Measuring Sustainability in Multi-Scale High-Performance Computing
本文通过引入一个多维度度量框架,解决多尺度高性能计算中的资源管理和可持续性问题,指导现代工作负载的部署策略。
本文通过引入一个多维度度量框架,解决多尺度高性能计算中的资源管理和可持续性问题,指导现代工作负载的部署策略。
本文提出一种基于冻结CLIP先验的自监督方法,通过解耦数据一致性更新和轻量级解码器实现Poisson逆问题的鲁棒求解。
This study addresses the severe ill-posedness of three-dimensional density reconstruction in gravity inversion, which arises from non-uniqueness, limited data coverage, and the exponential decay of field strength with depth. To tackle this challenge, the authors propose an unsupervised, depth-aware implicit neural representation that models the density volume using multiple coordinate-based neural networks, each corresponding to overlapping depth layers. The method incorporates layer-specific Fourier feature embeddings, physics-informed depth gain, and scheduled regularization, and directly optimizes against the gravity sensitivity matrix—eliminating the need for ground-truth density labels while providing structural priors that effectively mitigate depth ambiguity. Evaluated on four synthetic scenarios, the approach consistently outperforms both conventional and neural baselines in RMSE, PSNR, and SSIM metrics, yielding more compact, spatially coherent, and vertically accurate reconstructions. Field experiments further confirm its consistency with observed gravity data.
This study addresses the challenge of detecting and segmenting methane plumes in hyperspectral satellite imagery by proposing a multimodal Transformer model that integrates physical priors with deep learning. The core innovation lies in the Feature-Guided Methane Enhancement (FGME) mechanism, which injects physically interpretable methane cues into RGB representations across multiple semantic scales, enabling efficient and precise segmentation. Evaluated on the MPDataset, the proposed method substantially outperforms existing approaches, achieving improvements of 0.92 in mIoU, 0.87 in mPrecision, and 1.01 in Recall. Notably, it attains this enhanced accuracy while significantly reducing computational overhead, thereby striking a superior balance between segmentation performance and computational efficiency.
This study addresses the long-standing challenge of atmospheric compensation in long-range passive long-wave infrared (LWIR) hyperspectral imaging, which is severely degraded by atmospheric absorption, emission, and path radiance, yet has been largely overlooked due to modeling complexity. To recover true target spectra efficiently, this work proposes a lightweight ensemble deep learning framework that introduces, for the first time, an ensemble Transformer architecture to jointly estimate atmospheric transmittance, path radiance, and a shared downwelling radiance spectrum. A sparse autoencoder embedded within the framework discovers latent activation patterns aligned with geographic regions, even without explicit geolocation supervision. Evaluated on a MODTRAN-simulated dataset, the method achieves consistently low spectral distortion across all estimated atmospheric components. The code and dataset are publicly released to facilitate further research.
本文通过引入一个多维度度量框架,解决多尺度高性能计算中的资源管理和可持续性问题,指导现代工作负载的部署策略。
本文提出一种基于冻结CLIP先验的自监督方法,通过解耦数据一致性更新和轻量级解码器实现Poisson逆问题的鲁棒求解。
This study addresses the severe ill-posedness of three-dimensional density reconstruction in gravity inversion, which arises from non-uniqueness, limited data coverage, and the exponential decay of field strength with depth. To tackle this challenge, the authors propose an unsupervised, depth-aware implicit neural representation that models the density volume using multiple coordinate-based neural networks, each corresponding to overlapping depth layers. The method incorporates layer-specific Fourier feature embeddings, physics-informed depth gain, and scheduled regularization, and directly optimizes against the gravity sensitivity matrix—eliminating the need for ground-truth density labels while providing structural priors that effectively mitigate depth ambiguity. Evaluated on four synthetic scenarios, the approach consistently outperforms both conventional and neural baselines in RMSE, PSNR, and SSIM metrics, yielding more compact, spatially coherent, and vertically accurate reconstructions. Field experiments further confirm its consistency with observed gravity data.
This study addresses the challenge of detecting and segmenting methane plumes in hyperspectral satellite imagery by proposing a multimodal Transformer model that integrates physical priors with deep learning. The core innovation lies in the Feature-Guided Methane Enhancement (FGME) mechanism, which injects physically interpretable methane cues into RGB representations across multiple semantic scales, enabling efficient and precise segmentation. Evaluated on the MPDataset, the proposed method substantially outperforms existing approaches, achieving improvements of 0.92 in mIoU, 0.87 in mPrecision, and 1.01 in Recall. Notably, it attains this enhanced accuracy while significantly reducing computational overhead, thereby striking a superior balance between segmentation performance and computational efficiency.
This study addresses the long-standing challenge of atmospheric compensation in long-range passive long-wave infrared (LWIR) hyperspectral imaging, which is severely degraded by atmospheric absorption, emission, and path radiance, yet has been largely overlooked due to modeling complexity. To recover true target spectra efficiently, this work proposes a lightweight ensemble deep learning framework that introduces, for the first time, an ensemble Transformer architecture to jointly estimate atmospheric transmittance, path radiance, and a shared downwelling radiance spectrum. A sparse autoencoder embedded within the framework discovers latent activation patterns aligned with geographic regions, even without explicit geolocation supervision. Evaluated on a MODTRAN-simulated dataset, the method achieves consistently low spectral distortion across all estimated atmospheric components. The code and dataset are publicly released to facilitate further research.