A connectivity-based method for detecting clumpy structures in molecular clouds

Jiang, Yongxiang; Zheng, Sheng; Jiang, Zhibo; Zeng, Shu-Guang; Chen, Z.; Zeng, Xiaojuan; Luo, Xin; Huang, Yi‐Hui Christine

doi:10.1016/j.ascom.2022.100613

Cited by 4 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The third subprocess is local region segmentation based on local gradients. In the smallest neighborhood of voxels, each signal region is segmented into local regions by ascending along the highest gradient of intensity (Jiang et al 2022). The fourth subprocess is minimum distance clustering of local regions based on connectivity.…”

Section: The Facetclumps Algorithmmentioning

confidence: 99%

“…The approach of segmenting the signal region based on local gradients has been widely applied and has been shown to be effective (Berry 2013;Jiang et al 2022). FacetClumps utilizes a similar approach to identify local regions and then merges them together.…”

Section: Local Region Segmentation Based On Gradientmentioning

confidence: 99%

“…To quantitatively assess the performance of different algorithms, we introduce the evaluation metrics (Jiang et al 2022) of recall rate (R, Equation (17)), precision rate (P, Equation (18)), F 1 score (F 1 , Equation (19)), location error (ΔX, Equation (20)), flux fluctuation (ΔFlux, Equation (21)), and regional intersection over union (IOU; Equation (22)):…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…Some of the available clump-finding algorithms include GaussClumps (Stutzki & Guesten 1990), ClumpFind (Williams et al 1994), ReinHold (Berry 2013), FellWalker (Berry 2013), Local Density Clustering (LDC; Luo et al 2022), and ConBased (Jiang et al 2022). The location of peaks is a crucial aspect of GaussClumps, ClumpFind, ReinHold, and LDC.…”

Section: Introductionmentioning

confidence: 99%

“…The location of peaks, particularly those of faint clumps, is readily impacted by noise. To identify the location of the denser central source and reduce the reliance on the peak in the detection process, FacetClumps utilizes morphology (e.g., Serra 1982;Koskinen et al 1991;Sinha & Dougherty 1992;Jiang et al 2022) to extract signal regions from the original data, and incorporates the Gaussian facet model (Haralick 1984;Brejl & Sonka 2000;Qiang & Haralick 2002;Wang et al 2007) and extremum theory of multivariate function to locate clump centers in the signal regions. A single molecular clump is relatively smooth and continuous; however, FellWalker may detect multiple distinct components as a single clump, while LDC obtains the connectivity by selecting the subpart with the largest volume from the potential clumps and discarding the smaller, discontinuous subparts.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

FacetClumps: A Facet-based Molecular Clump Detection Algorithm

Jiang,

Chen,

Zheng

et al. 2023

ApJS

View full text Add to dashboard Cite

A comprehensive understanding of molecular clumps is essential for investigating star formation. We present an algorithm for molecular clump detection, called FacetClumps. This algorithm uses a morphological approach to extract signal regions from the original data. The Gaussian facet model is employed to fit the signal regions, which enhances the resistance to noise and the stability of the algorithm in diverse overlapping areas. The introduction of the extremum determination theorem of multivariate functions offers theoretical guidance for automatically locating clump centers. To guarantee that each clump is continuous, the signal regions are segmented into local regions based on gradient, and then the local regions are clustered into the clump centers based on connectivity and minimum distance to identify the regional information of each clump. The experiments conducted with both simulated and synthetic data demonstrate that FacetClumps exhibits great recall and precision rates, small location error and flux loss, and a high consistency between the region of detected clump and that of simulated clump, and the experiments demonstrate that FacetClumps is generally stable in various environments. Notably, the recall rate of FacetClumps in the synthetic data, which comprises 13CO (J = 1−0) emission line of the MWISP within 11.°7 ≤ l ≤ 13.°4, 0.°22 ≤ b ≤ 1.°05, and 5 km s−1 ≤ v ≤ 35 km s−1 and simulated clumps, reaches 90.2%. Additionally, FacetClumps demonstrates satisfactory performance when applied to observational data.

show abstract

Section: The Facetclumps Algorithmmentioning

confidence: 99%

Section: Local Region Segmentation Based On Gradientmentioning

confidence: 99%

Section: Evaluation Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

FacetClumps: A Facet-based Molecular Clump Detection Algorithm

Jiang,

Chen,

Zheng

et al. 2023

ApJS

View full text Add to dashboard Cite

show abstract

Automatically verifying molecular clumps based on supervised learning

Long,

Zheng,

Huang

et al. 2024

New Astronomy

View full text Add to dashboard Cite

Semi-supervised deep learning for molecular clump verification

Luo,

Zheng,

Jiang

et al. 2024

A&A

View full text Add to dashboard Cite

A reliable molecular clump detection algorithm is essential for studying these clumps. Existing detection algorithms for molecular clumps still require that detected candidates be verified manually, which is impractical for large-scale data. Semi-supervised learning methods, especially those based on deep features, have the potential to accomplish the task of molecular clump verification thanks to the powerful feature extraction capability of deep networks. Our main objective is to develop an automated method for the verification of molecular clump candidates. This method utilises a 3D convolutional neural network (3D CNN) to extract features of molecular clumps and employs semi-supervised learning to train the model, with the aim being to improve its generalisation ability and data utilisation. It addresses the issue of insufficient labelled samples in traditional supervised learning and enables the model to better adapt to new, unlabelled samples, achieving high accuracy in the verification of molecular clumps. We propose SS-3D-Clump, a semi-supervised deep clustering method that jointly learns the parameters of a 3D CNN and the cluster assignments of the generated features for automatic verification of molecular clumps. SS-3D-Clump iteratively classifies the features with the Constrained-KMeans and uses these class labels as supervision to update the weights of the entire network. We used CO data from the Milky Way Imaging Scroll Painting project covering 350 square degrees in the Milky Way’s first, second, and third quadrants. The ClumpFind algorithm was applied to extract molecular clump candidates in these regions, which were subsequently verified using SS-3D-Clump. The SS-3D-Clump model, trained on a dataset comprising three different density regions, achieved an accuracy of 0.933, a recall rate of 0.955, a precision rate of 0.945, and an F1 score of 0.950 on the corresponding test dataset. These results closely align with those obtained through manual verification. Our experiments demonstrate that the SS-3D-Clump model achieves high accuracy in the automated verification of molecular clumps. It effectively captures the essential features of the molecular clumps and overcomes the challenge of limited labelled samples in supervised learning by using unlabelled samples through semi-supervised learning. This enhancement significantly improves the generalisation capability of the SS-3D-Clump model, allowing it to adapt effectively to new and unlabelled samples. Consequently, SS-3D-Clump can be integrated with any detection algorithm to create a comprehensive framework for the automated detection and verification of molecular clumps.

show abstract

A connectivity-based method for detecting clumpy structures in molecular clouds

Cited by 4 publications

References 19 publications

FacetClumps: A Facet-based Molecular Clump Detection Algorithm

FacetClumps: A Facet-based Molecular Clump Detection Algorithm

Automatically verifying molecular clumps based on supervised learning

Semi-supervised deep learning for molecular clump verification

Contact Info

Product

Resources

About