Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287149035> ?p ?o ?g. }
- W4287149035 endingPage "A176" @default.
- W4287149035 startingPage "A176" @default.
- W4287149035 abstract "Context. Determining properties of dust that formed in and around supernovae from observations remains challenging. This may be due to either incomplete coverage of data in wavelength or time, but also due to often inconspicuous signatures of dust in the observed data. Aims. Here we address this challenge using modern machine learning methods to determine the amount and temperature of dust as well as its composition from a large set of simulated data. We aim to quantify if such methods are suitable to infer quantities and properties of dust from future observations of supernovae. Methods. We developed a neural network consisting of eight fully connected layers and an output layer with specified activation functions that allowed us to predict the dust mass, temperature, and composition as well as their respective uncertainties for each single supernova of a large set of simulated supernova spectral energy distributions (SEDs). We produced the large set of supernova SEDs for a wide range of different supernovae and dust properties using the advanced, fully three-dimensional radiative transfer code MOCASSIN. We then convolved each SED with the entire suite of James Webb Space Telescope (JWST) bandpass filters to synthesise a photometric data set. We split this data set into three subsets which were used to train, validate, and test the neural network. To find out how accurately the neural network can predict the dust mass, temperature, and composition from the simulated data, we considered three different scenarios. First, we adopted a uniform distance of ~0.43 Mpc for all simulated SEDs. Next we uniformly distributed all simulated SEDs within a volume of 0.43–65 Mpc and, finally, we artificially added random noise corresponding to a photometric uncertainty of 0.1 mag. Lastly, we conducted a feature importance analysis via SHapley Additive explanations (SHAP) to find the minimum set of JWST bandpass filters required to predict the selected dust quantities with an accuracy that is comparable to standard methods in the literature. Results . We find that our neural network performs best for the scenario in which all SEDs are at the same distance and for a minimum subset of seven JWST bandpass filters within a wavelength range 3−25 µm. This results in rather small root-mean-square errors (RMSEs) of ~0.08 dex and ~42 K for the most reliable predicted dust masses and temperatures, respectively. For the scenario in which SEDs are distributed out to 65 Mpc and contain synthetic noise, the most reliable predicted dust masses and temperatures achieve an RMSE of ~0.12 dex and ~38 K, respectively. Thus, in all scenarios, both predicted dust quantities have smaller predicted uncertainties compared to those in the literature achieved with common SED fitting methods of actual observations of supernovae. Moreover, our neural network can well distinguish between the different dust species included in our work, reaching a classification accuracy of up to 95% for carbon and 99% for silicate dust. Conclusions. Although we trained, validated, and tested our neural network entirely on simulated SEDs, our analysis shows that a suite of JWST bandpass filters containing NIRCam F 070 W , F 140 M , F 356 W and F 480 M as well as MIRI F 560 W , F 770 W , F 1000 W , F 1130 W , F 1500 W , and F 1800 W filters are likely the most important filters needed to derive the quantities and determine the properties of dust that formed in and around supernovae from future observations. We tested this on selected optical to infrared data of SN 1987A at 615 days past explosion and find good agreement with dust masses and temperatures inferred with standard fitting methods in the literature." @default.
- W4287149035 created "2022-07-25" @default.
- W4287149035 creator A5002819401 @default.
- W4287149035 creator A5021226554 @default.
- W4287149035 creator A5055730784 @default.
- W4287149035 creator A5071823183 @default.
- W4287149035 date "2022-10-01" @default.
- W4287149035 modified "2023-10-01" @default.
- W4287149035 title "Inferring properties of dust in supernovae with neural networks" @default.
- W4287149035 cites W1498436455 @default.
- W4287149035 cites W1806891645 @default.
- W4287149035 cites W1933086658 @default.
- W4287149035 cites W1965372241 @default.
- W4287149035 cites W1968718345 @default.
- W4287149035 cites W1979253784 @default.
- W4287149035 cites W1986351423 @default.
- W4287149035 cites W1992526765 @default.
- W4287149035 cites W1993845407 @default.
- W4287149035 cites W2006869439 @default.
- W4287149035 cites W2007993160 @default.
- W4287149035 cites W2009767465 @default.
- W4287149035 cites W2013064166 @default.
- W4287149035 cites W2031615933 @default.
- W4287149035 cites W2031826267 @default.
- W4287149035 cites W2034535798 @default.
- W4287149035 cites W2042413420 @default.
- W4287149035 cites W2043858372 @default.
- W4287149035 cites W2045491779 @default.
- W4287149035 cites W2050965589 @default.
- W4287149035 cites W2067898484 @default.
- W4287149035 cites W2075852822 @default.
- W4287149035 cites W2079135578 @default.
- W4287149035 cites W2092748333 @default.
- W4287149035 cites W2106642026 @default.
- W4287149035 cites W2107451664 @default.
- W4287149035 cites W2110177531 @default.
- W4287149035 cites W2111406701 @default.
- W4287149035 cites W2116446904 @default.
- W4287149035 cites W2155814217 @default.
- W4287149035 cites W2157113027 @default.
- W4287149035 cites W2158698691 @default.
- W4287149035 cites W2166261940 @default.
- W4287149035 cites W2227426508 @default.
- W4287149035 cites W2322594199 @default.
- W4287149035 cites W2462504425 @default.
- W4287149035 cites W2735500652 @default.
- W4287149035 cites W2768318238 @default.
- W4287149035 cites W2774894185 @default.
- W4287149035 cites W2784207801 @default.
- W4287149035 cites W2791406578 @default.
- W4287149035 cites W2896279780 @default.
- W4287149035 cites W2898676835 @default.
- W4287149035 cites W2948931498 @default.
- W4287149035 cites W2950131746 @default.
- W4287149035 cites W2999154694 @default.
- W4287149035 cites W3014421555 @default.
- W4287149035 cites W3022668787 @default.
- W4287149035 cites W3033295715 @default.
- W4287149035 cites W3098111710 @default.
- W4287149035 cites W3098334804 @default.
- W4287149035 cites W3100461390 @default.
- W4287149035 cites W3100472613 @default.
- W4287149035 cites W3100854496 @default.
- W4287149035 cites W3101362155 @default.
- W4287149035 cites W3101818064 @default.
- W4287149035 cites W3102421726 @default.
- W4287149035 cites W3104062568 @default.
- W4287149035 cites W3105313451 @default.
- W4287149035 cites W3123596771 @default.
- W4287149035 cites W3131783066 @default.
- W4287149035 cites W3136077771 @default.
- W4287149035 cites W4237044253 @default.
- W4287149035 cites W4238404964 @default.
- W4287149035 cites W4297949998 @default.
- W4287149035 doi "https://doi.org/10.1051/0004-6361/202243078" @default.
- W4287149035 hasPublicationYear "2022" @default.
- W4287149035 type Work @default.
- W4287149035 citedByCount "1" @default.
- W4287149035 countsByYear W42871490352023 @default.
- W4287149035 crossrefType "journal-article" @default.
- W4287149035 hasAuthorship W4287149035A5002819401 @default.
- W4287149035 hasAuthorship W4287149035A5021226554 @default.
- W4287149035 hasAuthorship W4287149035A5055730784 @default.
- W4287149035 hasAuthorship W4287149035A5071823183 @default.
- W4287149035 hasBestOaLocation W42871490351 @default.
- W4287149035 hasConcept C120665830 @default.
- W4287149035 hasConcept C121332964 @default.
- W4287149035 hasConcept C127592171 @default.
- W4287149035 hasConcept C151730666 @default.
- W4287149035 hasConcept C154945302 @default.
- W4287149035 hasConcept C159985019 @default.
- W4287149035 hasConcept C192562407 @default.
- W4287149035 hasConcept C204323151 @default.
- W4287149035 hasConcept C2779343474 @default.
- W4287149035 hasConcept C41008148 @default.
- W4287149035 hasConcept C44870925 @default.
- W4287149035 hasConcept C50644808 @default.
- W4287149035 hasConcept C58489278 @default.