BEGIN:VCALENDAR VERSION:2.0 PRODID:-//linuxsoftware.nz//NONSGML Joyous v1.4//EN BEGIN:VEVENT SUMMARY:Descriptive and Predictive Modeling of Chaos in Cold Atom Physics using Explainable Deep Learning DTSTART:20251204T110000Z DTEND:20251204T130000Z DTSTAMP:20260610T074333Z UID:1e497eec-6db2-4a3c-b719-757b3d68f3e4 SEQUENCE:2 CREATED:20251128T094616Z DESCRIPTION:Ultracold atom clouds display intricate dynamics that can appe ar chaotic and lack a comprehensive explanatory framework. This dissertati on investigates photon bubble turbulence in a 85Rb atom cloud confined in a magneto-optical trap\, using recent advances in artificial intelligence to move beyond the limitations of classical modeling. Reduced-order method s and sparse regression provide interpretability but fail to capture long- term dynamics or generalize across regimes. To overcome these issues\, dee p learning models were developed\, with a focus on convolutional autoencod ers for reconstructing and analyzing atom cloud images. Results showed tha t these architectures consistently outperformed classical baselines\, even in lowdimensional latent spaces\, demonstrating the ability of convolutio nal representations to extract physically meaningful features. Latent spac e analysis revealed that the apparently chaotic turbulence is underpinned by compact structures\, suggesting a simple order to chaos. Classification experiments showed that detuning values\, determined by laser frequencies in the trap\, can be reliably inferred from images\, exposing discriminat ive features tied to light–atom interactions. Explainability was introdu ced through Grad-CAM\, linking classification decisions to density structu res in the clouds. The findings confirmed two dynamical regimes\, stable a nd turbulent\, separated by a phase transition\, with further evidence of a transitional regime near resonance. Overall\, explainable deep learning emerges as a powerful framework for predictive and descriptive modeling of ultracold atom systems\, while also deepening our understanding of turbul ence\, phase transitions\, and light–atom coupling. LAST-MODIFIED:20251128T094624Z LOCATION:Sala V1.06 Pavilhão de Civil URL:http://df.vps.tecnico.ulisboa.pt/pt/eventos/descriptive-and-predictive -modeling-of-chaos-in-cold-atom-physics-using-explainable-deep-learning/ X-ALT-DESC;FMTTYPE=text/html:

Ultracold atom clou ds display intricate dynamics that can appear chaotic and lack a comprehen sive explanatory framework. This dissertation investigates photon bubble t urbulence in a 85Rb atom cloud confined in a magneto-optical trap\, using recent advances in artificial intelligence to move beyond the limitations of classical modeling. Reduced-order methods and sparse regression provide interpretability but fail to capture long-term dynamics or generalize acr oss regimes.

To overcome these issues\, deep learning models wer e developed\, with a focus on convolutional autoencoders for reconstructin g and analyzing atom cloud images. Results showed that these architectures consistently outperformed classical baselines\, even in lowdimensional la tent spaces\, demonstrating the ability of convolutional representations t o extract physically meaningful features. Latent space analysis revealed t hat the apparently chaotic turbulence is underpinned by compact structures \, suggesting a simple order to chaos.

Classification experiment s showed that detuning values\, determined by laser frequencies in the tra p\, can be reliably inferred from images\, exposing discriminative feature s tied to light–atom interactions. Explainability was introduced through Grad-CAM\, linking classification decisions to density structures in the clouds. The findings confirmed two dynamical regimes\, stable and turbulen t\, separated by a phase transition\, with further evidence of a transitio nal regime near resonance. Overall\, explainable deep learning emerges as a powerful framework for predictive and descriptive modeling of ultracold atom systems\, while also deepening our understanding of turbulence\, phas e transitions\, and light–atom coupling.

END:VEVENT END:VCALENDAR