The Texas A&M University System is a state university system in Texas and is one of the state's six independent university systems.The Texas A&M University System is one of the largest systems of higher education in the United States, with a budget of $6.3 billion. Through a statewide network of 11 universities and eight state agencies, and the RELLIS Campus, the Texas A&M System educates more than 153,000 students and makes more than 22 million additional educational contacts through service and outreach programs each year. System-wide, research and development expenditures exceeded $996 million in FY 2017 and helped drive the state's economy.The system's flagship institution is Texas A&M University in College Station. The letters "A&M", originally A.M.C. and short for "Agricultural and Mechanical College", are retained as a tribute to the university's former designation.
Accurate forecasting of energy prices is critical to effectively mitigate operational risks and make strategic bidding decisions in day-ahead (DA) electricity markets. However, it is highly challenging due to volatile characteristics, seasonality, rapid spikes, and other nonlinear factors of price signals. In the given context, deep learning (DL) has gained attention in recent years due to its high potential in nonlinear approximation, but each model has its strengths and limitations. Therefore, this paper proposes a hybrid DL approach for time-series DA energy price forecasting based on the Transformer and Bidirectional Long Short-Term Memory (BiLSTM) model that facilitates strategically combining various components to extract patterns and further improve the sequence processing task. The proposed model uses a transformer architecture to capture patterns, temporal dynamics, and BiLSTM networks to forecast energy price fluctuations. The proposed approach is validated with simulations based on price data from the New York Independent System Operator, and the results show that the proposed approach consistently outperforms state-of-the-art DL models, achieving the lowest MAE (2.7818 $/MWh), RMSE (6.4937 $/MWh), sMAPE (6.6060%), MAPE (6.3741%) and highest R$<^>{2}$ (0.9393). The effectiveness of the proposed approach was justified through various case studies from different perspectives.
Overshooting storms are convective systems with updrafts that penetrate through the tropopause into the overlying stratosphere. These storms can rapidly transport a wide variety of chemical species and aerosols from the boundary layer and free troposphere directly to the stratosphere. The central plains of the U.S. and the Sierra Madre Occidental of Mexico are two of the global hotspots for overshooting convection. While the existence of these storms has been known for several decades, the amount of tropospheric air, including water vapor, trace gases, and aerosols, transported across the tropopause is poorly understood, as is their impact on the dynamics, chemistry, and radiative balance of the stratosphere. Climate models suggest that as Earth’s climate continues to warm, overshooting convection over the U.S. may increase, potentially causing changes to stratospheric composition and transport. To address these scientific questions, the NASA ER-2 high-altitude research aircraft flew 31 missions during the summers of 2021 and 2022 to make observations of the outflow from overshooting storms in the stratosphere over North America and the eastern Pacific Ocean as part of the Dynamics and Chemistry of the Summer Stratosphere (DCOTSS) project. The ER-2 carried a payload of 12 instruments to measure meteorological parameters, water and its isotopologues, trace gases, and aerosol properties. Ozone, water vapor, and aerosol sondes were also launched on balloons during the field deployments. This paper describes the science goals of the DCOTSS project, the aircraft measurement strategy, the data produced by the project, and highlights of science results to date.
Plant growth is significantly impacted by the concentration of nutrients in the soil. Accurate and real-time measurement of nitrates and nitrites levels remains a significant challenge. Existing laboratory-based methods are expensive, time-consuming, and labor-intensive, highlighting the need for a rapid, on-site solution. This study proposes a rapid method for measuring nitrates and nitrite levels in water samples collected from tile drainage. We utilized Hach Nitrate and Nitrite test strips for image dataset collection as these test strips change color based on the concentration of nitrate and nitrite in the water samples. A purpose-built black box, equipped with an internal lighting arrangement for imaging test strips, was designed to collect images of the test strips. Unlike many existing smartphone-based colorimetric approaches, which are sensitive to ambient lighting variations and often rely on external calibration or offline analysis, the proposed system integrates a controlled illumination environment with real-time edge computation for robust on-site detection of nitrate and nitrite. An Nvidia Orin Nano module, connected with an IMX219 camera sensor, was used to capture images of the test strips. Image preprocessing was performed, followed by the implementation of a VGG16-based network for feature extraction. A dataset of approximately 3128 images spanning multiple nitrate and nitrite concentration levels was collected under controlled imaging conditions. Multiple machine learning models including logistic regression (LR), support vector machines (SVM), k-nearest neighbors (KNN), naïve Bayes (NB), and random forest (RF) were evaluated for classification. The nitrate detection using KNN achieved an accuracy of 99.96
Understanding the influence of recycling agents (RA) on different aged binders and their impact on subsequent aging mechanisms is vital for the effective recycling of aged binders and identifying threshold RA dosages. The present study aims to investigate the interaction effects of RA through an integrated framework by analysing chemical characteristics using Saturates, Aromatics, and Resins with Asphaltene determinator (SAR-AD) method and Fourier Transform Infrared (FTIR) spectroscopy, while corroborating these findings through microstructural changes captured using Atomic Force Microscopy (AFM). Recycled blends prepared with binders aged to three extents and varying RA dosages were tested in unaged and long-term aged conditions. Results indicate that RA increases lighter hydrocarbons, balances asphaltene-maltene polarity, and promotes non-covalent interactions, with the quantum of influences reducing as RA dosage and RAP binder age increase. These mechanisms contribute to softening and dispersion effects, with the dispersion persisting with subsequent aging, indicating that RA alters the aromatisation process. The findings reveal that beyond a threshold RA dosage, its primary effect is softening the binder, while its impact on functional groups and dispersion becomes marginal.
The classification of pores into their intrinsic depo-diagenetic or petrophysical morphotypes is a fundamental practice within carbonate petrography, providing linkage between pore-scale textures and their associated petrophysical signatures and/or paragenetic histories. Typically, pore classification is performed manually in a qualitative/semi-quantitative manner, which is hampered by inefficiency, subjectivity, and a lack of scalability. Though aimed at addressing the limitations of manual pore classification, efforts to automate petrographic pore-typing through artificial intelligence and computer vision techniques are limited by the inability of models to classify pores into genetic classes solely based upon simplistic size and shape features, which have been the focus of the existing literature. To address this nuanced classification problem, we present PoreViT: a Vision Transformer (ViT) model used to classify macropores observed in thin-sections into their respective Lucia classes (interparticle, touching vug, separate vug). The core novelty of PoreViT lies in its Feature Fusion block, which integrates ViT features, enhanced by a Global Token Addition layer, with spatial features extracted from a Convolutional Neural Network (CNN). Critically, our classifier leverages neighborhood information to provide the model with localized pore system topology, recognizing that pore types need to be identified not just by shape but also by their local spatial context. Trained and tested using 4115 labels obtained from 25 high-resolution thin-section scans, PoreViT provides an accurate, automated classification of carbonate macropores, achieving precision and recall values of 0.92 and 0.93 (macro-F1 0.92) corresponding to absolute improvements of +4.0% and +4.0%, and relative gains of +4.54% and +4.5%, respectively, over the best-performing CNN model (DenseNet121). The high throughput pore-textural classification capabilities demonstrated herein offer unprecedented opportunities in the integrated quantitative characterization of carbonates.
