arXiv subjects

Akinori Yamanaka

Publications and source records attributed to Akinori Yamanaka.

4 recordsLinked to original sources

arXiv2023

Correlation between morphological evolution of splashing drop and exerted impact force revealed by interpretation of explainable artificial intelligence

This study reveals a possible correlation between splashing morphology and the normalized impact force exerted by an impacting drop on a solid surface. This finding is obtained from a newly proposed feature extraction method and a subsequent interpretation of the classification of splashing and non-splashing drops performed by an explainable artificial intelligence (XAI) video classifier. Notably, the values of the weight matrix elements of the XAI that correspond to the extracted features are found to change with the temporal evolution of the drop morphology. We compute the rate of change of the contributions of each frame with respect to the classification value of a video as an important index to quantify the contributions of the extracted splashing and non-splashing features at different impact times to the classification of the XAI model. Remarkably, the rate computed for the extracted splashing features is found to closely match the profile of the normalized impact force, where the splashing features are most pronounced immediately after the normalized impact force reaches its peak value. This study has provided an example that clarifies the relationship between the complex morphological evolution of a splashing drop and physical parameters by interpreting the classification of an XAI video classifier.

physics.flu-dyn↗

arXiv2022

Features of a Splashing Drop on a Solid Surface and the Temporal Evolution extracted through Image-Sequence Classification using an Interpretable Feedforward Neural Network

This paper reports the features of a splashing drop on a solid surface and the temporal evolution, which are extracted through image-sequence classification using a highly interpretable feedforward neural network (FNN) with zero hidden layer. The image sequences used for training-validation and testing of the FNN show the early-stage deformation of milli-sized ethanol drops that impact a hydrophilic glass substrate with the Weber number ranges between 31-474 (splashing threshold about 173). Specific videographing conditions and digital image processing are performed to ensure the high similarity among the image sequences. As a result, the trained FNNs achieved a test accuracy higher than 96%. Remarkably, the feature extraction shows that the trained FNN identifies the temporal evolution of the ejected secondary droplets around the aerodynamically lifted lamella and the relatively high contour of the main body as the features of a splashing drop, while the relatively short and thick lamella as the feature of a nonsplashing drop. The physical interpretation for these features and their respective temporal evolution have been identified except for the difference in contour height of the main body between splashing and nonsplashing drops. The observation reported in this study is important for the development of a data-driven simulation for modeling the deformation of a splashing drop during the impact on a solid surface.

physics.flu-dyn↗

arXiv2022

Image features of a splashing drop on a solid surface extracted using a feedforward neural network

This article reports nonintuitive characteristic of a splashing drop on a solid surface discovered through extracting image features using a feedforward neural network (FNN). Ethanol of area-equivalent radius about 1.29 mm was dropped from impact heights ranging from 4 cm to 60 cm (splashing threshold 20 cm) and impacted on a hydrophilic surface. The images captured when half of the drop impacted the surface were labeled according to their outcome, splashing or nonsplashing, and were used to train an FNN. A classification accuracy higher than 96% was achieved. To extract the image features identified by the FNN for classification, the weight matrix of the trained FNN for identifying splashing drops was visualized. Remarkably, the visualization showed that the trained FNN identified the contour height of the main body of the impacting drop as an important characteristic differentiating between splashing and nonsplashing drops, which has not been reported in previous studies. This feature was found throughout the impact, even when one and three-quarters of the drop impacted the surface. To confirm the importance of this image feature, the FNN was retrained to classify using only the main body without checking for the presence of ejected secondary droplets. The accuracy was still higher than 82%, confirming that the contour height is an important feature distinguishing splashing from nonsplashing drops. Several aspects of drop impact are analyzed and discussed with the aim of identifying the possible mechanism underlying the difference in contour height between splashing and nonsplashing drops.

physics.flu-dyn↗

arXiv2016

Data assimilation for massive autonomous systems based on second-order adjoint method

Data assimilation (DA) is a fundamental computational technique that integrates numerical simulation models and observation data on the basis of Bayesian statistics. Originally developed for meteorology, especially weather forecasting, DA is now an accepted technique in various scientific fields. One key issue that remains controversial is the implementation of DA in massive simulation models under limited computation time and resources. In this paper, we propose an adjoint-based DA method for massive autonomous models that produces optimum estimates and their uncertainties within practical computation time and resource constraints. The uncertainties are given as several diagonal components of an inverse Hessian matrix, which is the covariance matrix of a normal distribution that approximates the target posterior probability density function in the neighborhood of the optimum. Conventional algorithms for deriving the inverse Hessian matrix require $O(CN^2+N^3)$ computations and $O(N^2)$ memory, where $N$ is the number of degrees of freedom of a given autonomous system and $C$ is the number of computations needed to simulate time series of suitable length. The proposed method using a second-order adjoint method allows us to directly evaluate the diagonal components of the inverse Hessian matrix without computing all of its components. This drastically reduces the number of computations to $O(C)$ and the amount of memory to $O(N)$ for each diagonal component. The proposed method is validated through numerical tests using a massive two-dimensional Kobayashi's phase-field model. We confirm that the proposed method correctly reproduces the parameter and initial state assumed in advance, and successfully evaluates the uncertainty of the parameter. Such information regarding uncertainty is valuable, as it can be used to optimize the design of experiments.

stat.ME↗