Consistent Mapping Research Articles

Updated Radiative Transfer Model for Titan in the Near-infrared Wavelength Range: Validation against Huygens Atmospheric and Surface Measurements and Application to the Cassini/VIMS Observations of the Dragonfly Landing Area

We present an analysis of Titan data acquired by the Cassini Visual and Infrared Mapping Spectrometer (VIMS) at the landing site of the Dragonfly mission, using a new version of our radiative transfer model for Titan, with significant updates for the spectroscopic parameters of atmospheric gases and photochemical aerosols. Our updated radiative transfer model is validated against the in situ spectroscopic measurements of the Huygens probe during its descent and once landed. We confirm that aerosols with a fractal dimension of 2.3–2.4 provide the best fit to the observations. We apply our radiative transfer model to four VIMS data cubes over the Selk crater region including the Dragonfly landing and exploration areas, further validating our model by producing consistent aerosol population and surface albedo maps. These infrared albedo maps, further corrected from the photometry, enable us to study the Selk crater region in terms of surface composition, landscape formation, and evolution. Our results suggest that the Selk crater is in an intermediate state of degradation and that the mountainous terrains of the area (including the crater rim and ejecta) are likely to be dominated by fine grains of tholin-like sediment. This organic sediment would be transported to the lowlands (crater floor and surrounding plains), possibly with water ice particles, by rivers, and further deposited and processed to form the sand particles that feed the neighboring dune fields. These results provide information for the operational and scientific preparation of the Dragonfly mission, paving the way for future exploration of Titan’s surface composition and geology.

Efficient joint object matching via linear programming

Joint object matching, also known as multi-image matching, namely, the problem of finding consistent partial maps among all pairs of objects within a collection, is a crucial task in many areas of computer vision. This problem subsumes bipartite graph matching and graph partitioning as special cases and is NP-hard, in general. We develop scalable linear programming (LP) relaxations with theoretical performance guarantees for joint object matching. We start by proposing a new characterization of consistent partial maps; this in turn enables us to formulate joint object matching as an integer linear programming (ILP) problem. To construct strong LP relaxations, we study the facial structure of the convex hull of the feasible region of this ILP, which we refer to as the joint matching polytope. We present an exponential family of facet-defining inequalities that can be separated in strongly polynomial time, hence obtaining a partial characterization of the joint matching polytope that is both tight and cheap to compute. To analyze the theoretical performance of the proposed LP relaxations, we focus on permutation group synchronization, an important special case of joint object matching. We show that under the random corruption model for the input maps, a simple LP relaxation, that is, an LP containing only a very small fraction of the proposed facet-defining inequalities, recovers the ground truth with high probability if the corruption level is below 40%. Finally, via a preliminary computational study on synthetic data, we show that the proposed LP relaxations outperform a popular SDP relaxation both in terms of recovery and tightness.

Continuous mapping of aboveground biomass using Landsat time series

Aboveground biomass (AGB) is an essential variable in the study of the carbon cycle, and remote sensing provides the only viable means for mapping and monitoring biomass at large scales in time and space. Still, inconsistencies in biomass estimates are large which necessitates methods to achieve consistent mapping of biomass over time and space. In this study, we combine Lidar-derived biomass-estimates from GLAS measurements, time series analysis of 20 years of Landsat data, and machine learning algorithms to map biomass for a study area in the Amazon basin. The results show that we are able to map AGB consistently over space and time at annual intervals between 1999 and 2019, with a root-mean-square error (RMSE) of 64 to 92 Mg AGB ha−1 (depending on the evaluation methodology used) for the best performing models, with AGB estimates ranging between 0 to 600 Mg AGB ha−1. Models run with the Extreme gradient boosting (XGBoost) resulted in the lowest errors. The presented methodological approach makes it possible to map biomass over time in large areas with wide biomass ranges, and without saturation below 400 Mg AGB ha−1.

VASA: an exploratory visualization tool for mapping spatio-temporal structure of mobility – a COVID-19 case study

ABSTRACT Exploratory data analysis tools designed to measure global and local spatial autocorrelation (e.g. Moran’s I statistic) have become standard in modern GIS software. However, there has been little development in amending these tools for visualization and analysis of patterns captured in spatio-temporal data. We design and implement an exploratory mapping tool, VASA (Visual Analysis for Spatial Association), that streamlines analytical pipelines in assessing spatio-temporal structure of data and enables enhanced visual display of the patterns captured in data. Specifically, VASA applies a set of cartographic visual variables to map local measures of spatial autocorrelation and helps delineate micro and macro trends in space-time processes. Two visual displays are presented: recency and consistency map and line-scatter plots. The former combines spatial and temporal data view of local clusters, while the latter drills down on the temporal trends of the phenomena. As a case study, we demonstrate the usability of VASA for the investigation of mobility patterns in response to the COVID-19 pandemic throughout 2020 in the United States. Using daily county-level and grid-level mobility metrics obtained from three different sources (SafeGraph, Cuebiq, and Mapbox), we demonstrate cartographic functionality of VASA for a swift exploratory analysis and comparison of mobility trends at different regional scales.

Multitemporal greenhouse mapping for high-resolution remote sensing imagery based on an improved YOLOX

Plastic greenhouses (PGs), as safeguard agricultural facilities, have changed the cultivation structure of agriculture, to a certain extent, and can seriously impact the environment. Exploring the temporal characteristics of greenhouses in terms of quantity and area is significant for sustainable agricultural development and environmental protection. Pixel or object-based large-scale greenhouse mapping has difficulty meeting the demand for the simultaneous extraction of greenhouse quantity and area. Multibranch task model can provide the number and area information of greenhouse. However, there are various labeling methods and model between different branches, which lead to the deviation between quantity and area results. This paper proposes a model that is based on improved you only look once X (YOLOX) and kullback–leibler divergence (KLD), called YOLOX and KLD plus (YXLD + ), to obtain spatiotemporally consistent greenhouse mapping. The new model still has stable performance in dense scenes, with a 5.7 % improvement in average precision compared to BBAVectors. Finally, a multitemporal greenhouse map of Zhoukou City was obtained using imagery provided by Google Earth (GE). Overall, the distribution of greenhouses in Zhoukou City remained stable between 2012 and 2017. However, the number and area of greenhouses in local areas has increased rapidly in the past five years, with the number of greenhouses increasing by 47.08 % and the area expanding by 41.38 %. Greenhouses' distribution and changing characteristics concentrate on the gently sloping areas from the northwest to the southeast. These results provide an objective perspective on the development of the local agricultural cultivation structure, which is of significant importance for the promotion of agricultural modernization.

Mapping Land Use/Land Cover Changes and Forest Disturbances in Vietnam Using a Landsat Temporal Segmentation Algorithm

Accurately mapping land use/land cover changes (LULCC) and forest disturbances provides valuable information for understanding the influence of anthropogenic activities on the environment at regional and global scales. Many approaches using satellite remote sensing data have been proposed for characterizing these long-term changes. However, a spatially and temporally consistent mapping of both LULCC and forest disturbances at medium spatial resolution is still limited despite their critical contributions to the carbon cycle. In this study, we examined the applicability of Landsat time series temporal segmentation and random forest classifiers to mapping LULCC and forest disturbances in Vietnam. We used the LandTrendr temporal segmentation algorithm to derive key features of land use/land cover transitions and forest disturbances from annual Landsat time series data. We developed separate random forest models for classifying land use/land cover and detecting forest disturbances at each segment and then derived LULCC and forest disturbances that coincided with each other during the period of 1988–2019. The results showed that both LULCC classification and forest disturbance detection achieved low accuracy in several classes (e.g., producer’s and user’s accuracies of 23.7% and 78.8%, respectively, for forest disturbance class); however, the level of accuracy was comparable to that of existing datasets using the same reference samples in the study area. We found relatively high confusion between several land use/land cover classes (e.g., grass/shrub, forest, and cropland) that can explain the lower overall accuracies of 67.6% and 68.4% in 1988 and 2019, respectively. The mapping of forest disturbances and LULCC suggested that most forest disturbances were followed by forest recovery, not by transitions to other land use/land cover classes. The landscape complexity and ephemeral forest disturbances contributed to the lower classification and detection accuracies in this study area. Nevertheless, temporal segmentation and derived features from LandTrendr were useful for the consistent mapping of LULCC and forest disturbances. We recommend that future studies focus on improving the accuracy of forest disturbance detection, especially in areas with subtle landscape changes, as well as land use/land cover classification in ambiguous and complex landscapes. Using more training samples and effective variables would potentially improve the classification and detection accuracies.

MVIL-Fusion: Monocular Visual-Inertial-LiDAR Simultaneous Localization and Mapping in Challenging Environments

We propose mVIL-Fusion, a three-level multisensor fusion system that is able to achieve robust state estimation and globally consistent mapping in perceptually degraded environments. First, LiDAR depth-assisted visual-inertial odometry (VIO) with LiDAR odometry (LO) synchronous prediction and distortion correction functions is proposed as the frontend of our system. Second, a novel double-sliding-window-based optimization of midend joints of LiDAR scan-to-scan translation constraints (VIO status detection function) and scan-to-map rotation constraints (local mapping function) is used to enhance the accuracy and robustness of the state estimation. In the backend, loop closures of local-map-based keyframes are identified with altitude verification, and the global map is generated by incremental smoothing of a pose-only factor graph with altitude prior. The performance of our system is verified on both a public dataset and several self-collected sequences in challenging environments. To benefit the robotics community, our implementation is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Stan994265/mVIL-Fusion</uri> .

Hybrid metric-feature mapping based on camera and Lidar sensor fusion

Mapping the surroundings is a challenging task required for mobile robot. Fusion of heterogeneous sensors measurement has gradually been the main focus of robot perception. In this work, the Lidar and camera measurement is fused to obtain robust motion estimation and construct hybrid metric-feature map. By coupling visual information, the powerful tracking ability of visual features is heuristically applied to support the scan matching. With the estimation of Lidar odometry, the camera motion in complicated scene can be guaranteed. Meanwhile, the hybrid map is divided into submaps to improve the mapping efficiency, and each submap is composed of a grid-based metric submap and a group of visual features. Then a multi-stage loop closure strategy is applied to determine the loop candidate. Besides, multi-layer optimization including local bundle adjustment and pose graph optimization is performed to obtain global consistent map. The effectiveness of the proposed method is verified in different scenarios.

Level-Aware Consistent Multilevel Map Translation From Satellite Imagery

With the rapid development of remote sensing technology, the quality of satellite imagery (SI) is getting higher, which contains rich cartographic information that can be translated into maps. However, existing methods either only focus on generating single-level map or do not fully consider the challenges of multilevel translation from satellite imageries, i.e., the large domain gap, level-dependent content differences, and main content consistency. In this article, we propose a novel level-aware fusion network for the SI-based multilevel map generation (MLMG) task. It aims to tackle these three challenges. To deal with the large domain gap, we propose to generate maps in a coarse-to-fine way. To well-handle the level-dependent content differences, we design a level classifier to explore different levels of the map. Besides, we use a map element extractor to extract the major geographic element features from satellite imageries, which is helpful to keep the main content consistency. Next, we design a multilevel fusion generator to generate a consistent multilevel map from the multilevel preliminary map, which further ensures the main content consistency. In addition, we collect a high-quality multilevel dataset for SI-based MLMG. Experimental results show that the proposed method can provide substantial improvements over the state-of-the-art alternatives in terms of both objective metric and visual quality.

The Relationship Between Music-Related Types of Synesthesia and Mental Imagery in Synesthete Musicians

Synesthesia is a perceptual and conceptual phenomenon that has been linked to a heightened capacity for mental imagery. However, our understanding of music-related types of synesthesia and mental imagery is still in its infancy. This study therefore aims to examine the relationship between music-related types of synesthesia and mental imagery in a sample of synesthete musicians. Four forms of data collection were employed: an online survey, a synesthesia test battery, an absolute pitch test, and a semi-structured interview. This article focuses on results obtained in response to open-ended questions relating to synesthete musicians’ mental imagery. An analysis of the interview data revealed heightened vividness of auditory imagery (AI), including the ability to control the speed, dynamics, and intensity of the imagery. A bidirectional analysis of the functional relationship between AI and synesthesia ascertained that multimodal mental imagery (MMI) could be triggered by AI, thus bypassing the need for sensory stimulation. Furthermore, cases of complex visual imagery (CVI) were confirmed to meet the synesthetic criteria of being automatic and involuntary, as well as being consistent and stable mappings between specific musical stimuli and CVI. These findings are noteworthy as they call into question the general assumption that synesthetic percepts are generic and simple in nature. Together, these findings contribute to our understanding of music-related types of synesthesia and mental imagery, challenge contemporary understanding of certain categorical aspects of music-related synesthetic percepts, and provide us with a deeper understanding of the nature of cross-modal associations in general.

A Robust Light-Weight Fused-Feature Encoder-Decoder Model for Monocular Facial Depth Estimation From Single Images Trained on Synthetic Data

Due to the real-time acquisition and reasonable cost of consumer cameras, monocular depth maps have been employed in a variety of visual applications. Regarding ongoing research in depth estimation, they continue to suffer from low accuracy and enormous sensor noise. To improve the prediction of depth maps, this paper proposed a lightweight neural facial depth estimation model based on single image frames. Following a basic encoder-decoder network design, the features are extracted by initializing the encoder with a high-performance pre-trained network and reconstructing high-quality facial depth maps with a simple decoder. The model can employ pixel representations and recover full details in terms of facial features and boundaries by employing a feature fusion module. When tested and evaluated across four public facial depth datasets, the suggested network provides more reliable and state-of-the-art results, with significantly less computational complexity and a reduced number of parameters. The training procedure is primarily based on the use of synthetic human facial images, which provide a consistent ground truth depth map, and the employment of an appropriate loss function leads to higher performance. Numerous experiments have been performed to validate and demonstrate the usefulness of the proposed approach. Finally, the model performs better than existing comparative facial depth networks in terms of generalization ability and robustness across different test datasets, setting a new baseline method for facial depth maps.

The Systems Approach in Soil Science and Landscape Science

The article describes the current state of the systems approach in two closely related scientific disciplines - soil science and landscape science. It is shown that, despite the widespread recognition of the need to apply the systems approach to solving topical theoretical and practical problems in these disciplines, it remains unrealized. This is manifested in the prevailing view of soils as systems rather than as elements of higher-order systems, the mixing of the basic landscape elements with their properties, the recognition of landscape systems and elements as spatially heterogeneous formations, the different understanding of emergent properties, structure, hierarchy of soil and landscape systems, and, as a result, in the absence of their unified system definitions, basic classification systems, consistent multiscale global maps, and, finally, a hierarchical decision-making system for sustainable management, protection and assessment of soils and landscapes. It is shown that such a situation is largely due to the conceptual-terminological confusion around the systems approach in philosophy. At the end of the article, the authors share their own experience in applying the systems approach in soil science and landscape science.

Research on Multi-Sensor Fusion SLAM Algorithm Based on Improved Gmapping

Simultaneous Localization and Mapping (SLAM) is the core technology of the intelligent robot system, and it is also the basis for its autonomous movement. In recent years, it has been found that SLAM using a single sensor has certain limitations, such as Inertial Measurement Unit (IMU) noise and serious drift, and 2D radar can only detect environmental information on the same horizontal plane. In this regard, this paper constructs a multi-sensor back-end fusion SLAM algorithm that combines vision, laser, encoder and IMU information. Experiments have proved that compared with using a single sensor, the application of a multi-sensor fusion system makes the edges of the constructed map clearer and the noise reduced. Aiming at the problem of increased calculation caused by particle degradation and too many particles, this paper improves the Gmappping algorithm, and uses the combination of selective resampling and Kullback-Leibler Distance (KLD) sampling to complete resampling. It has been proved by experiments that compared with the original algorithm of Gmapping, the application of the improved algorithm increases the particle convergence speed by 39.85% in the process of indoor mapping. Aiming at the problems that the traditional loop detection algorithm is easily affected by environmental factors, resulting in low detection accuracy, and the loop detection algorithm based on deep convolutional neural network has a large amount of calculation and takes a long time to detect. The main research of this paper is to apply a deep learning-based loop detection algorithm on the multi-sensor fusion framework, and use the combination of high-dimensional and low-dimensional features of the image for loop detection. This paper uses different algorithms to conduct comparative experiments on the dataset CityCentre. The experimental results show that compared with the traditional algorithms Bag of Words (BoW), AlexNet algorithm, VGG19 algorithm, and ResNet32 algorithm, the accuracy of the algorithm proposed in this paper has increased by 31.26%, 14.21%, 3.05%, and 1.56%, respectively. In addition, the comparison experiment results of SLAM mapping with the original Real-Time Appearance-Based Mapping (RTAB-MAP) algorithm prove that the loop closure detection algorithm based on deep learning proposed in this paper can enable the system to better build a globally consistent map, including more environmental information.

UPRLIMET: UPstream Regional LiDAR Model for Extent of Trout in stream networks

Predicting the edges of species distributions is fundamental for species conservation, ecosystem services, and management decisions. In North America, the location of the upstream limit of fish in forested streams receives special attention, because fish-bearing portions of streams have more protections during forest management activities than fishless portions. We present a novel model development and evaluation framework, wherein we compare 26 models to predict upper distribution limits of trout in streams. The models used machine learning, logistic regression, and a sophisticated nested spatial cross-validation routine to evaluate predictive performance while accounting for spatial autocorrelation. The model resulting in the best predictive performance, termed UPstream Regional LiDAR Model for Extent of Trout (UPRLIMET), is a two-stage model that uses a logistic regression algorithm calibrated to observations of Coastal Cutthroat Trout (Oncorhynchus clarkii clarkii) occurrence and variables representing hydro-topographic characteristics of the landscape. We predict trout presence along reaches throughout a stream network, and include a stopping rule to identify a discrete upper limit point above which all stream reaches are classified as fishless. Although there is no simple explanation for the upper distribution limit identified in UPRLIMET, four factors, including upstream channel length above the point of uppermost fish, drainage area, slope, and elevation, had highest importance. Across our study region of western Oregon, we found that more of the fish-bearing network is on private lands than on state, US Bureau of Land Mangement (BLM), or USDA Forest Service (USFS) lands, highlighting the importance of using spatially consistent maps across a region and working across land ownerships. Our research underscores the value of using occurrence data to develop simple, but powerful, prediction tools to capture complex ecological processes that contribute to distribution limits of species.

SUREHYP: An Open Source Python Package for Preprocessing Hyperion Radiance Data and Retrieving Surface Reflectance

Surface reflectance is an essential product from remote sensing Earth observations critical for a wide variety of applications, including consistent land cover mapping and change, and estimation of vegetation attributes. From 2000 to 2017 the Earth Observing-1 Hyperion instrument acquired the first satellite based hyperspectral image archive from space resulting in over 83,138 publicly available images. Hyperion imagery however requires significant preprocessing to derive surface reflectance. SUREHYP is a Python package designed to process batches of Hyperion images, bringing together a number of published algorithms and methods to correct at sensor radiance and derive surface reflectance. In this paper, we present the SUREHYP workflow and demonstrate its application on Hyperion imagery. Results indicate SUREHYP produces flat terrain surface reflectance results comparable to commercially available software, with reflectance values for the whole spectral range almost entirely within 10% of the software's over a reference target, yet it is publicly available and open source, allowing the exploitation of this valuable hyperspectral archive on a global scale.

Mapping brain functional and structural abnormities in autism spectrum disorder: moving toward precision treatment.

Autism spectrum disorder (ASD) is a formidable challenge for psychiatry and neuroscience because of its high prevalence, lifelong nature, complexity, and substantial heterogeneity. A major goal of neuroimaging studies of ASD is to understand the neurobiological underpinnings of this disorder from multi-dimensional and multi-level perspectives, by investigating how brain anatomy, function, and connectivity are altered in ASD, and how they vary across the population. However, ongoing debate exists within those studies, and neuroimaging findings in ASD are often contradictory. Over the past decade, we have dedicated to delineate a comprehensive and consistent mapping of the abnormal structure and function of the autistic brain, and this review synthesizes the findings across our studies reaching a consensus that the "social brain" are the most affected regions in the autistic brain at different levels and modalities. We suggest that the social brain network can serve as a plausible biomarker and potential target for effective intervention in individuals with ASD.

The Revisiting Problem in Simultaneous Localization and Mapping: A Survey on Visual Loop Closure Detection

Where am I? This is one of the most critical questions that any intelligent system should answer to decide whether it navigates to a previously visited area. This problem has long been acknowledged for its challenging nature in simultaneous localization and mapping (SLAM), wherein the robot needs to correctly associate the incoming sensory data to the database allowing consistent map generation. The significant advances in computer vision achieved over the last 20 years, the increased computational power, and the growing demand for long-term exploration contributed to efficiently performing such a complex task with inexpensive perception sensors. In this article, visual loop closure detection, which formulates a solution based solely on appearance input data, is surveyed. We start by briefly introducing place recognition and SLAM concepts in robotics. Then, we describe a loop closure detection system's structure, covering an extensive collection of topics, including the feature extraction, the environment representation, the decision-making step, and the evaluation process. We conclude by discussing open and new research challenges, particularly concerning the robustness in dynamic environments, the computational complexity, and scalability in long-term operations. The article aims to serve as a tutorial and a position paper for newcomers to visual loop closure detection.

Operational continental-scale land cover mapping of Australia using the Open Data Cube

ABSTRACT To comprehensively support national and international initiatives for sustainable development, land cover products need to be reliably and routinely generated within operational frameworks. Coupled with consistent semantics and taxonomies, ensuring confidence in mapping land cover for multiple time periods, facilitates informed decision-making at scales appropriate to multiple policy domains. The United Nations Food and Agriculture Organisation (FAO) Land Cover Classification System (LCCS) provides a taxonomy that comparable at different scales, level of detail and geographic location. The Open Data Cube (ODC) initiative offers a framework for operational continental-scale land cover mapping using analysis-ready Earth Observation data. This study utilised the FAO LCCS framework and the Landsat sensor data through Digital Earth Australia (DEA; Australia’s ODC instance) to generate consistent and continent-wide land cover mapping (DEA Land Cover) of the Australian continent. DEA Land Cover provides annual maps from 1988 to 2020 at 25 m resolution. Output maps were validated with ∼12,000 independent validation points, giving an overall map accuracy of 80%. DEA Land Cover provides Australia with a nationally consistent picture of land cover, with an open-source software package using readily available global coverage data and demonstrates a pathway of adoption for national implementations across the world.

Machine learned clusters explain heterogeneity in outcomes from map-guided ablation of Atrial Fibrillation results from the large PROspective STanford AF Registry (ProSTAR)

Abstract Background Several mapping systems are being introduced to guide atrial fibrillation (AF) ablation to patient-specific regions of interest. However, results have been extremely heterogeneous between studies, ranging from very poor to very promising. It is unknown if this reflects specific patient characteristics or procedural factors because most prior series were middle sized (N∼30–100 patients). Purpose To study 1 year and 3 year very long-term outcomes from map guided AF-driver ablation in a large patient registry with multiple operators, to identify clinical and procedural features influencing outcomes. In real-world AF patients with diverse comorbidities, we applied a consistent patient-tailored AF mapping and ablation strategy, monitored outcomes carefully and applied statistical and unsupervised machine learning approaches to identify features of success and failure. Method We studied 632 consecutive patients (65±10 y, 178 F) undergoing ablation for drug-refractory AF. 59.7% had persistent AF, and 29.9% had prior unsuccessful ablation (median 1 procedure). All patients underwent pulmonary vein isolation (PVI), followed by ablation of AF regions of interest mapped from 64 pole baskets (RhythmView, Abbott, IL), by 11 operators. Patients were followed using ambulatory ECG monitors quarterly for one year, and at the time of symptoms for 3 years. Results Fig. 1A shows overall freedom from AF at 1-year of 77.5% (95% CI: 74.2%, 80.9%) and at 3 years of 55.5% (95% CI: 51.2%, 60.1%). Freedom from AF/AT at 1-year was 70.1% (95% CI: 66.5%, 73.8%), and at 3 years was 48.6% (95% CI: 44.3%, 53.3%). Success was higher in patients with procedural termination, first ablation versus prior unsuccessful procedures, for paroxysmal AF than non-paroxysmal AF (1 year: AT/AF freedom 74.9% versus 66.7%, p=0.006), and smaller left atrium. Three clusters (Fig 1B) were identified comprising CHA2DS2VASc score, enlarged LA, prior failed case, presenting rhythm and termination during the procedure (Table 2). At 1 year, freedom from AT/AF was 77.8% (95% CI: 72.2%, 82.1%) for cluster 3 and 56.2% (95% CI: 48.3%, 65.4%) for cluster 1 (Fig. 1B). Conclusion In our large registry of N=632 patients undergoing AF-map guided ablations, machine learned clusters identified cohorts with success of 56.2 to 77.8% at 1 year. Future studies should identify if lower success represents technical challenges, such as difficulties in mapping very large atria, or more difficult to treat mechanisms. These results may inform patient inclusion and ablation strategy in upcoming AF treatment trials. Funding Acknowledgement Type of funding sources: Public grant(s) – National budget only. Main funding source(s): National budget only - NIH, R01 HL149134, R01HL83359

A physics-constrained neural network for multiphase flows

The present study develops a physics-constrained neural network (PCNN) to predict sequential patterns and motions of multiphase flows (MPFs), which includes strong interactions among various fluid phases. To predict the order parameters, which locate individual phases in the future time, a neural network (NN) is applied to quickly infer the dynamics of the phases by encoding observations. The multiphase consistent and conservative boundedness mapping algorithm (MCBOM) is next implemented to correct the predicted order parameters. This enforces the predicted order parameters to strictly satisfy the mass conservation, the summation of the volume fractions of the phases to be unity, the consistency of reduction, and the boundedness of the order parameters. Then, the density of the fluid mixture is updated from the corrected order parameters. Finally, the velocity in the future time is predicted by another NN with the same network structure, but the conservation of momentum is included in the loss function to shrink the parameter space. The proposed PCNN for MPFs sequentially performs (NN)-(MCBOM)-(NN), which avoids nonphysical behaviors of the order parameters, accelerates the convergence, and requires fewer data to make predictions. Numerical experiments demonstrate that the proposed PCNN is capable of predicting MPFs effectively.