arXiv subjects

Minjong Cheon

Publications and source records attributed to Minjong Cheon.

18 recordsLinked to original sources

arXiv2026

Rescene: band-limited stochastic forcing turns a frozen neural weather operator into a climate emulator

Over the past few years, the rapid development of machine learning (ML) models for weather forecasting has produced deterministic models whose medium-range skill matches or exceeds that of the European Centre for Medium-Range Weather Forecasts (ECMWF)'s high-resolution forecast (HRES). However, when these models are integrated freely beyond the horizon they were trained for, they blow up, drift, or lose their seasonal cycle, and retraining them for stability is expensive. We therefore ask what can be recovered from a strictly frozen backbone. We present Rescene, a 0.4 M-parameter wrapper around a frozen 1.5 degree, 6-hourly vision-transformer operator, developed using ERA5 reanalysis data and comprising a deterministic "slow clock" (0.33 M) that blends the forecast toward a lead-aware day-of-year climatology and a generative head (0.06 M) that adds a spectrally shaped stochastic perturbation at every step. The performance evaluation demonstrates that the deterministic wrapper alone is stable for decades but collapses daily variability to 40% of ERA5. Adding the generative head restores 126% (Z500) and 130% (MSLP) of the observed daily variability with pattern correlations of 0.89 and 0.92, recovers 82% of the observed blocking frequency, keeps the ensemble calibrated (spread-skill ratio 0.78-0.97 from day 7 to day 90), and integrates for 100 years with no detectable drift (+0.008 +/- 0.014 K per century). Moreover, because the perturbation is band-limited to total wavenumber $k \le 20$, the small scales are never forced, yet realistic $k \ge 20$ power is sustained: a direct decomposition of the 6-hourly energy budget shows that the frozen operator supplies 28 times more energy than the perturbation at $k \ge 40$, with a fractional growth rate 247 times larger at the grid scale than at planetary scales.

physics.ao-ph↗

arXiv2026

Robust for the Wrong Reasons: The Representational Geometry of LLM Robustness to Science Skepticism

Large language models (LLMs) are increasingly consulted on contested scientific questions, raising the concern that they will sycophantically retreat from established consensus when a user signals doubt -- drifting toward a false balance that treats settled science as one view among several. We test this across three open instruction-tuned models (Llama-3.1-8B, Qwen2.5-7B, Mistral-7B), three consensus-science domains (climate, vaccines, evolution), and single- and multi-turn settings, combining behavioral measurement with linear probing and activation patching. We do not observe sycophantic retreat. Instead, models show three distinct policies under the same skeptical pressure: reactive assertion, where consensus assertion increases rather than decreases (Llama); surface hedging, where tone softens while the position holds (Qwen); and non-response (Mistral). Pairwise judgments confirm the reactive shift is stance, not style (63.6%, p=.007), and a decomposition identifies increased consensus assertion, not false balance, as its driver (beta=+0.042 per dose, p<1e-77). Linear probes localize the divergence to middle layers -- perfect separation in Llama and Qwen versus 72% in Mistral, with non-overlapping confidence intervals -- indicating the non-responsive model does not linearly represent the skepticism signal at all. Crucially, this robustness does not transfer: it attenuates across domains and, in the safety-critical vaccine domain, can reverse, with myth-rebuttal weakening under skeptical pressure. We synthesize these into a four-way taxonomy separating active from accidental robustness, and argue that behavioral evaluation alone cannot distinguish a model that resists skepticism because it understands the signal from one that only appears to resist because it fails to perceive it.

physics.soc-ph↗

arXiv2026

Beyond Linear Superposition: Discovering Climate Features in AI Weather Models with KAN-SAE

Deep learning weather prediction models achieve remarkable predictive skill yet remain largely opaque: we know little about how they represent physical climate phenomena internally. Mechanistic interpretability through Sparse Autoencoders (SAEs) offers a principled route to decomposing these representations, but existing SAEs assume strictly linear feature superposition - a constraint ill-suited for the highly nonlinear atmospheric dynamics encoded in modern transformers. We introduce KAN-SAE, a sparse autoencoder whose encoder replaces the standard ReLU with learnable per-feature B-spline activations drawn from Kolmogorov-Arnold Networks (KANs), allowing each latent dimension to develop its own nonlinear gating profile. Applied to Sonny, KAN-SAE discovers 975 alive features (vs. 566 for a linear baseline, a 72% improvement) with 20% lower inter-feature redundancy and comparable reconstruction fidelity. Without any climate supervision, KAN-SAE identifies an interpretable European heatwave feature spatially concentrated over western Europe, and a western Pacific typhoon tracker confirmed by causal steering experiments. Our results demonstrate that nonlinear activations are essential for mechanistic interpretability of deep learning weather prediction models, recovering climate features that remain invisible to linear baselines.

cs.LG↗

arXiv2026

KAN-CL: Per-Knot Importance Regularization for Continual Learning with Kolmogorov-Arnold Networks

Catastrophic forgetting remains the central obstacle in continual learning (CL): parameters shared across tasks interfere with one another, and existing regularization methods such as EWC and SI apply uniform penalties without awareness of which input region a parameter serves. We propose KAN-CL, a continual learning framework that exploits the compact-support spline parameterization of Kolmogorov-Arnold Networks (KANs) to perform importance-weighted anchoring at per-knot granularity. Deployed as a classification head on a convolutional backbone with standard EWC regularization on the backbone (bbEWC) KAN-CL achieves forgetting reductions of 88% and 93% over a head-only KAN baseline on Split-CIFAR-10/5T and Split-CIFAR-100/10T respectively, while matching or exceeding the accuracy of all baselines on both benchmarks. We further provide a Neural Tangent Kernel (NTK) analysis showing that KAN's spline locality induces a structural rank deficit in the cross-task NTK, yielding a forgetting bound that holds even in the feature-learning regime. These results establish that combining an architecture with natural parameter locality (KAN head) with a complementary backbone regularizer (bbEWC) yields a compositional and principled approach to catastrophic forgetting.

cs.LG↗

arXiv2026

Sonny: Breaking the Compute Wall in Medium-Range Weather Forecasting

Weather forecasting is a fundamental problem for protecting lives and infrastructure from high-impact atmospheric events. Recently, data-driven weather forecasting methods based on deep learning have demonstrated strong performance, often reaching accuracy levels competitive with operational numerical systems. However, many existing models rely on large-scale training regimes and compute-intensive architectures, which raises the practical barrier for academic groups with limited compute resources. Here we introduce Sonny, an efficient hierarchical transformer that achieves competitive medium-range forecasting performance while remaining feasible within reasonable compute budgets. At the core of Sonny is a two-stage StepsNet design: a narrow slow path first models large-scale atmospheric dynamics, and a subsequent full-width fast path integrates thermodynamic interactions. To stabilize medium-range rollout without an additional fine-tuning stage, we apply exponential moving average (EMA) during training. On WeatherBench2, Sonny yields robust medium-range forecast skill, remains competitive with operational baselines, and demonstrates clear advantages over FastNet, particularly at extended tropical lead times. In practice, Sonny can be trained to convergence on a single NVIDIA A40 GPU in approximately 5.5 days.

cs.LG↗

arXiv2026

Demystifying KAN for Vision Tasks: The RepKAN Approach

Remote sensing image classification is essential for Earth observation, yet standard CNNs and Transformers often function as uninterpretable black-boxes. We propose RepKAN, a novel architecture that integrates the structural efficiency of CNNs with the non-linear representational power of KANs. By utilizing a dual-path design -- Spatial Linear and Spectral Non-linear -- RepKAN enables the autonomous discovery of class-specific spectral fingerprints and physical interaction manifolds. Experimental results on the EuroSAT and NWPU-RESISC45 datasets demonstrate that RepKAN provides explicit physically interpretable reasoning while outperforming state-of-the-art models. These findings indicate that RepKAN holds significant potential to serve as the backbone for future interpretable visual foundation models.

cs.CV↗

arXiv2025

Modernizing CNN-based Weather Forecast Model towards Higher Computational Efficiency

Recently, AI-based weather forecast models have achieved impressive advances. These models have reached accuracy levels comparable to traditional NWP systems, marking a significant milestone in data-driven weather prediction. However, they mostly leverage Transformer-based architectures, which often leads to high training complexity and resource demands due to the massive parameter sizes. In this study, we introduce a modernized CNN-based model for global weather forecasting that delivers competitive accuracy while significantly reducing computational requirements. To present a systematic modernization roadmap, we highlight key architectural enhancements across multiple design scales from an earlier CNN-based approach. KAI-a incorporates a scale-invariant architecture and InceptionNeXt-based blocks within a geophysically-aware design, tailored to the structure of Earth system data. Trained on the ERA5 daily dataset with 67 atmospheric variables, the model contains about 7 million parameters and completes training in just 12 hours on a single NVIDIA L40s GPU. Our evaluation shows that KAI-a matches the performance of state-of-the-art models in medium-range weather forecasting, while offering a significantly lightweight design. Furthermore, case studies on the 2018 European heatwave and the East Asian summer monsoon demonstrate KAI-a's robust skill in capturing extreme events, reinforcing its practical utility.

cs.CV↗

arXiv2025

Bridging KAN and MLP: MJKAN, a Hybrid Architecture with Both Efficiency and Expressiveness

Kolmogorov-Arnold Networks (KANs) have garnered attention for replacing fixed activation functions with learnable univariate functions, but they exhibit practical limitations, including high computational costs and performance deficits in general classification tasks. In this paper, we propose the Modulation Joint KAN (MJKAN), a novel neural network layer designed to overcome these challenges. MJKAN integrates a FiLM (Feature-wise Linear Modulation)-like mechanism with Radial Basis Function (RBF) activations, creating a hybrid architecture that combines the non-linear expressive power of KANs with the efficiency of Multilayer Perceptrons (MLPs). We empirically validated MJKAN's performance across a diverse set of benchmarks, including function regression, image classification (MNIST, CIFAR-10/100), and natural language processing (AG News, SMS Spam). The results demonstrate that MJKAN achieves superior approximation capabilities in function regression tasks, significantly outperforming MLPs, with performance improving as the number of basis functions increases. Conversely, in image and text classification, its performance was competitive with MLPs but revealed a critical dependency on the number of basis functions. We found that a smaller basis size was crucial for better generalization, highlighting that the model's capacity must be carefully tuned to the complexity of the data to prevent overfitting. In conclusion, MJKAN offers a flexible architecture that inherits the theoretical advantages of KANs while improving computational efficiency and practical viability.

cs.LG↗

arXiv2025

MambaOutRS: A Hybrid CNN-Fourier Architecture for Remote Sensing Image Classification

Recent advances in deep learning for vision tasks have seen the rise of State Space Models (SSMs) like Mamba, celebrated for their linear scalability. However, their adaptation to 2D visual data often necessitates complex modifications that may diminish efficiency. In this paper, we introduce MambaOutRS, a novel hybrid convolutional architecture for remote sensing image classification that re-evaluates the necessity of recurrent SSMs. MambaOutRS builds upon stacked Gated CNN blocks for local feature extraction and introduces a novel Fourier Filter Gate (FFG) module that operates in the frequency domain to capture global contextual information efficiently. Our architecture employs a four-stage hierarchical design and was extensively evaluated on challenging remote sensing datasets: UC Merced, AID, NWPU-RESISC45, and EuroSAT. MambaOutRS consistently achieved state-of-the-art (SOTA) performance across these benchmarks. Notably, our MambaOutRS-t variant (24.0M parameters) attained the highest F1-scores of 98.41\% on UC Merced and 95.99\% on AID, significantly outperforming existing baselines, including larger transformer models and Mamba-based architectures, despite using considerably fewer parameters. An ablation study conclusively demonstrates the critical role of the Fourier Filter Gate in enhancing the model's ability to capture global spatial patterns, leading to robust and accurate classification. These results strongly suggest that the complexities of recurrent SSMs can be effectively superseded by a judicious combination of gated convolutions for spatial mixing and frequency-based gates for spectral global context. Thus, MambaOutRS provides a compelling and efficient paradigm for developing high-performance deep learning models in remote sensing and other vision domains, particularly where computational efficiency is paramount.

cs.CV↗

arXiv2025

AtmosMJ: Revisiting Gating Mechanism for AI Weather Forecasting Beyond the Year Scale

The advent of Large Weather Models (LWMs) has marked a turning point in data-driven forecasting, with many models now outperforming traditional numerical systems in the medium range. However, achieving stable, long-range autoregressive forecasts beyond a few weeks remains a significant challenge. Prevailing state-of-the-art models that achieve year-long stability, such as SFNO and DLWP-HPX, have relied on transforming input data onto non-standard spatial domains like spherical harmonics or HEALPix meshes. This has led to the prevailing assumption that such representations are necessary to enforce physical consistency and long-term stability. This paper challenges that assumption by investigating whether comparable long-range performance can be achieved on the standard latitude-longitude grid. We introduce AtmosMJ, a deep convolutional network that operates directly on ERA5 data without any spherical remapping. The model's stability is enabled by a novel Gated Residual Fusion (GRF) mechanism, which adaptively moderates feature updates to prevent error accumulation over long recursive simulations. Our results demonstrate that AtmosMJ produces stable and physically plausible forecasts for about 500 days. In quantitative evaluations, it achieves competitive 10-day forecast accuracy against models like Pangu-Weather and GraphCast, all while requiring a remarkably low training budget of 5.7 days on a V100 GPU. Our findings suggest that efficient architectural design, rather than non-standard data representation, can be the key to unlocking stable and computationally efficient long-range weather prediction.

cs.LG↗

arXiv2025

Mj\"olnir: A Deep Learning Parametrization Framework for Global Lightning Flash Density

Recent advances in AI-based weather forecasting models, such as FourCastNet, Pangu-Weather, and GraphCast, have demonstrated the remarkable ability of deep learning to emulate complex atmospheric dynamics. Building on this momentum, we propose Mj\"olnir, a novel deep learning-based framework for global lightning flash density parameterization. Trained on ERA5 atmospheric predictors and World Wide Lightning Location Network (WWLLN) observations at a daily temporal resolution and 1 degree spatial resolution, Mj\"olnir captures the nonlinear mapping between large-scale environmental conditions and lightning activity. The model architecture is based on the InceptionNeXt backbone with SENet, and a multi-task learning strategy to simultaneously predict lightning occurrence and magnitude. Extensive evaluations yield that Mollnir accurately reproduces the global distribution, seasonal variability, and regional characteristics of lightning activity, achieving a global Pearson correlation coefficient of 0.96 for annual mean fields. These results suggest that Mj\"olnir serves not only as an effective data-driven global lightning parameterization but also as a promising AI-based scheme for next-generation Earth system models (AI-ESMs).

cs.LG↗

arXiv2024

Advancing Meteorological Forecasting: AI-based Approach to Synoptic Weather Map Analysis

As global warming increases the complexity of weather patterns; the precision of weather forecasting becomes increasingly important. Our study proposes a novel preprocessing method and convolutional autoencoder model developed to improve the interpretation of synoptic weather maps. These are critical for meteorologists seeking a thorough understanding of weather conditions. This model could recognize historical synoptic weather maps that nearly match current atmospheric conditions, marking a significant step forward in modern technology in meteorological forecasting. This comprises unsupervised learning models like VQ-VQE, as well as supervised learning models like VGG16, VGG19, Xception, InceptionV3, and ResNet50 trained on the ImageNet dataset, as well as research into newer models like EfficientNet and ConvNeXt. Our findings proved that, while these models perform well in various settings, their ability to identify comparable synoptic weather maps has certain limits. Our research, motivated by the primary goal of significantly increasing meteorologists' efficiency in labor-intensive tasks, discovered that cosine similarity is the most effective metric, as determined by a combination of quantitative and qualitative assessments to accurately identify relevant historical weather patterns. This study broadens our understanding by shifting the emphasis from numerical precision to practical application, ensuring that our model is effective in theory practical, and accessible in the complex and dynamic field of meteorology.

cs.LG↗

arXiv2024

Habaek: High-performance water segmentation through dataset expansion and inductive bias optimization

Water segmentation is critical to disaster response and water resource management. Authorities may employ high-resolution photography to monitor rivers, lakes, and reservoirs, allowing for more proactive management in agriculture, industry, and conservation. Deep learning has improved flood monitoring by allowing models like CNNs, U-Nets, and transformers to handle large volumes of satellite and aerial data. However, these models usually have significant processing requirements, limiting their usage in real-time applications. This research proposes upgrading the SegFormer model for water segmentation by data augmentation with datasets such as ADE20K and RIWA to boost generalization. We examine how inductive bias affects attention-based models and discover that SegFormer performs better on bigger datasets. To further demonstrate the function of data augmentation, Low-Rank Adaptation (LoRA) is used to lower processing complexity while preserving accuracy. We show that the suggested Habaek model outperforms current models in segmentation, with an Intersection over Union (IoU) ranging from 0.91986 to 0.94397. In terms of F1-score, recall, accuracy, and precision, Habaek performs better than rival models, indicating its potential for real-world applications. This study highlights the need to enhance structures and include datasets for effective water segmentation.

cs.CV↗

arXiv2024

Demonstrating the Efficacy of Kolmogorov-Arnold Networks in Vision Tasks

In the realm of deep learning, the Kolmogorov-Arnold Network (KAN) has emerged as a potential alternative to multilayer projections (MLPs). However, its applicability to vision tasks has not been extensively validated. In our study, we demonstrated the effectiveness of KAN for vision tasks through multiple trials on the MNIST, CIFAR10, and CIFAR100 datasets, using a training batch size of 32. Our results showed that while KAN outperformed the original MLP-Mixer on CIFAR10 and CIFAR100, it performed slightly worse than the state-of-the-art ResNet-18. These findings suggest that KAN holds significant promise for vision tasks, and further modifications could enhance its performance in future evaluations.Our contributions are threefold: first, we showcase the efficiency of KAN-based algorithms for visual tasks; second, we provide extensive empirical assessments across various vision benchmarks, comparing KAN's performance with MLP-Mixer, CNNs, and Vision Transformers (ViT); and third, we pioneer the use of natural KAN layers in visual tasks, addressing a gap in previous research. This paper lays the foundation for future studies on KANs, highlighting their potential as a reliable alternative for image classification tasks.

cs.CV↗

arXiv2024

Kolmogorov-Arnold Network for Satellite Image Classification in Remote Sensing

In this research, we propose the first approach for integrating the Kolmogorov-Arnold Network (KAN) with various pre-trained Convolutional Neural Network (CNN) models for remote sensing (RS) scene classification tasks using the EuroSAT dataset. Our novel methodology, named KCN, aims to replace traditional Multi-Layer Perceptrons (MLPs) with KAN to enhance classification performance. We employed multiple CNN-based models, including VGG16, MobileNetV2, EfficientNet, ConvNeXt, ResNet101, and Vision Transformer (ViT), and evaluated their performance when paired with KAN. Our experiments demonstrated that KAN achieved high accuracy with fewer training epochs and parameters. Specifically, ConvNeXt paired with KAN showed the best performance, achieving 94% accuracy in the first epoch, which increased to 96% and remained consistent across subsequent epochs. The results indicated that KAN and MLP both achieved similar accuracy, with KAN performing slightly better in later epochs. By utilizing the EuroSAT dataset, we provided a robust testbed to investigate whether KAN is suitable for remote sensing classification tasks. Given that KAN is a novel algorithm, there is substantial capacity for further development and optimization, suggesting that KCN offers a promising alternative for efficient image analysis in the RS field.

cs.CV↗

arXiv2024

KARINA: An Efficient Deep Learning Model for Global Weather Forecast

Deep learning-based, data-driven models are gaining prevalence in climate research, particularly for global weather prediction. However, training the global weather data at high resolution requires massive computational resources. Therefore, we present a new model named KARINA to overcome the substantial computational demands typical of this field. This model achieves forecasting accuracy comparable to higher-resolution counterparts with significantly less computational resources, requiring only 4 NVIDIA A100 GPUs and less than 12 hours of training. KARINA combines ConvNext, SENet, and Geocyclic Padding to enhance weather forecasting at a 2.5{\deg} resolution, which could filter out high-frequency noise. Geocyclic Padding preserves pixels at the lateral boundary of the input image, thereby maintaining atmospheric flow continuity in the spherical Earth. SENet dynamically improves feature response, advancing atmospheric process modeling, particularly in the vertical column process as numerous channels. In this vein, KARINA sets new benchmarks in weather forecasting accuracy, surpassing existing models like the ECMWF S2S reforecasts at a lead time of up to 7 days. Remarkably, KARINA achieved competitive performance even when compared to the recently developed models (Pangu-Weather, GraphCast, ClimaX, and FourCastNet) trained with high-resolution data having 100 times larger pixels. Conclusively, KARINA significantly advances global weather forecasting by efficiently modeling Earth's atmosphere with improved accuracy and resource efficiency.

cs.LG↗

arXiv2024

Advancing Data-driven Weather Forecasting: Time-Sliding Data Augmentation of ERA5

Modern deep learning techniques, which mimic traditional numerical weather prediction (NWP) models and are derived from global atmospheric reanalysis data, have caused a significant revolution within a few years. In this new paradigm, our research introduces a novel strategy that deviates from the common dependence on high-resolution data, which is often constrained by computational resources, and instead utilizes low-resolution data (2.5 degrees) for global weather prediction and climate data analysis. Our main focus is evaluating data-driven weather prediction (DDWP) frameworks, specifically addressing sample size adequacy, structural improvements to the model, and the ability of climate data to represent current climatic trends. By using the Adaptive Fourier Neural Operator (AFNO) model via FourCastNet and a proposed time-sliding method to inflate the dataset of the ECMWF Reanalysis v5 (ERA5), this paper improves on conventional approaches by adding more variables and a novel approach to data augmentation and processing. Our findings reveal that despite the lower resolution, the proposed approach demonstrates considerable accuracy in predicting atmospheric conditions, effectively rivaling higher-resolution models. Furthermore, the study confirms the model's proficiency in reflecting current climate trends and its potential in predicting future climatic events, underscoring its utility in climate change strategies. This research marks a pivotal step in the realm of meteorological forecasting, showcasing the feasibility of lower-resolution data in producing reliable predictions and opening avenues for more accessible and inclusive climate modeling. The insights gleaned from this study not only contribute to the advancement of climate science but also lay the groundwork for future innovations in the field.

cs.AI↗

arXiv2022

Design of a novel Korean learning application for efficient pronunciation correction

The Korean wave, which denotes the global popularity of South Korea's cultural economy, contributes to the increasing demand for the Korean language. However, as there does not exist any application for foreigners to learn Korean, this paper suggested a design of a novel Korean learning application. Speech recognition, speech-to-text, and speech-to-waveform are the three key systems in the proposed system. The Google API and the librosa library will transform the user's voice into a sentence and MFCC. The software will then display the user's phrase and answer, with mispronounced elements highlighted in red, allowing users to more easily recognize the incorrect parts of their pronunciation. Furthermore, the Siamese network might utilize those translated spectrograms to provide a similarity score, which could subsequently be used to offer feedback to the user. Despite the fact that we were unable to collect sufficient foreigner data for this research, it is notable that we presented a novel Korean pronunciation correction method for foreigners.

cs.CL↗