arXiv subjects

Hakan Başağaoğlu

Publications and source records attributed to Hakan Başağaoğlu.

5 recordsLinked to original sources

arXiv2026

Predictors and Orchestrators: Parsimonious Machine Learning within an Agentic AI Harness for Multi-Horizon Karst Aquifer Forecasting

Forecasting karst aquifer dynamics is difficult because recharge responses are nonlinear, event-driven, and governed by strongly heterogeneous flow paths. This study develops and evaluates a deployment-aware framework for 1-12-week-ahead prediction of spring discharge and groundwater level using approximately 79 years of hydroclimatic observations from the Edwards Aquifer, Texas. Five model families were compared under a common temporal evaluation design: extreme gradient boosting, extremely randomized trees, long short-term memory, convolutional neural networks, and Transformers. Predictions were evaluated using coefficient of determination, Kling-Gupta efficiency, root-mean-square error, and agreement with operational drought thresholds. Extreme gradient boosting was consistently most reliable, with R2 at least 0.97, 0.96, and 0.94 across 1-4-, 5-8-, and 9-12-week horizons, respectively, and greater than 90% critical-stage agreement at the first three drought stages across all horizons. Deep models were competitive at short horizons but degraded progressively and exhibited isolated failures at longer lead times. We attribute this contrast to an alignment between tree partitioning and low-dimensional, axis-aligned hydroclimatic predictors, together with the tendency of neural models to smooth irregular extremes. The validated models were embedded in a five-agent operational architecture that automates data acquisition, model assignment, deterministic prediction, threshold monitoring, prospective verification, literature retrieval, and reporting. The contribution is therefore a transferable framework joining parsimonious model selection, leakage-aware multi-horizon evaluation, decision-relevant threshold skill, and auditable agentic automation.

cs.LG↗

arXiv2021

Explainable Artificial Intelligence Reveals Novel Insight into Tumor Microenvironment Conditions Linked with Better Prognosis in Patients with Breast Cancer

We investigated the data-driven relationship between features in the tumor microenvironment (TME) and the overall and 5-year survival in triple-negative breast cancer (TNBC) and non-TNBC (NTNBC) patients by using Explainable Artificial Intelligence (XAI) models. We used clinical information from patients with invasive breast carcinoma from The Cancer Genome Atlas and from two studies from the cbioPortal, the PanCanAtlas project and the GDAC Firehose study. In this study, we used a normalized RNA sequencing data-driven cohort from 1,015 breast cancer patients, alive or deceased, from the UCSC Xena data set and performed integrated deconvolution with the EPIC method to estimate the percentage of seven different immune and stromal cells from RNA sequencing data. Novel insights derived from our XAI model showed that CD4+ T cells and B cells are more critical than other TME features for enhanced prognosis for both TNBC and NTNBC patients. Our XAI model revealed the critical inflection points (i.e., threshold fractions) of CD4+ T cells and B cells above or below which 5-year survival rates improve. Subsequently, we ascertained the conditional probabilities of $\geq$ 5-year survival in both TNBC and NTNBC patients under specific conditions inferred from the inflection points. In particular, the XAI models revealed that a B-cell fraction exceeding 0.018 in the TME could ensure 100% 5-year survival for NTNBC patients. The findings from this research could lead to more accurate clinical predictions and enhanced immunotherapies and to the design of innovative strategies to reprogram the TME of breast cancer patients.

q-bio.GN↗

arXiv2020

Particle Shape Influences Settling and Sorting Behavior in Microfluidic Domains

We present a new numerical model to simulate settling trajectories of discretized individual or a mixture of particles of different geometrical shapes in a quiescent fluid and their flow trajectories in a flowing fluid. Simulations unveiled diverse particle settling trajectories as a function of their geometrical shape and density. The effects of the surface concavity of a boomerang particle and aspect ratio of a rectangular particle on the periodicity and amplitude of oscillations in their settling trajectories were numerically captured. Use of surrogate circular particles for settling or flowing of a mixture of non-circular particles were shown to miscalculate particle velocities by a factor of 0.9-2.2 and inaccurately determine the particles' trajectories. In a microfluidic chamber with particles of different shapes and sizes, simulations showed that steady vortices do not necessarily always control particle entrapments, nor do larger particles get selectively and consistently entrapped in steady vortices. Strikingly, a change in the shape of large particles from circular to elliptical resulted in stronger entrapments of smaller circular particles, but enhanced outflows of larger particles, which could be an alternative microfluidics-based method for sorting and separation of particles of different sizes and shapes.

physics.comp-ph↗

arXiv2020

Enhanced computational performance of the lattice Boltzmann model for simulating micron- and submicron-size particle flows and non-Newtonian fluid flows

Significant improvements in the computational performance of the lattice-Boltzmann (LB) model, coded in FORTRAN90, were achieved through application of enhancement techniques. Applied techniques include optimization of array memory layouts, data structure simplification, random number generation outside the simulation thread(s), code parallelization via OpenMP, and intra- and inter-timestep task pipelining. Effectiveness of these optimization techniques was measured on three benchmark problems: (i) transient flow of multiple particles in a Newtonian fluid in a heterogeneous fractured porous domain, (ii) thermal fluctuation of the fluid at the sub-micron scale and the resultant Brownian motion of a particle, and (iii) non-Newtonian fluid flow in a smooth-walled channel. Application of the aforementioned optimization techniques resulted in an average 21 performance improvement, which could significantly enhance practical uses of the LB models in diverse applications, focusing on the fate and transport of nano-size or micron-size particles in non-Newtonian fluids.

physics.comp-ph↗

arXiv2020

Combined effects of fluid type and particle shape on particles flow in microfluidic platforms

Recent numerical analyses to optimize the design of microfluidic devices for more effective entrapment or segregation of surrogate circulating tumor cells (CTCs) from healthy cells have been reported in the literature without concurrently accommodating the non-Newtonian nature of the body fluid and the non-uniform geometric shapes of the CTCs. Through a series of two-dimensional proof-of-concept simulations with increased levels of complexity (e.g., number of particles, inline obstacles), we investigated the validity of the assumptions of the Newtonian fluid behavior for pseudoplastic fluids and the circular particle shape for different-shaped particles (DSPs) in the context of microfluidics-facilitated shape-based segregation of particles. Simulations with a single DSP revealed that even in the absence of internal geometric complexities of a microfluidics channel, the aforementioned assumptions led to 0.11-0.21W (W is the channel length) errors in lateral displacements of DSPs, up to 3-20% errors in their velocities, and 3-5% errors in their travel times. When these assumptions were applied in simulations involving multiple DSPs in inertial microfluidics with inline obstacles, errors in the lateral displacements of DSPs were as high as 0.78W and in their travel times up to 23%, which led to different (un)symmetric flow and segregation patterns of DSPs. Thus, the fluid type and particle shape should be included in numerical models and experiments to assess the performance of microfluidics for targeted cell (e.g., CTCs) harvesting.

physics.comp-ph↗