, thereby reducing the time spent searching for information directly from source documents or contacting support staff. The experiments have yielded positive results.

Analysis of the future potential impact of environmental and climate changes on wildfire spread in Ghana's ecological zones using a Random Forest (RF) machine learning approach

Climate change is increasing the hazards and catastrophes in many parts of the world, without sparing the natural zones, which are likewise growing more vulnerable in the face of human pressure. This study looked at how climate change affects wildfire spread via prediction in the Guinean savannah (GSZ) and the forest-savannah mosaic (FSZ) in Ghana. Random forest regression was employed to attain this goal. As a result, the CCLM4-8-17 model outputs were employed and analyzed under two Representative Concentration Pathway (RCP4.5 and RCP8.5), since they better forecast the climate of the biological zones studied with less error (R2, RMSE, Bias, Spearman Correlation). As a result, there is a decrease in rainfall over the simulated period (2022–2100) in both zones (FSZ, GSZ), considering both scenarios (RCP4.5; RCP8.5), and an increase in temperature in FSZ (+0.08 °C for RCP4.5 and 0.1 °C for RCP8.5) and GZS (+0.04 °C for RCP4 and +0.09 °C for RCP8.5). Under RCP4 and RCP8 scenarios, the average number of active fires (HS) on their part shows that the average near future (2022–2060) will have more areas favourable to fire activities (active points) in both ecological zones: RCP4_GSZ_HS (316 n), RCP4_FSZ_HS (252 n), RCP8_GSZ_HS (333 n), RCP8_FSZ_HS (285 n), followed by the average far future (2061–2100) The average burnt area (BA) under RCP4.5 and RCP8.4 that average near future (2022–2060) will also contain a more burnt area in both ecological zones: RCP4_GSZ_BA (25290.96 ha), RCP4_FSZ_BA (20758.51 ha), RCP8_GSZ_BA (25766.66 ha), RCP8_FSZ_BA (20699.91 ha) followed by average for far future (2061–2100): RCP4_GSZ_BA (14849.20 ha), RCP4_FSZ_BA (11782.11 ha), RCP8_GSZ_BA (19,299.07 ha), RCP8_FSZ_BA (1072.01 ha). Thus, under the RCP4.5 and RCP8.5 scenarios, tmax_RP4, SM, and ETA contribute more to fire activity and spread in the GSZ. However, in the FSZ, RH, tmax_RP4, and SM contribute more to fire activity and spread in the RCP4.5 and RCP8.5 scenarios, with varying amounts. Because of the above, decision-makers and academics must take tangible steps to develop novel techniques to minimise the future impacts of fires.

Estimation of time-variable friction parameters using machine learning

SUMMARY The laboratory-derived rate- and state-dependent friction (RSF) law governs rock friction. Although a number of studies have investigated the RSF friction parameters, they are not fully understood yet within a physical framework. In this study, we estimated the variation of RSF parameters during stick-slip cycles, in order to have insights into the temporal variation of fault conditions during slipping, which may help understand the relation between the change in friction parameters and the generation of gouge particles. To get a more refined understanding of the evolution of RSF parameters, we estimated these parameters for each of the hundreds of stick-slip events that occurred on laboratory faults during an experiment. We used experiment data for which the gouge particles were removed from the laboratory faults at the beginning of each experiment; this procedure made possible to evaluate the influence of the gouge layer evolution on the variation of the RSF parameters. Since the amount of data was very large, we adopted a random forest (RF) machine learning approach for data analysis. The RF model was trained on simulated friction data and then applied to the experiment stick-slip event data to estimate the RSF parameters. To generate simulated friction data of stick-slip events, a one-degree-of-freedom spring-slider model governed by the RSF law was assumed. From plots of friction change as a function of displacement, some representative features were extracted to account for the RSF parameters and were used as input to the RF algorithm. Using the RF approach, we captured the variation of the RSF parameters a, $b - a$ and ${D}_{\mathrm{c}}\ $defined in the RSF law. The results show that during a first transient phase, the parameter a becomes smaller, while parameters $b - a$ and ${D}_{\mathrm{c}}$ become larger, as the gouge layer becomes thicker. The variation of the RSF parameters becomes less pronounced during the following steady-state phase. These results suggest that the variation of RSF friction parameters may be related to the evolution of the gouge layer.

Predicting the performance and emissions of an HCCI-DI engine powered by waste cooking oil biodiesel with Al2O3 and FeCl3 nano additives and gasoline injection – A random forest machine learning approach

This study presents a novel method for predicting the performance and emissions of a Homogeneous Charge Compression Ignition-Direct Injection (HCCI-DI) engine fuelled by waste cooking oil biodiesel (WCOB) blended with Aluminum oxide (Al2O3) and Ferric chloride (FeCl3) nano additives and premixed with gasoline. The test fuels considered were pure diesel, WCOB, B50 (a 50–50 blend of diesel and WCOB), and the nano-additives at concentrations of 50 ppm and 100 ppm. All experiments were performed on a 4.4 kW HCCI-DI engine operating at 1500 rpm. The results revealed that, utilization of WCOB showed a substantial reduction in emissions. Hydrocarbon (HC), carbon monoxide (CO) and smoke emissions decreased by 54.17 %, 50 %, and 22.69 %. Nevertheless, oxides of nitrogen (NOx) emissions increased by 18.32 %. When introducing gasoline (20 %) as a premix in HCCI-DI engines, a favourable shift in emission and efficiency metrics was observed. The brake thermal efficiency (BTE) increased 4.23 %. Moreover, NOx and smoke emissions decreased by 4.3 % and 39.21 %. Furthermore, compared to conventional diesel-fueled combustion, the integration of the nano additives manifested promising results. After introducing Al2O3 into neat fuel, The BTE improved by 11.27 % for direct injection (DI) combustion and 18.31 % for HCCI-DI combustion. Additionally, there was a marked decrease in exhaust emissions. FeCl3 nano additive into the test fuel significantly reduced HC, CO, and smoke emissions. Furthermore, the random forest machine learning approach demonstrated an extensive accuracy in forecasting both engine performance and emissions for the HCCI-DI engine. The innovative combination of cutting-edge machine learning techniques and combustion technology used. This model to understand the complicated correlations between input parameters and engine outputs and account for the system's intrinsic non-linearities and interactions. This dramatically improves standard prediction approaches, often assuming linear correlations or disregarding variable interdependencies.

Climate conditions are primary predictors of the regional‐scale spatial diversity patterns of ectomycorrhizal fungi

AbstractAimSpatial models are valuable for revealing biodiversity patterns but are less commonly applied to soil microbes than to aboveground macroorganisms. Ectomycorrhizal (EM) fungi are symbiotic microbes with high taxonomic and functional diversity that are associated with forest trees. We aimed to predict regional‐scale spatial patterns of EM fungal richness and community composition.LocationForests and subalpine ecosystems in Japan, from Hokkaido to Okinawa.TaxonEM fungi (Asco‐ and Basidiomycetes).MethodsWe used EM fungal DNA sequence data from 1507 soil cores at 39 sites covering a wide range of environmental conditions. The random forest machine learning approach was applied to determine the relative importance of environmental variables (i.e. climate, soil and ecosystem productivity) and to make spatial predictions. The spatial patterns of EM fungal richness and community composition were mapped at 1‐km2 grid resolution.ResultsTemperature generally had a strong influence on EM fungal richness and community composition dissimilarity. Our regional spatial analysis revealed that (1) EM fungal richness was higher in northeastern and montane regions than in southwestern regions and low‐elevation plains, (2) different EM fungal lineages exhibited contrasting spatial diversity patterns and (3) community composition dissimilarity shifted sharply from high to low elevations, and gradually from northeastern to southwestern regions, mainly in relation to climate gradients. Areas with low applicability for spatial modelling were identified based on multidimensional environmental spaces, which will help to prioritize data collection for future research.Main ConclusionsOur study provides a baseline of the potential spatial patterns of EM fungal communities, which were explained primarily by climate variables and secondarily by soil factors and ecosystem productivity. The predicted spatial patterns may be valuable for identifying diversity hotspots and advancing the assessment of climate change impacts on ecologically important root‐associated fungi.

An Innovative Approach for Predicting Software Defects by Handling Class Imbalance Problem

From last decade unbalanced data has gained attention as a major challenge for enhancing software quality and reliability. Due to evolution in advanced software development tools and processes, today’s developed software product is much larger and complicated in nature. The software business faces a major issue in maintaining software performance and efficiency as well as cost of handling software issues after deployment of software product. The effectiveness of defect prediction model has been hampered by unbalanced data in terms of data analysis, biased result, model accuracy and decision making. Predicting defects before they affect your software product is one way to cut costs required to maintain software quality. In this study we are proposing model using two level approach for class imbalance problem which will enhance accuracy of prediction model. In the first level, model will balance predictive class at data level by applying sampling method. Second level we will use Random Forest machine learning approach which will create strong classifier for software defect. Hence, we can enhance software defect prediction model accuracy by handling class imbalance issue at data and algorithm level.

Random Forest Modeling of Acute Toxicity in Anal Cancer: Effects of Peritoneal Cavity Contouring Approaches on Model Performance

Our purpose was to analyze the effect on gastrointestinal (GI) toxicity models when their dose-volume metrics predictors are derived from segmentations of the peritoneal cavity after different contouring approaches. A random forest machine learning approach was used to predict acute grade ≥3 GI toxicity from dose-volume metrics and clinicopathologic factors for 246 patients (toxicity incidence=9.5%) treated with definitive chemoradiation for squamous cell carcinoma of the anus. Three types of random forest models were constructed based on different bowel bag segmentation approaches: (1) physician-delineated after Radiation Therapy Oncology Group (RTOG) guidelines, (2) autosegmented by a deep learning model (nnU-Net) following RTOG guidelines, and (3) autosegmented but spanning the entire bowel space. Each model type was evaluated using repeated cross-validation (100 iterations; 50%/50% training/test split). The performance of the models was assessed using area under the precision-recall curve (AUPRC) and the receiver operating characteristic curve (AUROCC), as well as optimal F1 score. When following RTOG guidelines, the models based on the nnU-Net auto segmentations (mean values: AUROCC, 0.71 ± 0.07; AUPRC, 0.42 ± 0.09; F1 score, 0.46 ± 0.08) significantly outperformed (P < .001) those based on the physician-delineated contours (mean values: AUROCC, 0.67 ± 0.07; AUPRC, 0.34 ± 0.08; F1 score, 0.36 ± 0.07). When spanning the entire bowel space, the performance of the autosegmentation models improved considerably (mean values: AUROCC, 0.87 ± 0.05; AUPRC, 0.70 ± 0.09; F1 score, 0.68 ± 0.09). Random forest models were superior at predicting acute grade ≥3 GI toxicity when based on RTOG-defined bowel bag autosegmentations rather than physician-delineated contours. Models based on autosegmentations spanning the entire bowel space show further considerable improvement in model performance. The results of this study should be further validated using an external data set.

Performance enhancement of smart grid with demand side management program contemplating the effect of uncertainty of renewable energy sources

ABSTRACT In a day ahead electricity market, all candidates of the electricity market, i.e. electricity users, aggregator, and grid operator urge to grow individual profit, but it is quite challenging to assure profit for all the candidates at a time. In this work, a multi-objective problem is formulated by combining the concept of demand side management (DSM) and Dynamic Economic Emission Dispatch (DEED). The multi-objective DSM – DEED problem is optimized by class topper optimization algorithm. In addition, an energy management algorithm (EMA) is proposed for optimal power utilization from various energy sources and to match the load demand with generated energy in presence of uncertainties of RESs. To get an accurate model, a random forest regression-based machine learning approach is considered in this paper to predict load demand, wind, and solar power on an hourly basis for a span of 24 hours. The objective here is to optimally schedule load consumption and power generation patterns simultaneously for a day to improve load factor, minimize operational cost, and maximize the profit of all the candidates of the electricity market simultaneously. The simulation findings highlight the effects of the proposed EMA and modified DSM program on the smart grid’s economy and performance.

Determining drivers of phytoplankton carbon to chlorophyll ratio at Atlantic Basin scale

We demonstrate the ability of flow cytometry to determine species specific cellular carbon and chlorophyll content in vivo by using laboratory cultures of phytoplankton encompassing a wide range of cell sizes. When applied to the large Atlantic Meridional Transect flow cytometry dataset, we reveal patterns in the species-specific phytoplankton carbon (C), chlorophyll (Chl) and C:Chl ratio. For Prochlorococcus the range of C:Chl is between 2 – 604; for Synechococcus 0.5 – 558. Using a Random Forest machine learning approach, we show that predictability of phytoplankton C:Chl, dominated by the prevalence of Prochlorococcus, is largely driven by silicate and nitrite concentration in the Atlantic Ocean.

A Random Forest Machine Learning Approach for the Identification and Quantification of Erosive Events

Predicting the occurrence of erosive rain events and quantifying the corresponding soil loss is extremely useful in all applications where assessing phenomenon impacts is required. These problems, addressed in the literature at different spatial and temporal scales and according to the most diverse approaches, are here addressed by implementing random forest (RF) machine learning models. For this purpose, we used the datasets built through many years of soil loss observations at the plot-scale experimental site SERLAB (central Italy). Based on 32 features describing rainfall characteristics, the RF classifier has achieved a global accuracy of 84.8% in recognizing erosive and non-erosive events, thus demonstrating slightly higher performances than previously used (non-machine learning) methodologies. A critical performance is the percentage of erosive events correctly recognized to the observed total (72.3%). However, since the most relevant erosive events are correctly identified, we found only a slight underestimation of the total rainfall erosivity (91%). The RF regression model for estimating the event soil loss, based on three event features (runoff coefficient, erosivity, and period of occurrence), demonstrates better performances (RMSE = 2.30 Mg ha−1) than traditional regression models (RMSE = 3.34 Mg ha−1).

Non-small cell lung cancer patients treated with Anti-PD1 immunotherapy show distinct microbial signatures and metabolic pathways according to progression-free survival and PD-L1 status

ABSTRACT Due to the high variance in response rates concerning anti-PD1 immunotherapy (IT), there is an unmet need to discover innovative biomarkers to predict immune checkpoint inhibitor (ICI)-efficacy. Our study included 62 Caucasian advanced-stage non-small cell lung cancer (NSCLC) patients treated with anti-PD1 ICI. Gut bacterial signatures were evaluated by metagenomic sequencing and correlated with progression-free survival (PFS), PD-L1 expression and other clinicopathological parameters. We confirmed the predictive role of PFS-related key bacteria with multivariate statistical models (Lasso- and Cox-regression) and validated on an additional patient cohort (n = 60). We find that alpha-diversity showed no significant difference in any comparison. However, there was a significant difference in beta-diversity between patients with long- (>6 months) vs. short (≤6 months) PFS and between chemotherapy (CHT)-treated vs. CHT-naive cases. Short PFS was associated with increased abundance of Firmicutes (F) and Actinobacteria phyla, whereas elevated abundance of Euryarchaeota was specific for low PD-L1 expression. F/Bacteroides (F/B) ratio was significantly increased in patients with short PFS. Multivariate analysis revealed an association between Alistipes shahii, Alistipes finegoldii, Barnesiella visceriola, and long PFS. In contrast, Streptococcus salivarius, Streptococcus vestibularis, and Bifidobacterium breve were associated with short PFS. Using Random Forest machine learning approach, we find that taxonomic profiles performed superiorly in predicting PFS (AUC = 0.74), while metabolic pathways including Amino Acid Synthesis and Fermentation were better predictors of PD-L1 expression (AUC = 0.87). We conclude that specific metagenomic features of the gut microbiome, including bacterial taxonomy and metabolic pathways might be suggestive of ICI efficacy and PD-L1 expression in NSCLC patients.

Random Forest Modeling of Soil Properties in Saline Semi-Arid Areas

The problem of salinization/spreading of saline soils is becoming more urgent in many regions of the world, especially in context of climate change. The monitoring of salt-affected soils’ properties is a necessary procedure in land management and irrigation planning and is aimed to obtain high crop harvest and reduce degradation processes. In this work, a machine learning method was applied for modeling of the spatial distribution of topsoil (0–20 cm) properties—in particular: soil organic carbon (SOC), pH, and salt content (dry residue). A random forest (RF) machine learning approach was used in combination with environmental variables to predict soil properties in a semi-arid area (Trans-Ural steppe zone). Soil, salinity, and texture maps; topography attributes; and remote sensing data (RSD) were used as predictors. The coefficient of determination (R2) and the root mean square error (RMSE) were used to estimate the performance of the RF model. The cross-validation result showed that the RF model achieved an R2 of 0.59 and an RMSE of 0.68 for SOM; 0.36 and 0.65, respectively, for soil pH; and 0.78 and 1.21, respectively for dry residue prediction. The SOC content ranged from 0.8 to 2.8%, with an average value of 1.9%; soil pH ranged from 5.9 to 8.4, with an average of 7.2; dry residue varied greatly from 0.04 to 16.8%, with an average value of 1.3%. A variable importance analysis indicated that remote sensing variables (salinity indices and NDVI) were dominant in the spatial prediction of soil parameters. The importance of RSD for evaluating saline soils and their properties is explained by their absorption characteristics/reflectivity in the visible and near-infrared spectra. Solonchak soils are distinguished by a salt crust on the land surface and, as a result, reduced SOC contents and vegetation biomass. However, the change in saline and non-saline soils over a short distance with mosaic structure of soil cover requires high-resolution RSD or aerial images obtained from unmanned aerial vehicle/drones for successful digital mapping of soil parameters. The presented results provide an effective method to estimate soil properties in saline landscapes for further land management/reclamation planning of degraded soils in arid and semi-arid regions.

Econometrics and Machine Learning Approach on Correlation in Stock Return between US Firms and Chinese Suppliers

This study investigates machine learning on influential factors on the correlation of the stock return movements between US firms and their Chinese suppliers, given that the overall correlation has already been proven in the previous study. The present investigation was conducted by performing econometrical analysis and applying a variety of regression models to US firms' stock returns (independent variable) and their Chinese suppliers' stock returns (dependent variable) with various factors involved. From the results, it was evident that industry differences are a factor that caused variations in the degree of stock return correlations. Furthermore, firm size and stock trading volume yielded positive impacts on the significance of the correlation. Subsequently, predicated on said findings, a prediction model was generated using the Random Forest machine learning approach. Using US customer firms' monthly stock return data, as well as the three aforementioned factors, the monthly stock return value of their Chinese supplier firms can be predicted.

359 Utilization of machine learning approaches on multimodal and ambulatory data to predict individualized symptom course in adults with obsessive-compulsive disorder.

OBJECTIVES/GOALS: This study will collect multimodal and longitudinal data in adults with obsessive-compulsive disorder and healthy controls. A mixed effects random forest machine learning approach will be taken to develop a model that can predict individualized longitudinal OCD symptom burden. METHODS/STUDY POPULATION: Baseline resting state functional MRI (rsfMRI) and measures of symptom burden will be collected in adults with OCD and healthy controls. Longitudinal measures of behavior and physiology–such as heart rate, activity, and sleep metrics - will be collected using Fitbit Charge 5 tracker. Daily assessments of symptom burden and functional status will be collected through a smartphone app. Individuals with OCD will start pharmacotherapy during the study period and all participants will be followed for a total of 10 weeks. Repeat rsfMRI imaging will occur at study conclusion. Data will be analyzed using a mixed effects random forest machine learning algorithm with assessment of model performance. RESULTS/ANTICIPATED RESULTS: Prior studies of symptom severity in psychiatric illness and affect in non-clinical populations have found longitudinal features - such as lexical and acoustic measures, participant context, heart rate, and sleep metrics–that were predictive of these states over time. It is anticipated that the present study will extend these results to individuals with OCD and identify physiologic and behavioral features that track personalized symptom burden longitudinally in this patient population. A model able to predict when symptoms are elevated could allow for provision of additional treatment or interventions targeted to times of high symptom burden. DISCUSSION/SIGNIFICANCE: This study will be the first to collect and analyze longitudinal measures of behavior, symptoms, and physiology in patients with OCD with a goal of predicting symptom burden. Identification of elevated symptom burden would allow for implementation of just-in-time treatment, during these periods.

Prediction and evaluation of energy and exergy efficiencies of a nanofluid-based photovoltaic-thermal system with a needle finned serpentine channel using random forest machine learning approach

The Photovoltaic thermal (PVT) collector performance is numerically investigated considering the effect of using needle fins in the serpentine channel with Nanofluid (NF). The influence of increasing the nanoparticle concentration (φ) and Reynolds number (Re) on the energy and exergy features of the PVT device is examined. A comparison is made between the hydrothermal characteristics of the PVT with the finned and plain serpentine channels. The utilization of needle fins improves the thermal efficiency (ηth), electrical efficiency (ηel), and overall efficiency (ηel) by 8.56–10.22%, 0.13–0.24%, 5.12–5.67%, respectively, against the PVT with the plain serpentine channel. Moreover, thermal exergy efficiency (ξth), electrical exergy efficiency (ξel), and overall exergy efficiency (ξov) by 8.56–1.22%, 0.13–0.24%, and 2.61–2.79%, respectively, versus the PVT with the plain serpentine channel. Moreover, the Random Forest (RF) machine learning approach is used to develop a predictive model for ηth, ηel, ηel, ξth, ξel and ξov in terms of Re and φ. The outcomes of modeling proved that all the results were in an acceptable level of accuracy and the overall efficiency in both energy and exergy yielded superior precision in comparison with the other targets.

Mapping individual tree and plot-level biomass using airborne and mobile lidar in piñon-juniper woodlands

Piñon-juniper (PJ) woodlands are a widespread dryland ecosystem in the US containing an immense but poorly-constrained amount of aboveground biomass (AGB). Found at the dry end of the climatic range within which trees can persist, PJ faces an uncertain future in a changing climate, giving unique importance to mapping its AGB, past, present, and future. Lidar remote sensing offers great potential towards that end with research in a range of tree-dominant ecosystems demonstrating a strong capacity for mapping AGB. However, studies applying lidar to the task of mapping AGB in PJ are few. Given the unique structural characteristics of PJ trees, which tend to be short in stature (<10 m), possess multiple stems often obscured by low crown base heights, and irregularly-shaped canopies, there remains a high degree of uncertainty surrounding tree- and stand-level structural mapping in these woodlands. To resolve our limited understanding of how to best quantify AGB in PJ using lidar, we conducted a field-validated analysis comparing lidar platform (airborne laser scanner, ALS vs. mobile laser scanner, MLS) and analytical framework (area-based modeling vs. individual tree-based modeling). We used a random forest machine learning approach to predicting tree- and stand-level structure with leave-one-out cross-validation to assess model performance. In an area-based context, MLS only marginally outperformed ALS, with both able to explain approximately 80 % of variance in AGB. However, in an individual tree-based context, MLS significantly outperforms ALS at several tasks, including: (1) delineating tree crowns (MLS delineated 100 % of trees; ALS delineated 69 %); (2) directly characterizing tree structural parameters including height (R2ALS = 0.52 vs. R2MLS = 0.74) and crown area (R2ALS = 0.26 vs. R2MLS = 0.68); and (3) modeling AGB (R2ALS = 0.38 vs. R2MLS = 0.62). We attribute this difference in performance to the vastly greater structural detail contained within the MLS point cloud data as compared to ALS, with the former possessing an average of approximately 30,000 pts/m2 and the latter 14 pts/m2. Based on our results, we make the following recommendation: if individual tree structure is needed, MLS is the far superior option; however, given the wider availability, ALS data are a suitable substitute when mapping PJ AGB, particularly under an area-based modeling analytical framework. This study represents the first time MLS data have been applied to tree structure mapping in PJ, and provides strong quantitative evidence towards best structural and AGB mapping practices in this unique, widespread, and important ecosystem. It serves as a solid foundation upon which future studies aiming to map AGB in PJ and other similar dryland woodland ecosystems can be built.

Geographic Variation and Risk Factor Association of Early Versus Late Onset Colorectal Cancer

The proportion of patients diagnosed with colorectal cancer (CRC) at age < 50 (early-onset CRC, or EOCRC) has steadily increased over the past three decades relative to the proportion of patients diagnosed at age ≥ 50 (late-onset CRC, or LOCRC), despite the reduction in CRC incidence overall. An important gap in the literature is whether EOCRC shares the same community-level risk factors as LOCRC. Thus, we sought to (1) identify disparities in the incidence rates of EOCRC and LOCRC using geospatial analysis and (2) compare the importance of community-level risk factors (racial/ethnic, health status, behavioral, clinical care, physical environmental, and socioeconomic status risk factors) in the prediction of EOCRC and LOCRC incidence rates using a random forest machine learning approach. The incidence data came from the Surveillance, Epidemiology, and End Results program (years 2000-2019). The geospatial analysis revealed large geographic variations in EOCRC and LOCRC incidence rates. For example, some regions had relatively low LOCRC and high EOCRC rates (e.g., Georgia and eastern Texas) while others had relatively high LOCRC and low EOCRC rates (e.g., Iowa and New Jersey). The random forest analysis revealed that the importance of community-level risk factors most predictive of EOCRC versus LOCRC incidence rates differed meaningfully. For example, diabetes prevalence was the most important risk factor in predicting EOCRC incidence rate, but it was a less important risk factor of LOCRC incidence rate; physical inactivity was the most important risk factor in predicting LOCRC incidence rate, but it was the fourth most important predictor for EOCRC incidence rate. Thus, our community-level analysis demonstrates the geographic variation in EOCRC burden and the distinctive set of risk factors most predictive of EOCRC.

The retrieval of aerosol optical properties based on a random forest machine learning approach: Exploration of geostationary satellite images

Aerosol optical properties are among the most fundamental parameters in atmospheric environmental studies. Satellite aerosols retrievals that are based on deep learning or machine learning approach have been widely discussed in remote sensing studies, but the flexible random forest (RF) model has not received much attention in the retrieval of geostationary satellite, like Himawari-8. Thus, the Himawari-8 aerosol retrieval achieved by RF model requires further investigation and optimization. Based on the radiative transfer equation, this study proposed a RF model driven by a differential operator, which quantifies a simple linear relationship between aerosol optical depth (AOD) and top-of-atmosphere (TOA) reflectance enhancement. The spectral information of aerosols is achieved by independent TOA reflectance comparison between images rather than one result from multiple band synthesis. The method allows simple feature inputs and shows weak dependence on auxiliary data. It also achieves simultaneous retrievals over different surfaces and maintains mathematical correlation between spectral AODs and Angstrom Exponents (AE). The model performance was evaluated using a series of comprehensive temporal and spatial validation analyses. A sample-based tenfold cross-validation (10-CV) shows that the new method can simultaneously improve the estimation of aerosol properties, with considerably high correlation coefficients (R2) of 0.85 for AODs at the 0.50 μm wavelengths, a mean absolute error (MAE) of 0.08, a root mean square error (RMSE) of 0.13 and >70% of the samples fell within the AOD expected error (EE). The high accuracy of the spectral AOD retrievals also exhibits good performance on AE calculations, with at least 2/3 of the samples falling within the EE. The site based 10-CV also evaluates the spatial predictions on AODs at the 0.50 μm wavelength, with R2 of 0.67, MAE of 0.12 and RMSE of 0.18. It also has outperformed the Himawari operational aerosol products and appeared to be comparable to other popular machine learning models with better AE retrievals in some typical regions. Two typical regional pollution cases also highlight the advantages of the new aerosol monitoring approach. The 5 km resolution aerosol retrievals exhibit good spatial coverage and performance when describing the regional pollution levels and types. The proposed method improves the performance of RF in retrieving aerosol properties from geostationary satellites and also offers a new prospective for aerosol remote sensing using machine learning approaches.