Improving Irregularly Sampled Time Series Learning with Dense Descriptors of Time

Sousa, Rafael Teixeira; Pereira, Lucas; Soares, Anderson S.

doi:10.48550/arxiv.2003.09291

Cited by 2 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This maximum period is arbitrarily defined such that it exceeds the maximum empirical last observation time t i,−1 , found among the light curves from the training set train  , by setting k T = 1.5. The flexibility to learn any arbitrary time function, 19 and not just a collection of periodic functions, as done in Vaswani et al (2017), Kazemi et al (2019), andSousa et al (2020), might be especially beneficial for nonperiodic transient events such as SNe, as there could be potentially more informative time regions in the early explosion days: earlier than and close to the SN peak, instead of periodically spaced informative zones. Thus, the TimeModAttn model might learn an adequate modulation over those SN time regions to correctly extract useful information.…”

Section: Temporal Modulation (Timefilm)mentioning

confidence: 99%

Deep Attention-based Supernovae Classification of Multiband Light Curves

Pimentel

Estévez

Förster

2022

View full text Add to dashboard Cite

In astronomical surveys, such as the Zwicky Transient Facility, supernovae (SNe) are relatively uncommon objects compared to other classes of variable events. Along with this scarcity, the processing of multiband light curves is a challenging task due to the highly irregular cadence, long time gaps, missing values, few observations, etc. These issues are particularly detrimental to the analysis of transient events: SN-like light curves. We offer three main contributions: (1) Based on temporal modulation and attention mechanisms, we propose a deep attention model (TimeModAttn) to classify multiband light curves of different SN types, avoiding photometric or hand-crafted feature computations, missing-value assumptions, and explicit imputation/interpolation methods. (2) We propose a model for the synthetic generation of SN multiband light curves based on the Supernova Parametric Model, allowing us to increase the number of samples and the diversity of cadence. Thus, the TimeModAttn model is first pretrained using synthetic light curves. Then, a fine-tuning process is performed. The TimeModAttn model outperformed other deep learning models, based on recurrent neural networks, in two scenarios: late-classification and early-classification. Also, the TimeModAttn model outperformed a Balanced Random Forest (BRF) classifier (trained with real data), increasing the balanced-F 1score from ≈.525 to ≈.596. When training the BRF with synthetic data, this model achieved a similar performance to the TimeModAttn model proposed while still maintaining extra advantages. (3) We conducted interpretability experiments. High attention scores were obtained for observations earlier than and close to the SN brightness peaks. This also correlated with an early highly variability of the learned temporal modulation.

show abstract

Section: Temporal Modulation (Timefilm)mentioning

confidence: 99%

Deep Attention-based Supernovae Classification of Multiband Light Curves

Pimentel

Estévez

Förster

2022

View full text Add to dashboard Cite

show abstract

“…The flexibility to learn any arbitrary time function 13 , and not just a collection of periodic functions, as done in (Vaswani et al 2017;Kazemi et al 2019;Sousa et al 2020), might be especially beneficial for non-periodic transient events such as SNe, as there could be potentially more informative time regions in the early explosion days: earlier than and close to the SN-peak, instead of periodically spaced informative zones. Therefore, the TimeModAttn model might learn to induce a highly expressive modulation over those SN time regions.…”

Section: Temporal Modulation (Timefilm)mentioning

confidence: 99%

Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves

Pimentel¹,

Estévez²,

Förster³

2022

Preprint

View full text Add to dashboard Cite

In astronomical surveys, such as the Zwicky Transient Facility (ZTF), supernovae (SNe) are relatively uncommon objects compared to other classes of variable events. Along with this scarcity, the processing of multi-band light-curves is a challenging task due to the highly irregular cadence, long time gaps, missing-values, low number of observations, etc. These issues are particularly detrimental for the analysis of transient events with SN-like light-curves. In this work, we offer three main contributions. First, based on temporal modulation and attention mechanisms, we propose a Deep Attention model called TimeModAttn to classify multi-band light-curves of different SN types, avoiding photometric or hand-crafted feature computations, missing-values assumptions, and explicit imputation and interpolation methods. Second, we propose a model for the synthetic generation of SN multi-band light-curves based on the Supernova Parametric Model (SPM). This allows us to increase the number of samples and the diversity of the cadence. The TimeModAttn model is first pre-trained using synthetic light-curves in a semi-supervised learning scheme. Then, a fine-tuning process is performed for domain adaptation. The proposed TimeModAttn model outperformed a Random Forest classifier, increasing the balanced-F 1 score from ≈ .525 to ≈ .596. The TimeModAttn model also outperformed other Deep Learning models, based on Recurrent Neural Networks (RNNs), in two scenarios: late-classification and early-classification. Finally, we conduct interpretability experiments. High attention scores are obtained for observations earlier than and close to the SN brightness peaks, which are supported by an early and highly expressive learned temporal modulation.

show abstract

Improving Irregularly Sampled Time Series Learning with Dense Descriptors of Time

Cited by 2 publications

References 5 publications

Deep Attention-based Supernovae Classification of Multiband Light Curves

Deep Attention-based Supernovae Classification of Multiband Light Curves

Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves

Contact Info

Product

Resources

About