Salt-induced diffusiophoresis is the migration of a charged nanoparticle in water, induced by an imposed directional gradient of salt concentration. This transport phenomenon has emerged as a valuable tool for particle manipulation inside porous materials and microfluidics. Micelles are a common example of nanoparticles with the crucial ability of hosting small guest molecules. Thus, micelle diffusiophoresis is important in the manipulation of small molecules. Diffusiophoresis depends on the intrinsic ability of micelles to randomly move (diffuse) in water. In this poster, we report experimental micelle diffusion coefficients for the surfactant hexadecylpyridinium chloride (CPC) in the presence of aqueous NaCl and KCl. The electrical double layer theory was successfully employed to explain the effect of surfactant and salt concentrations on the observed micelle diffusion coefficient. These data were then used to characterize salt-induced diffusiophoresis of charged micelles.

Influence of a NiO Hole Transport Layer on Charge Separation in FTO|WO₃|BiVO₄ Photoanodes for TEMPO-Mediated Oxidation

Favor Igwilo, Texas Christian University, Class of 2026
Laboratory of Dr. Benjamin Sherman, PhD;
Department of Chemistry and Biochemistry

Efficient hole transport is critical for driving oxidative transformations in photoelectrochemical systems. In this study, we investigate multilayer FTO|WO₃|BiVO₄|NiO photoanodes for application in TEMPO-mediated oxidation of benzyl alcohol to benzaldehyde, an important chemical reaction used in industrial processes. The stable radical 2,2,6,6-tetramethylpiperidin-1-oxyl (TEMPO) enables selective alcohol oxidation under mild conditions and represents a more sustainable alternative to conventional stoichiometric oxidants that generate hazardous waste. Enhancing interfacial charge transport is essential to improve the viability of this photoelectrosynthetic process.

We hypothesize that nickel oxide (NiO), a p-type semiconductor, can function as an effective hole transport layer due to its favorable valence band alignment, hole mobility, abundance, and low cost relative to traditional materials such as titanium dioxide (TiO₂). A liquid phase deposition protocol was developed to fabricate uniform NiO thin films on fluorine-doped tin oxide substrates, which were subsequently integrated into FTO|WO₃|BiVO₄ substrates. The resulting multilayer photoanodes were evaluated to determine whether NiO enhances charge separation and hole extraction under various conditions.

Electrochemical characterization was performed using cyclic voltammetry to probe redox behavior and assess catalytic onset potentials, chronoamperometry to quantify steady-state photocurrent and operational stability, and electrochemical impedance spectroscopy to evaluate interfacial charge transfer resistance. Measurements were conducted under both dark and illuminated conditions, with and without TEMPO, in Tetrabutylammonium hexafluorophosphate (TBAPF6)in acetonitrile (ACN) solution. We anticipate that incorporation of NiO will reduce interfacial charge transfer resistance, increase photocurrent density in the presence of TEMPO, and improve kinetic parameters associated with benzyl alcohol oxidation.
Photocurrent densities of FTO|WO₃|BiVO₄ and FTO|WO₃|BiVO₄|NiO photoanodes were directly compared to quantify the effect of the NiO interlayer. Additionally, heterogeneous electron transfer rate constants (k₀) were determined under TEMPO-containing conditions to assess how the multilayer structure influences interfacial electron transfer kinetics.

This work establishes a working protocol for NiO liquid phase deposition and clarifies the role of NiO in enhancing TEMPO-mediated photoelectrosynthetic oxidation. These findings can later inform the design of cost-effective photoelectrode architectures for sustainable organic reactions.

By combining the supportive structure of alginate hydrogels, the semiconductive nature of porous silicon (pSi) membranes, and the biodegradability of both of these materials, a unique, non-invasive biosensor can ideally be created for the chemical analysis of health-relevant analytes.
Hydrogels are water-infused, biodegradable polymer networks that are easily able to interface with human skin. Alginate polymer hydrogels are particularly useful due to being derived from brown algae, making them environmentally abundant and inexpensive. The polymer is modified with acrylamide segments to add stability and shelf-life to the hydrogel material. Ultimately, these characteristics make hydrogels ideal for supporting the pSi membranes while assimilating them to a variety of tissues.
Porous silicon (pSi) is a highly porous form of the widely used elemental semiconductor and is used to conduct and measure electrical signals throughout the hydrogel matrix. When established in a diode form, these membranes exhibit measurable current values as a function of voltage, which can be used to detect bioelectrical stimuli such as the concentration of physiologically relevant ionic species such as Na+, K+, and Ca2+.
Recent experiments focus on integrating pSi membranes in Acrylamide/alginate co-polymer hydrogels to test how variations in ion concentration affect the flow of current measured as a function of applied voltage. Porous silicon membranes ~110 μm thick and 79% porosity, are fabricated from the anodization of low resistivity (100) Si in methanolic HF at an applied bias of 100 mA/cm2 for 30 minutes. Membranes pieces ~2 mm by 2 mm are heated for one hour at 650°C. They are then affixed to Cu wire using Ag epoxy and annealed for 15 minutes at 95°C. The wires are then fashioned to form the membrane diodes and clear nail polish is used to coat the backs of the membranes, the Cu wire connection, and the wire itself to prevent current flow from the back of the membrane or bubble formation. The electrochemical cell is created by placing two pSi membranes parallel to each other ~2 mm apart, vertically, in a fixed electrolyte composition. The current is measured as function of applied voltage (typically from 0-5 V) for systems with different concentrations of NaCl in the nM to mM range. The NaCl solutions are injected directly into the hydrogel in between the two pSi membranes in 2 μL units.
This presentation will focus on the fabrication protocol, as well as results from experiments with varying NaCl concentrations. Previous experiments have determined linearity of the current and applied voltage function in the region of 0.25 mM to 1 mM concentration ranges of pure NaCl solution. Future experiments will seek to repeat these findings within the alginate hydrogel matrix.

Alzheimer’s Disease (AD) presents a significant personal and economic burden, yet therapeutic strategies targeting its progression have largely been unsuccessful. Key pathological features of AD include oxidative stress, dysregulation of metal ions, and the aggregation of amyloid-beta (Aβ) peptides into plaques. Previous work in the Green Lab has focused on the development of macrocyclic compounds capable of chelating transition metals such as copper and iron—both of which contribute to oxidative stress and Aβ plaque formation. These macrocycles also incorporate aromatic rings that mitigate oxidative damage by scavenging free radicals. However, while effective in addressing metal ion misregulation and oxidative stress, these compounds do not prevent Aβ aggregation. To address this limitation, we have incorporated the KLVFF peptide—known for its ability to bind Aβ and inhibit its aggregation—into our macrocyclic framework using solid-phase peptide synthesis. The resulting trifunctional molecule is designed to simultaneously chelate metal ions, reduce oxidative stress, and inhibit Aβ plaque formation. This multifunctional approach offers a promising therapeutic strategy for slowing or preventing the progression of AD into its more debilitating stages.

The WHO has declared antimicrobial resistance a top 10 global threat. New antimicrobials with novel modes of action are therefore desperately needed. One such mode of action would be to target the aromatic amino acid biosynthesis pathway. Several extremely potent inhibitors of Dehydroquinate Synthase have been previously synthesized. One of those, a vinylphosphonate compound, was selected as the lead compound for this study. In this project, the inhibitor was re-synthesized and several methods to prepare prodrugs have been investigated. The synthesis of prodrugs of other related compounds was also explored.

In this work, a single-layer tungsten oxide (WO₃) film on fluorine-doped tin oxide (FTO) coated glass was successfully prepared by the dip-coating method, followed by thermal treatment at 450°C. The structure and electrochemical properties of the WO₃ film were then determined via UV-Vis spectroscopy, IR absorption, surface profilometry, and XRD analysis. The result suggests that the films have consistent thickness and uniformity, with future investigations needed to explore how they interact with the addition of a nickel oxide layer and bismuth vanadate layer determined by electrochemical measurements such as cyclic voltammetry, chronoamperometry under light and dark conditions. WO₃ electrode can be used as the base layer to make FTO-WO₃-Bismuth Van(BiVO₄)-Nickel Oxide (NiO) electrode.
Future work will focus on developing multilayer photoelectrodes and further investigate the relationship between film structure, thickness, and photoelectrochemical performance while integrating WO₃ films with bismuth vanadate (BiVO₄) and nickel oxide (NiO).

Alzheimer’s Disease (AD) is a neurodegenerative terminal disease that affects 11% of Americans who are 65+ years old. The progression of AD has been associated with the dysregulation of reactive oxygen species (ROS) via multiple mechanisms, resulting in oxidative stress and neuronal damage. One of the focuses of the Green Lab at TCU is the development of PyN3 pyridinophanes that act as antioxidants to counter the effects caused by unregulated ROS. While most compounds synthesized within the lab both have antioxidant characteristics and activate the Nrf2 pathway, they face the issue of having poor permeability to the Blood Brain Barrier (BBB), making them unable to deliver the therapeutic effects to the diseased neurons. To counter this deficit, the series of molecules proposed herein aim to increase the lipophilicity of the base PyN3 molecules while maintaining or increasing their antioxidant potential. In pursuit of these aims, we aimed to utilize Suzuki-Miyara-like carbon-carbon bond formation to add aromatic, lipophilic, antioxidant moieties to the para position of the parent PyN3 molecule. Computational studies, including the BOILED-Egg plot, were used to identify these synthetic targets for probable BBB permeability with the goal of highlighting a new route in drug synthesis to increase the delivery of active compounds to target tissues past the BBB.

Macrocycles are promising drug design frameworks because their folding can enhance stability, solubility, and membrane permeability. Recently, triazine macrocycles derived from two monomers were reported. The cyclization is quantitative, but the role of chirality in macrocycle formation remains unclear. To address this issue, triazine macrocycles were synthesized from Fmoc-protected amino acids to test whether chiral sorting occurs. Chiral sorting refers to the tendency of amino acid precursors to selectively pair as homochiral species (D-D or L-L) or heterochiral species (D-L). Understanding this behavior can dictate macrocycle folding and stability. Preliminary results with valine and isoleucine suggest strong chiral sorting favoring homochiral species. In contrast, chiral sorting does not appear to occur alanine or isovaline, both of which follow the expected 1:2:1 distribution of DD, DL, and LL. These findings highlight stereochemical influences on macrocycle formation and provide insights for designing macrocycles with improved therapeutic potential.

Reactive Oxygen Species (ROS) are associated with a broad spectrum of diseases, ranging from bone loss to cancer. One strategy to combat ROS is to treat sources of such species in the body with materials capable of generating hydrogen and reacting with ROS to neutralize it. This project involves incorporating an H₂-generating material known as Calcium Disilicide (CaSi₂) into membranes of another H₂-generating material known as porous silicon for tandem antioxidant drug delivery. Porous silicon (pSi) is an important substrate in drug delivery as its nano-network of pores allows controlled loading of drugs. Our approach centers on the use of spark ablation to deposit CaSi₂ into the pSi. Both porous silicon and CaSi₂ are nontoxic and can be resorbed over time in vivo.

To prepare CaSi₂/pSi, a piece of pSi membrane is fixed to substrate with a small drop of nail polish, and CaSi₂ powder is added. A capillary tube is placed on the pSi and spark ablated with a high-voltage Tesla coil, causing Si atoms on the porous membrane to vaporize along with CaSi₂ and the mixture resettles upon cooling. Scanning Electron Microscopy (SEM) is used to characterize morphology, and in situ Energy Dispersive X-ray Spectroscopy (EDX) to determine the percentage of calcium in the sample. We use the criterion of highest CaSi₂ loading percentage to determine the conditions for most efficient addition of CaSi₂ into the membrane. We have successfully incorporated calcium disilicide into porous Si membranes; current experiments are attempting to measure the amount of hydrogen produced synergistically to improve the performance of porous silicon as a means to treat in situ ROS production.

Density Functional Theory (DFT) is a method for simulating molecules by approximating their electron densities, with various functionals available to model these systems. M11plus is one such functional, a range-separated hybrid meta functional that combines long-range non-local Hartree–Fock exchange with the non-local Rung 3.5 correlation, which has demonstrated effectiveness across a broad range of chemical databases. This work implements the oM11plus functional, a tweaked version of M11plus, into the PySCF open-source Python library.

This research aims to develop and characterize synthetic riboswitches for creatinine and trimethylamine N-oxide (TMAO), metabolic biomarkers for kidney and cardiovascular dysfunctions. Riboswitches are structured RNA elements located in the 5’-untranslated regions (UTRs) of bacterial mRNAs that regulate downstream gene expression through ligand-induced conformational changes with high affinity and selectivity. To select for the synthetic riboswitches specific to creatinine, the glycine riboswitch library was subjected to a dual genetic selection. In the positive selection, the riboswitches that bind to creatinine or any endogenous molecules will produce the CAT-UPP fusion protein, allowing the host cells to survive in the presence of chloramphenicol. The negative selection is carried out in media containing 5-fluorouracil (5-FU) in the absence of creatinine. Any riboswitches activated by endogenous ligands will die in the presence of 5-FU. The surviving cells should contain the riboswitches that are activated only by creatinine. After several repeated selection steps, including increased concentrations of chloramphenicol and 5-FU, no glycine riboswitch variants were identified to show chloramphenicol resistance in the presence of creatinine. We will continue the project with different riboswitch libraries. We identified a synthetic riboswitch to TMAO, a riboswitch that was derived from the genetic selection of the theophylline riboswitch library that clearly shows chloramphenicol resistance only in the presence of TMAO. We will further test this TMAO riboswitch by colorimetric or fluorescence assays using β-galactosidase and green fluorescence protein, respectively, in the presence of varying concentrations of TMAO.

Sustainable synthetic approaches to drug delivery carriers such as porous silicon are becoming increasingly important for biomedical applications such as drug delivery, where extreme electronic-grade purity is not required, even though silicon remains a critical material in electronics and energy technologies. This work develops a green, self-propagating high-temperature synthesis (SHS) approach to produce high-surface-area porous silicon using plant-derived silicon dioxide (SiO₂) as the precursor, magnesium (Mg) as the reductant, and sodium chloride (NaCl) as a thermal moderator. The exothermic magnesiothermic reaction is initiated using a controlled electrical input of less than (or equal to) 9V, enabling silicon formation while significantly reducing external energy requirements compared to conventional high-temperature silicon production methods.

In practice, Mg and SiO₂ reactants are exposed to a finite voltage for approximately 10–15 minutes to allow the SHS reaction to propagate. After synthesis, the crude product is purified by dissolving reaction byproducts in concentrated hydrochloric acid, leaving behind porous silicon. X-ray powder diffraction (XRD) is used to evaluate crystallinity and phase composition. While XRD analysis confirms the formation of silicon, persistent crystalline silica peaks indicate incomplete reduction and phase coexistence that currently limits effective separation. Ongoing work focuses on optimizing reaction conditions and refining reaction kinetics to improve phase selectivity and identify optimal synthesis parameters. Despite these challenges, the low-energy synthesis strategy and use of accessible raw materials highlight the potential of SHS-derived porous silicon as a scalable and sustainable platform for future drug delivery applications, particularly in resource-limited settings.

Reactive oxygen species (ROS) are byproducts of normal cellular metabolism and play important roles in cell signaling and immune defense. However, when their production exceeds the cell’s antioxidant capacity, ROS accumulation leads to oxidative stress, damaging proteins, lipids, and DNA. In the brain, this oxidative imbalance has been closely linked to the development and progression of neurodegenerative diseases like Alzheimer’s. Under normal conditions, superoxide dismutase (SOD) enzymes play a key role in protecting cells by breaking down harmful superoxide radicals. Yet, reduced SOD activity and impaired regulation have been consistently observed in patients with neurodegeneration, including Alzheimer’s disease. Small-molecule mimics of SOD, therefore, represent a promising therapeutic approach. In this study, we evaluate an expanded library of tetra-aza macrocyclic ligands chelating either copper or manganese metals. Mechanistic analysis reveals how structural modifications to the macrocyclic ring, particularly R-group substitutions that alter steric environment and electronic properties, directly influence catalytic reactivity and stability. Evaluation of Cu- and Mn-based complexes highlights distinct trends in activity and identifies structural motifs that enhance SOD-like function. These findings provide design principles for developing antioxidant therapeutics targeting oxidative stress.

“Superfrog Science: Experiments for at Home and in the Classroom” is a creative endeavor that encourages young scientists to get curious about science and help learn a variety of chemistry concepts. This book is a visual representation of the importance of exploring the bounds of creativity in science. Join Superfrog as he goes on a learning adventure conducting science experiments and using the scientific method to deepen his knowledge about chemistry, making it easy to learn by conducting each experiment with easy-to-follow comic panels. This book strives to make science experiments accessible, affordable, and fun. It is perfect for encouraging hands-on learning, with in-depth explanations of the “how” and “why” of these experiments. Superfrog asks discussion questions and provides variations of the experiments to get his students to think about cause-and-effect and variable manipulation when it comes to the scientific process, as well as encourage collaboration with his peers. The educational activities featured are made for scientific discovery inside and outside the classroom. Make chemistry fun and easy with Superfrog!

Riboswitches are structured RNA elements that regulate gene expression through ligand-induced conformational changes and provide a platform for engineering cell-based biosensors. By coupling aptamers to reporter genes, synthetic riboswitches enable small-molecule–dependent detection of clinically relevant metabolites. This study focuses on sarcosine, associated with prostate cancer progression, and urate, linked to gout. Two sarcosine-responsive candidates were evaluated in E. coli using β-galactosidase and GFP reporter systems. Although construct integrity was confirmed, neither candidate demonstrated ligand-dependent activation in CDR or minimal media, suggesting insufficient regulatory activity under tested conditions. In parallel, a urate-responsive riboswitch library underwent dual selection with chloramphenicol resistance for positive selection and 5-fluorouracil counterselection for negative selection. After multiple selection rounds and screening of 192 colonies, no urate-specific variants were identified. Increasing chloramphenicol concentration to strengthen positive selection similarly yielded no hits. Future work will focus on further increasing both positive and negative selection intensity to enhance enrichment of functional variants and improve development of RNA-based biosensors for accessible metabolite detection. Additionally, future efforts will explore the adenine riboswitch library as a potential platform for developing novel biomarker detection systems.

Interactive Querying and Visualization of Solar Events

Author: Thu My Banh, Cathy Nguyen, Pandey Chetraj

Access to structured solar flare event data is essential for space weather (SWx) research, operational analysis, and machine learning applications. While the solar flare event archive maintained by the Lockheed Martin Solar and Astrophysics Laboratory (LMSAL) provides a widely used curated record of flare activity, the archive is primarily accessible through static web interfaces rather than a programmable query system. This makes automated filtering, dataset generation, and large-scale analysis difficult for researchers. To address this limitation, we developed a full-stack web application that provides programmatic access to LMSAL solar flare event records through a queryable API. A Python-based data ingestion pipeline retrieves and deduplicates event information from LMSAL’s rolling snapshot archive and stores it in a structured format. A FastAPI backend exposes endpoints that allow users to filter events by date range and GOES flare classification, enabling rapid dataset generation for analysis workflows. The frontend, implemented in React, allows users to query the event catalog, visualize results in a structured table, and export filtered datasets as CSV or JSON files. To improve data reliability and context, the system cross-references LMSAL event records with NOAA solar flare catalogs, allowing users to compare event metadata across independent data sources. Additionally, the application integrates with the Helioviewer API to display solar imagery corresponding to each event, with derived heliographic positions overlaid onto the solar disk to provide spatial context. The resulting system provides a lightweight platform for exploring, querying, and exporting solar flare event data, lowering the barrier to accessing operational flare records and facilitating dataset generation for space weather analysis and predictive modeling.

Large language models (LLMs) are increasingly framed as force multipliers for cyberattacks, yet most existing evaluations focus on isolated artifact generation rather than the construction and execution of full offensive workflows. This paper presents a controlled empirical study of LLM-assisted cyberattack construction across multiple representative attack classes, including automated SQL injection exploitation, spyware assembly, reverse shell establishment, and denial-of-service traffic generation. We evaluate several contemporary models—including ChatGPT-4o, ChatGPT-5.2, ChatGPT-5.1-instant, Claude Sonnet 4.6, and Gemini 3—within fully sandboxed virtualized environments, treating each model strictly as an advisory system embedded within a human-driven workflow.

Our experimental design decomposes attacks into staged operational workflows encompassing reconnaissance, payload generation, system integration, troubleshooting, and persistence. This structure enables systematic analysis of where automation succeeds or fails during real execution rather than relying on single-shot demonstrations. Across scenarios, LLMs consistently reduce effort for localized technical tasks such as command syntax recall, tool configuration, payload scaffolding, and procedural troubleshooting. However, reliable end-to-end attack execution remains limited. SQL injection automation succeeds primarily when established tools encapsulate complex orchestration, while more complex scenarios such as spyware assembly fail at system-level integration, environment-specific dependency resolution, and evasion of host defenses.

Across models and attack classes, automation consistently breaks at environment-dependent boundaries requiring global reasoning, state awareness, and cross-stage workflow coordination. These findings suggest that contemporary LLMs do not autonomously execute cyberattacks but instead function as workflow accelerators that lower the expertise threshold required to operationalize existing offensive techniques. This capability-boundary perspective provides a more realistic foundation for threat modeling, defensive planning, and future evaluation of AI-assisted cybersecurity risks.

Medical students lack effective tools for developing clinical reasoning, as most resources emphasize memorization rather than decision-making. DiseaseQuest is an AI-powered, gamified platform that addresses this gap through realistic patient simulations and decision-based scenarios. It enables students to work through complete clinical cases using interactive, patient-centered dialogue. Supported by a multi-agent framework, the platform provides adaptive guidance, diagnostic feedback, and personalized evaluations. By promoting active learning and problem-solving, DiseaseQuest offers a transformative approach that replaces passive study with immersive, hands-on practice, helping students strengthen diagnostic thinking and better prepare for real-world clinical decision-making.

As obesity continues to rise in the United States, bariatric surgery has become as increasingly common medical intervention to support significant and sustained weight loss. However, the procedure presents challenges, as patients must adopt strict dietary guidelines, develop consistent meal tracking habits, and maintain long-term lifestyle changes. Existing weight-loss applications fail to address the unique nutritional requirements of bariatric patients, which include surgery-specific restrictions, medical conditions, personal preference in food, and individualized lifestyle factors. Along with that, they lack integrated long-term monitoring tools that allow healthcare providers to effectively track patient progress and adherence after surgery. This senior design project presents a prototype mobile application developed from scratch to support patients throughout the bariatric journey. The application integrates AI-driven personalization to generate tailored daily nutritional guidance, adapt to individual health data, and provide meal tracking support. In addition, the platform centralizes patient data for healthcare providers, improving long-term monitoring, increasing tracking accuracy, and reducing manual workload. By combining personalized patient support with provider-facing analytics, this solution aims to enhance postoperative adherence and improve long-term surgical outcomes.

Understanding weather conditions during flight operations can help explain incidents and reduce risky behavior. The Brazos Safety Systems Weather Application integrates aviation weather data sources, including METAR reports and radar imagery, to visualize conditions around airports and during historical flights. Users can upload flight records and review the associated weather conditions through the application. By presenting aviation weather data in a centralized and accessible format, the application supports post-flight analysis and helps identify weather-related factors connected to flight incidents. The goal is to provide insights that improve understanding of past flight conditions and help prevent similar issues in future aviation operations.

Solar flares are among the most significant drivers of space-weather disturbances, motivating ongoing efforts to develop reliable forecasting methods from solar observations. The Solar Dynamics Observatory continuously produces high-resolution full-disk solar imagery used for monitoring solar activity. These observations have enabled substantial progress in machine learning–based flare prediction; however, most models remain confined to research studies, with limited deployment in operational systems that support continuous forecasting and systematic performance validation. This work presents a lightweight operational framework for near-real-time solar flare forecasting built around machine learning models proposed in the literature. The system retrieves full-disk solar imagery from the Helioviewer API, performs automated preprocessing, and generates predictions using a convolutional neural network–based forecasting model. Predictions and corresponding observations are stored to enable periodic forecast verification using standard performance metrics, allowing model performance to be monitored over time and potential prediction drift to be identified. The framework is implemented as an interactive application using Streamlit, providing an integrated interface for automated data ingestion, near-real-time inference, and ongoing model evaluation. The proposed system enables continuous monitoring of solar flare forecasts while providing a practical framework for tracking model performance and detecting prediction drift in operational settings.

We present the AI-Driven Adaptive Tutoring (AIAT) framework, a modular multi-agent system that generates structured, retrieval-grounded, and multimedia-enhanced courses. AIAT targets a common gap in AI in Education: large language models (LLMs) can produce fluent explanations, but they often lack pedagogical structure, factual grounding, and multimodal integration. To address this, AIAT uses a three-stage pipeline. First, a blueprint agent creates a course outline with learning objectives and topic dependencies using schema-validated structured outputs. Second, a chapter-expansion agent instantiates atomic topics with formative questions and summaries in JSON mode. Third, an enrichment agent generates topic-level explanations, visualization specifications, and triggers for narrated video production. Retrieval-augmented generation (RAG) combines a MongoDB Atlas Vector Search backend for course materials and a Pinecone pipeline for PDF-derived knowledge, grounding explanations in external content. A Next.js frontend streams responses and assembles text, diagrams, and videos into a unified learner experience.

The design is explicitly guided by mastery learning, cognitive load theory, and the Cognitive Theory of Multimedia Learning, with principles such as atomic topics, anti-fluff constraints, and visual-verbal alignment encoded in prompts and schemas. We report system-level metrics (e.g., latency by component) and operational reliability, and we outline a concrete evaluation plan, including pre/post-learning assessments, expert rubric-based accuracy checks, and subjective cognitive load measures. We also discuss the equity and accessibility implications of relying on commercial APIs and propose mitigation strategies (e.g., caching, partial use of lightweight models, and instructor-in-the-loop authoring). The contribution of this work is a reproducible architecture that connects multi-agent orchestration, RAG, and multimodal rendering to pedagogical theory, along with an evaluation roadmap that explicitly addresses the current lack of large-scale human studies.

Space Weather Forecasting relies on large volumes of time-stamped solar observations paired with event catalogs describing flare occurrence and intensity. While these datasets are widely available, preparing them for machine learning remains a substantial and often overlooked challenge. Researchers must convert irregular observation streams into consistent temporal samples, construct observation and prediction windows, align events with observations, manage missing data and cadence inconsistencies, and ensure that training and evaluation splits avoid temporal or regional data leakage. These preprocessing steps are typically implemented in ad-hoc scripts that are difficult to reproduce, extend, or compare across studies. We propose an open-source Python library that standardizes the construction of machine-learning-ready datasets for solar event forecasting. The library ingests user-provided observation tables (e.g., SDO image timestamps and file paths) and event catalogs (e.g., GOES flare lists) and automatically generates indexed training samples suitable for PyTorch datasets and data loaders. Users can define flexible observation windows ranging from single time points to multi-frame temporal sequences, specify prediction horizons, and configure event-labeling rules. The framework also provides mechanisms for handling missing observations, irregular cadences, and explicit representation of temporal gaps. To support rigorous experimental design, the library includes reproducible dataset partitioning strategies such as chronological and tri-monthly splits, as well as optional active-region-aware grouping based on NOAA region catalogs. These features allow researchers to build both full-disk and active-region-based forecasting datasets while minimizing common sources of information leakage. Although the initial implementation focuses on solar flare prediction, the framework is designed to be extensible to other space weather phenomena including coronal mass ejections (CMEs) and solar energetic particle (SEP) events. By formalizing the transformation from raw observational records and event lists into reproducible machine learning datasets, this tool reduces the overhead of data preparation and promotes more transparent, comparable, and scalable space weather forecasting research.

Solar flares are significant space weather phenomena that can impact satellites, communication systems, and many technological infrastructures, rendering accurate flare forecasting a crucial objective in heliophysics study.The NASA Community Coordinated Modeling Center (CCMC) Flare Scoreboard collects predictions from multiple solar flare forecasting models developed by different research groups. While this resource provides a useful platform for comparing different forecasting approaches, systematic validation of these models remains challenging because predictions are reported in different formats and are not easily comparable across models. In this work, we develop an automated framework to collect and organize flare forecasts from several models available in the CCMC Flare Scoreboard and convert them into a consistent dataset that allows direct comparison between models. The processed dataset includes predictions across multiple years and forecast windows. To evaluate model performance, we compare the predicted flare probabilities with observed flare events reported in the SolarSoft (SSW) Latest Events archive. By aligning forecast windows with actual flare occurrences, we establish a consistent approach for validating model predictions. This approach facilitates a systematic comparison of forecasting behaviour among various models and assists in identifying those that exhibit superior or inferior predicted ability.The resulting pipeline provides a reproducible way to analyze solar flare forecasting systems and supports future efforts to improve the reliability of space weather prediction methods.

Solar flares are major drivers of space-weather disturbances and can disrupt satellites, communication systems, and navigation infrastructure. Recent deep learning approaches have demonstrated promising performance for solar flare forecasting, yet many models operate either on full-disk solar observations or on isolated active-region patches. This separation limits their ability to combine global solar context with localized magnetic structure and can affect the reliability of predictions. In addition, full-disk models often provide limited information about which regions drive their forecasts. This study presents a two-stage deep learning framework that integrates full-disk and active-region–level analysis within a unified flare forecasting pipeline. The system first performs full-disk inference using a convolutional neural network trained on solar magnetograms to estimate the global probability of flare occurrence. Attribution-based explanations are then generated to identify regions that most strongly influence the model prediction. These regions are mapped back to the solar disk and converted into candidate active-region patches, accounting for solar rotation and spatial alignment. The resulting patches are subsequently analyzed using a dedicated active-region forecasting model trained on SDO HMI SHARP data to produce localized flare probabilities. By integrating global context with targeted active-region analysis, the proposed framework combines two complementary forecasting models into an end-to-end prediction system. The resulting pipeline provides both full-disk and region-level flare probabilities, improving interpretability while enhancing the reliability of flare forecasts through focused secondary analysis of the most relevant solar regions.