Digital Commons Network^™

Stabilized Multi-Objective Optimization For Camouflage Attack In Remote Sensing, Omid Rajabi Rostami, Kazi Aminul Islam, Liuwan Zhu, Rui Ning, Chungsheng Xin, Hongyi Wu, Jiang Li

Electrical & Computer Engineering Faculty Publications

We investigate the vulnerability of multi-task maritime surveillance systems in which object detection and semantic segmentation operate concurrently. We propose Stabilized Multi-Objective Optimization (SMO), a framework that jointly targets Mask R-CNN and U-Net with a single universal adversarial texture in a digital white-box setting, with additional cross-model transfer evaluation. SMO combines a logarithmic-inversion loss transformation, feature inconsistency, and a systematic comparison of six optimization strategies for seven heterogeneous objectives. The loss transformation controls loss-dependent gradient scaling, while a U-Net generator supplies a spatially coherent texture and a hull-aligned application function accommodates target geometry without explicit Expectation over Transformation (EoT) sampling. …

Application Of Organic Geochemistry To The Characterization Of Hydrochar And Biochar: Insights Into Composition And Optimization, Michael A. Kruge, Teresa A. Centeno, Alvaro Amado-Fierro, José Manuel González-Lafuente, Rubén Forján, José Luis Gallego

Department of Earth and Environmental Studies Faculty Scholarship and Creative Works

Hydrothermal carbonization has garnered significant attention in recent studies due to potential applications of the hydrochar produced, which overlap with those of torrefied biochar, including soil improvement, carbon sequestration, and energy production. However, unlike the relatively uniform properties of biochar, hydrochar characteristics can vary greatly depending on the feedstock used. Advanced characterization techniques are essential to better understand these materials and enhance their practical applications. Research on hydrochar requires a multi-faceted approach, including molecular-level studies, to optimize production processes and identify specific applications.

In this regard, analytical methods commonly used in organic geochemistry could play a crucial role in deepening …

Analysis Of Policies And Incentives For The Successful Implementation Of Hydrogen-Fueled Medium-Duty And Heavy-Duty Vehicles In Humboldt County, California, Alka Verma

Cal Poly Humboldt theses and projects

The 21st century has seen a significant rise in global greenhouse gas (GHG) emissions, with the transportation sector contributing 23% of these emissions. Medium-duty and heavy-duty vehicles (MD/HD) are particularly impactful, accounting for over a quarter of transport-related emissions. In Humboldt County, California, transportation represents 53% of total emissions, with MD/HD vehicles being a major contributor. As light-duty vehicles shift to zero-emission alternatives, the MD/HD sector faces unique challenges. Hydrogen fuel cell vehicles offer a promising solution, providing longer range, higher energy density, and quicker refueling compared to battery electric vehicles (BEVs). These features make hydrogen an attractive option for …

Development Of The Core Lit Apparatus For Seaweed Hatcheries (Clash) Bioreactor Using A Germplasm Approach, Phillip O. Tahimic

Cal Poly Humboldt theses and projects

In comparison to the Asian aquaculture industry, the United States has minimal seaweed production. There are several drivers of the limited industry in the US, such as regulatory constraints and limited market demand, but the ability to scale is a considerable barrier to commercialization. One possible solution is the development of land-based systems that integrate bioreactors, which utilize fewer resources and do not wholly rely on an oceanic flow-through system. This study assessed the application of a modular bioreactor, known as Core Lit Apparatus for Seaweed Hatcheries (CLASH), as a nursery system and open-source project designed to expand land-based seaweed …

Land Cover Classification Using Optimized Imagery Resolution And Machine Learning Algorithms For A Long-Term Monitoring And Restoration Project, Jessica R. Suoja

Cal Poly Humboldt theses and projects

Ecosystem services and functions are prone to water resource exploitation resulting in cascading effects that include decrease of biodiversity and loss of riparian vegetation, a keystone habitat in desert riparian ecosystems. Mono Lake is a prime example of overexploitation of water resources leading to legal action and eventually a legally mandated long-term monitoring and restoration project. Monitoring and restoration projects can benefit from techniques such as remote sensing and machine learning algorithms to generate accurate land cover classification maps for calculating land cover change over time. However, the spatial resolution of remote sensing imagery and the machine learning algorithms chosen …

Digital Twin Technologies For Battery Systems: Advancements, Applications, And Future Directions, Seyed Saeed Madani, Yasmin Shabeer, Michael Fowler, Satyam Panchal, Carlos Ziebert, Hicham Chaoui, François Allard

Electrical & Computer Engineering Faculty Publications

The relationships among deep learning, edge computing, artificial intelligence (AI), and the most recent advancements in digital twin (DT) technology for battery energy storage systems are discussed in this paper. The study highlights the need for improved cloud-edge coordination, AI model development, and stronger cybersecurity features by demonstrating real-world applications of digital twin technology in electric vehicles (EVs), aircraft, and grid storage. It also described DT-based structures for fault detection, real-time monitoring, and optimization through standardization and battery management system (BMS) fusion. Because DT-based solutions for distributed energy resources (DERs) offer improved energy management systems, various studies have been conducted …

Automated Writer And Acquisition-Condition Classification Of Digitally Captured Handwriting Using Statistical Dynamic Features And Support Vector Machines, Long-Huang Tsai, Hsiang-Ju Lai, Wen-Chao Yang, Jiajun Jiang, Chung-Hao Chen

Electrical & Computer Engineering Faculty Publications

Digitally captured handwriting preserves pen trajectories and dynamic signals, but it also records hardware- and input-dependent properties that can confound forensic interpretation. This study revises a support vector machine (SVM) screening framework using 16,500 samples from 30 writers, 11 writing-content categories, and five acquisition conditions spanning three tablets and stylus or finger input. Twenty-four raw and derived time-series variables were summarized by maximum, minimum, mean, median, and standard deviation, yielding 120 features; the mode statistic was removed. Writing direction and angular velocity were recalculated with atan2-based vector formulas. Unavailable device/API channels were encoded as zero, and Z-score parameters were estimated …

Machine Learning Classification Of Prostate Cancer Genomic Sequences Using K-Mer And Sequence-Derived Features, Kuldeep Rawat, Hirendra Nath Banerjee, Jamie Noble, Saa Naudia Deloatch, Satyendra Banerjee, Sachin Shetty, Soumya Banerjee

VMASC Publications

Prostate cancer disproportionately impacts African American men, who experience significantly higher mortality rates and earlier disease onset than other populations. Current diagnostic approaches, including prostate-specific antigen testing and biopsy, lack sufficient specificity and sensitivity, underscoring the need for accurate, molecular-level classification tools. This paper presents a machine learning framework for binary classification of genomic DNA sequences as cancerous or healthy. A dataset of 1684 FASTA-formatted sequences obtained from the National Library of Medicine - GenBank was analyzed, with 1662 sequences retained after quality control filtering. Feature engineering yielded 67 attributes, including GC content, Shannon entropy, sequence length, and trinucleotide k-mer …

Dyno : Dynamic Neurosymbolic Orchestrator For Multi-Agent Systems, Ritvik Garimella, Chathurangi Shyalika, Renjith Prasad, Amit Sheth

Publications

Large Language Model (LLM)-based multi-agent systems (LaMAS) represent an emerging paradigm for tackling complex, multi-step reasoning and decision-making problems. As these systems scale, orchestration, which is the ability to coordinate, manage, and evaluate the interactions among diverse agents, becomes central to their success. While recent orchestrators such as AgentFlow have demonstrated promise in managing communication and task delegation, they remain limited in their ability to understand task semantics, coordinate heterogeneous agent types (e.g., reactive vs. cognitive), and adaptively align outputs with human-defined goals. In this position paper, we introduce the DYNO (Dynamic Neurosymbolic Orchestrator), a system developed as part of …

A Dataset-Centric Analysis Of Evaluation Protocols In Face Morph Attack Detection, Sheerko R. Hmasalah, Abdulbasit K. Al-Talabani, Aras T. Asaad

Polytechnic Journal

Face morph attack detection (MAD) is often evaluated using datasets collected from diverse sources, created for different purposes, and acquired under varying conditions. This heterogeneity raises questions about how evaluation protocols and dataset characteristics influence reported performance. This work adopts a dataset-centric perspective to analyze the effects of evaluation protocol and dataset composition, including visual quality and morph-to-genuine imbalance, on MAD performance. Experiments are conducted on eight datasets and four morphing techniques using a fixed pipeline evaluated across six backbones, including Vision Transformer (ViT) and five CNN architectures, and ten evaluation scenarios covering homogeneous and heterogeneous cross-morph generalization. Performance is …

Solving High-Dimensional Differential Equations Using Recurrent And Residual Neural Network Architectures, Hind Khaled Kolaib

Knowledge Engineering and Data Science

High-dimensional Partial Differential Equations (PDEs) form the foundation of complex process modeling in various scientific and engineering applications, including finance, physics, and optimal control. However, classical numerical methods are adversely affected by the curse of dimensionality, making them inapplicable for large-scale problems. Recently, however, deep learning-based approaches have provided a new toolbox for these high-dimensional PDEs, including methods such as the Deep Backward Stochastic Differential Equation (Deep BSDE) method. Our approach draws on a more sophisticated deep learning backbone, using neural networks (in our case, a Residual Neural Network and a Long Short-Term Memory network (LSTM) integrated into the Deep …

To Print A Remake: An Analysis Of Hollywood Remakes And Their Cultural Value, Connor F. Seaton

Honors Undergraduate Theses

In recent years, audiences and movie critics have expressed concern that Hollywood’s growing reliance on remakes, sequels, franchises, and similar adaptations has led to a broader worry that originality is fading from modern cinema and that the industry is instead focused on using adaptations to maximize profits. Although adaptation is often seen as a commercially driven framework for reproducing existing intellectual property in a new media format, this thesis argues that it should be recognized as an autonomous cultural category with its own artistic, historical, and social significance and merit. By analyzing adaptation scholarship and reviewing its complex historical development, …

Using Inferences From Natural Language Narratives To Improve Video Question Answering, Hoang Bao Truong

Graduate Studies Theses and Dissertations 2026

The purpose of this thesis is to examine how structured narrative representation and reasoning strategies jointly affect the performance of Video Question Answering (VideoQA). Although recent advances in large multimodal and language models have improved video description and retrieval, causal and counterfactual reasoning remain challenging. This thesis studies an inference-only pipeline in which videos are converted into natural-language narratives, and those narratives may optionally be transformed into a structured NarrativeML format before multiple-choice questions are answered without task-specific fine-tuning. NarrativeML is a machine-readable narrative representation that explicitly encodes entities, events, and their causal and temporal relations. Three representational contexts are …

Deciphering Ultrafast Photoinduced And Photocatalytic Reaction Dynamics On Oxide Surfaces: Direct Detection Of Radical Intermediates, Fragment Trapping, And Carbon–Carbon, Carbon–Oxygen, And Carbon–Hydrogen Bond Formation Pathways, Aakash Gupta

Graduate Studies Theses and Dissertations 2026

Understanding photoinduced reactions at solid interfaces is essential for advancing heterogeneous photocatalysis, surface photochemistry, and energy conversion technologies. This dissertation investigates the ultrafast dynamics of reactive intermediates, fragment trapping, and radical-mediated bond formation on oxide surfaces using time-of-flight mass spectrometry in conjunction with femtosecond pump-probe spectroscopy. Various experimental findings are validated through collaborations via density functional theory (DFT). By combining temporal, mass, and energy-resolved measurements, this work provides molecular-level insight into the elementary processes governing light-driven surface reactions. The photodissociation dynamics of CH₃I adsorbed on TiO₂(110), TiO₂(100), and amorphous silicon oxide surfaces are examined …

Revolution In The Age Of Social Media: A Mathematical Model For Information, Dissent, And Stability, Killian Muollo

Graduate Studies Theses and Dissertations 2026

Revolutions, defined by Skocpol as rapid transformations in class, state, and/or social structures, are important world events that can cause civil wars, spark international trends, and result in transitions toward democratic and autocratic regimes alike. They are characterized largely by the mechanism of mass mobilization, which is increasingly facilitated by online networks and digital communication. In this dissertation, we investigate such means and outcomes of revolutions as dynamical systems. We construct three models describing separate but complementary aspects of revolution, beginning at the smallest unit of analysis and then moving outward in scope. First, we construct a graph-based model to …

Comparative Life Cycle Assessment Of End-Of-Life Crystal Silicon Photovoltaic Panels: Recovery Methods And Extended Life In Agricultural Application, Patima Chaichana, Vacharaporn Soonsin, Nattapong Tuntiwiwattanapun

Applied Environmental Research

The increasing deployment of crystalline silicon (c-Si) photovoltaic (PV) panels has raised concerns about their waste management. This study evaluated management strategies for discarded c-Si PV panels in Thailand, integrating environmental and economic analyses. Life cycle assessment (LCA) and cost-effectiveness analysis (CEA) were applied. The LCA can be divided into 2 parts: (1) secured landfill vs decentralized recycling by existing facilities vs centralized full recovery and (2) reusing PV panels in agricultural applications. The results revealed that secured landfills were the most environmentally burdensome (34.43 Pt), whereas centralized recycling achieved net benefits (-211.93 Pt) through emission reductions and recovery of …

Blue Carbon Stock Assessment And Climate Resilience Potential Of Mangrove Forest In Hung Thang Commune, Vietnam, Hla Phong Ko, Pham Hong Tinh, Nguyen Thuy Duong

Applied Environmental Research

Mangrove forests are vital blue carbon sinks that contribute to climate change mitigation and coastal resilience. This study assessed the carbon stock and spatial‒temporal dynamics of a mangrove forest in Hung Thang commune, Hai Phong Province, Vietnam, via a combination of field measurements, soil organic carbon (SOC) analysis, and normalized difference vegetation index (NDVI)-based remote sensing models. The results revealed that mangroves in the Hung Thang community store an average of 87.42 tC ha-1, with SOC accounting for approximately 19% of the total carbon. A generalized additive model (GAM) analysis revealed a consistent increase in carbon stocks between 1996 and …

Heavy Metals And Organic Carbon In Sediments Of Seagrass Sediments Of Trang Province, Thailand, Siriporn Pradit, Pornthep Wirachwong, Thongchai Nitiratsuwan, Sujaree Bureekul, Supraewpan Lohalaksanadech, Thawanrat Kobkeatthawin, Monticha Jirajaras, Prakrit Noppradit, Sanya Sirivithayapakorn

Applied Environmental Research

In this study, the accumulation of heavy metals (Cd, Cr, Cu, Fe, and Pb) in water, suspended sediments, sediments, and seagrass in Kalase Bay, Trang Province, Thailand, during the 2024 dry season was investigated. These findings indicate that the enrichment factor (EF) for all the metals was less than 1, suggesting that anthropogenic contamination is not a significant concern in the area. The translocation factor (TF) values were less than 1 for all the metals except Cu, whose TF was greater than 1; however, these values were not statistically significant, indicating limited phytoextraction capacity. The bioconcentration factor (BCF) values for …

Evaluation Of Soil Moisture Content, Ph, And Dominant Microorganisms In Crude Oil–Contaminated Soil Treated With Cow Dung, Indole-3-Acetic Acid (Iaa), And Simulated Microgravity, Amenze Ovenseri, Tawari-Fufeyin P.

Applied Environmental Research

Crude oil negatively affects soil physicochemical properties and microbial activity, thereby hindering plant growth and posing notable environmental and agricultural issues. The combined effects of cow dung, indole-3-acetic acid (IAA), and simulated microgravity on the recovery of soil degraded by crude oil were explored using Zea mays as the test plant. Soil was contaminated with crude oil at different concentrations (0%, 1%, 3%, and 5% v/w), with each concentration comprising eight treatments: cow dung, Zea mays seeds exposed to microgravity, and IAA alone or in combination. Changes in plant height, soil pH, soil moisture content, and soil microbial diversity were …

Evaluating Sediment Control Strategies Using Swat Based Bmp Assessment In A Tropical Highland Watershed, Northern Thailand, ฺBanchongsak Faksomboon, Wilailak Suanmali

Applied Environmental Research

Soil erosion remains a critical environmental challenge in the tropical highland watersheds of Southeast Asia, where steep terrain, intense monsoonal rainfall, and intensive land use interact to accelerate sediment generation and downstream degradation. This study aims to quantify spatial patterns of sediment yield and to systematically evaluate the effectiveness of individual and combined best management practices (BMPs) at both the watershed and subwatershed (SWW) scales using the Soil and Water Assessment Tool (SWAT) in a tropical highland watershed in northern Thailand. Baseline simulations reveal pronounced spatial heterogeneity in erosion severity, with substantial portions of the watershed exhibiting moderate to extreme …

Exploring Consumers’ Intention And Behavior In The Circular Economy : Evidence From Vietnam, Tuan Hoang Nguyen, Vo Minh Thang Phan

Applied Environmental Research

This study aims to address the key gaps in understanding the factors influencing the intention–behavior relationship of consumers in the context of the circular economy (CE). Grounded in the theory of planned behavior (TPB), this research extends the framework by integrating social pressure, attitudes toward green consumption, and the availability of CE products as crucial components that shape intention and behavior. Data were collected from 603 Vietnamese consumers and analyzed using partial least squares structural equation modeling (PLS-SEM). The results confirm the core TPB constructs, with perceived behavioral control emerging as the most influential factor. Notably, attitude toward green consumption …

Effects Of The Psb-To-Ow Ratio And Light Intensity On Biogas Composition During Phototrophic-Assisted Anaerobic Fermentation Of Organic Waste, Kridsana Jirasansawat, Sirilak Prasertkulsak, Nitiwist Teangthai

Applied Environmental Research

The integration of phototrophic processes into anaerobic fermentation offers a promising strategy for improving biogas quality; however, the combined effects of the photosynthetic bacteria-to-organic waste (PSB-to-OW) ratio and light intensity remain unclear. In this study, the photosynthetic bacteria (PSB)-assisted anaerobic fermentation of municipal organic waste under varying PSB-to-OW ratios and light intensities was evaluated. An optimal PSB-to-OW ratio of 1:2 resulted in significantly higher CH4 concentrations and lower CO2 and H2S concentrations than the other tested ratios did (p < 0.05). At this ratio, moderate illumination (2000 lx) resulted in the highest CH4 concentration (68.2 ± 0.3%), compared with 1000 lx (61.5 ± 0.4%) and 4000 lx (63.1 ± 0.5%). Under illumination, the CO2 and H2S concentrations were lower than those under dark conditions, indicating a more favorable biogas composition. Kinetic analysis indicated that CO2 and H2S exhibited apparent first-order behavior under illumination, with the highest rates occurring at 2000 lx (kH2S = 0.093 day-1; kCO2 = 0.059 day-1), suggesting light-dependent transformation processes. Metagenomic analysis revealed a microbial community dominated by sulfide-oxidizing (Chlorobium sp.), photoheterotrophic (Rhodopseudomonas sp.), and syntrophic bacteria, supporting coupled carbon conversion and sulfur transformation. Overall, optimization of the …

Ai And Courts: An International Human Rights Perspective, Veronika Fikfak, Laurence R. Helfer

Faculty Scholarship

International human rights courts and treaty bodies are increasingly turning to automated decision-making (ADM) technologies to expedite and improve their review of individual complaints. These tribunals have yet to consider many of the legal, normative, and practical issues raised by the use of different types of automation technologies for these purposes. This chapter offers an initial assessment of the benefits and challenges of introducing ADM into international human rights adjudication. We weigh up the benefits of introducing these tools to improve international human rights adjudication – which include greater speed and efficiency in processing and sorting cases, identifying patterns in …

Llm-Assisted Legal Propositions Identification From Party Arguments In The U.S. Supreme Court Briefs, Heng Zheng, Alex Zhang

Faculty Scholarship

Merits briefs are central to U.S. litigation, serving as the primary means for parties to present arguments and persuade judges. Legal propositions in these merits briefs are the atomic units of arguments, whose relationships evolve throughout litigation and inform court decisions and precedent. Large language models (LLMs) have been applied to legal document review, but there is limited evidence on their ability to identify legal propositions in merits briefs. Given the labor-intensive nature of the task, we evaluate a human-AI collaborative approach to identifying legal propositions in the U.S. Supreme Court merits briefs, in which legal annotators review and revise …

High Algal Biomass Is Decoupled From Metabolism In The Gallatin River, Cora Mae Steinbach

Graduate Student Theses, Dissertations, & Professional Papers

Assessing eutrophication in rivers is difficult compared to lakes and coastal waters, because most algal biomass occurs on the riverbed and flows interact and co-vary with production (Biggs and Close, 1989; Bernhardt et al., 2018). Riverine eutrophication is typically assessed using algal biomass and water column nutrients (U.S. Environmental Protection Agency, 2000), but biomass is highly variable and labor-intensive to measure, while nutrient concentrations often underestimate enrichment due to rapid biological uptake (Dodds and Smith, 2016). Reach-scale river metabolism can help evaluate long-term functional change in rivers recovering from nutrient enrichment (Arroita et al., 2019; Jankowski et al., 2021; Diamond …

"What Power Do We Have?" Community Capacity And Justice In Samoa, California’S Floating Offshore Wind Terminal Development, Lauren Mccall Hart

Cal Poly Humboldt theses and projects

Floating offshore wind (OSW) is a relatively novel technology in the United States, which is positioned to play an integral role in California’s decarbonization strategy. Two federal OSW lease areas have been established off the coast of Northern California, and plans are underway to develop supporting port infrastructure, including the Humboldt Bay Offshore Wind Heavy Lift Marine Terminal (HLMT). The proposed HLMT site is adjacent to communities on the Samoa Peninsula of Humboldt Bay, which currently face socio-environmental vulnerabilities and critical infrastructure gaps. The social implications of OSW port development remain poorly understood, particularly in rural and underserved communities. This …

Transformer-Based Language Models For Bitcoin Market Prediction And Interpretation, Erich Gozebina

Masters Theses

"In the context of a Master's thesis in applied mathematics, this work investigates compact transformer-based language models as an instrument for Bitcoin-related predictions and decision support. The work connects three topics: the structure of the Bitcoin system and its data, the mathematical and algorithmic foundations of deep autoregressive transformers, and the design of practical training pipelines for financial applications. On this foundation, a reproducible ETL pipeline for Bitcoin data is developed and two forecasting experiments are conducted with the compact language model nanochat. The first experiment approaches the prediction of next-day price movements through autoregressive next-token generation based on structured …

Gauge-Invariant Gravitational Wave Polarization In Metric F(R) Gravity With Cosmological Implications, Ramesh Radhakrishnan, David Mcnutt, Delaram Mirfendereski, Alejandro Pinero, Eric Davis, William Julius, Gerald Cleaver

Physics & Astronomy Faculty Publications

We develop a fully gauge-invariant analysis of gravitational-wave polarizations in metric 𝑓⁡(𝑅) gravity with a particular focus on the modified Starobinsky model 𝑓⁡(𝑅) =𝑅 +𝛼⁢𝑅2 −2⁢Λ, whose constant-curvature solution 𝑅𝑑 =4⁢Λ provides a natural de Sitter background for both early- and late-time cosmology. Linearizing the field equations around this background, we derive the Klein–Gordon equation for the curvature perturbation 𝛿⁢𝑅 and show that the scalar propagating mode acquires a mass 𝑚2𝜓 =1/(6⁢𝛼), highlighting how the same scalar degree of freedom governs inflationary dynamics at high curvature and the propagation of gravitational waves in the current accelerating Universe. Using the scalar–vector–tensor …

31p Solution Nmr Investigation Of Abasic Dna, Clarissa R. Krimmel

Graduate Theses/Dissertations

Base excision repair (BER) mechanisms fix single base lesions in DNA, such as T:G mismatches. During the base excision repair mechanism, an abasic site (AP site) is formed as an intermediate. AP sites are unstable and highly mutagenic; they can stop DNA replication. This research investigates how the conformational properties of abasic sites in DNA affect the binding recognition of enzymes involved in DNA repair mechanisms, including BER. Three different abasic sequences are being analyzed for this research project. A second project looks at the effects of a naturally occurring purine derivative, hypoxanthine, on the DNA backbone. These hypoxanthine lesions …

Interpretable Machine Learning For Bridge-Pier Scour Prediction And Flood Resilience, Adil Khan, Dalya Ismael

Engineering Technology Faculty Publications

Bridge-pier scour is a leading cause of flood-induced bridge failure, yet practice still lacks transparent, physics-informed tools that link data-driven prediction with design guidance. This study develops an interpretable, physics-aware machine-learning framework to predict equilibrium scour depth and translate those predictions into actionable strategies for flood-resilient infrastructure. Using the 2014 U.S. Geological Survey Pier-Scour Database (569 laboratory cases), five models: Gradient Boosting, AdaBoost (Tree), XGBoost, Gaussian Process (RBF kernel), and Kernel Ridge (polynomial), were trained and evaluated with K-fold cross-validation. Model performance was evaluated using R², RMSE, and MAE. Gradient Boosting performed best, achieving training and testing R² of 0.99 …