An inverse design method for supercritical airfoil based on conditional generative models

Inverse design has long been an efficient and powerful design tool in the aircraft industry.In this paper,a novel inverse design method for supercritical airfoils is proposed based on generative models in deep learning.A Conditional Variational Auto Encoder(CVAE)and an integrated generative network CVAE-GAN that combines the CVAE with the Wasserstein Generative Adversarial Networks(WGAN),are conducted as generative models.They are used to generate target wall Mach distributions for the inverse design that matches specified features,such as locations of suction peak,shock and aft loading.Qualitative and quantitative results show that both adopted generative models can generate diverse and realistic wall Mach number distributions satisfying the given features.The CVAE-GAN model outperforms the CVAE model and achieves better reconstruction accuracies for all the samples in the dataset.Furthermore,a deep neural network for nonlinear mapping is adopted to obtain the airfoil shape corresponding to the target wall Mach number distribution.The performances of the designed deep neural network are fully demonstrated and a smoothness measurement is proposed to quantify small oscillations in the airfoil surface,proving the authenticity and accuracy of the generated airfoil shapes.

Generative Adversarial Networks:Introduction and Outlook

Recently, generative adversarial networks(GANs)have become a research focus of artificial intelligence. Inspired by two-player zero-sum game, GANs comprise a generator and a discriminator, both trained under the adversarial learning idea.The goal of GANs is to estimate the potential distribution of real data samples and generate new samples from that distribution.Since their initiation, GANs have been widely studied due to their enormous prospect for applications, including image and vision computing, speech and language processing, etc. In this review paper, we summarize the state of the art of GANs and look into the future. Firstly, we survey GANs' proposal background,theoretic and implementation models, and application fields.Then, we discuss GANs' advantages and disadvantages, and their development trends. In particular, we investigate the relation between GANs and parallel intelligence,with the conclusion that GANs have a great potential in parallel systems research in terms of virtual-real interaction and integration. Clearly, GANs can provide substantial algorithmic support for parallel intelligence.

Federated Learning Model for Auto Insurance Rate Setting Based on Tweedie Distribution

In the assessment of car insurance claims,the claim rate for car insurance presents a highly skewed probability distribution,which is typically modeled using Tweedie distribution.The traditional approach to obtaining the Tweedie regression model involves training on a centralized dataset,when the data is provided by multiple parties,training a privacy-preserving Tweedie regression model without exchanging raw data becomes a challenge.To address this issue,this study introduces a novel vertical federated learning-based Tweedie regression algorithm for multi-party auto insurance rate setting in data silos.The algorithm can keep sensitive data locally and uses privacy-preserving techniques to achieve intersection operations between the two parties holding the data.After determining which entities are shared,the participants train the model locally using the shared entity data to obtain the local generalized linear model intermediate parameters.The homomorphic encryption algorithms are introduced to interact with and update the model intermediate parameters to collaboratively complete the joint training of the car insurance rate-setting model.Performance tests on two publicly available datasets show that the proposed federated Tweedie regression algorithm can effectively generate Tweedie regression models that leverage the value of data fromboth partieswithout exchanging data.The assessment results of the scheme approach those of the Tweedie regressionmodel learned fromcentralized data,and outperformthe Tweedie regressionmodel learned independently by a single party.

From furnace up to freezer:Elevational patterns of plant diversity in Mount Palvar,a semi-arid Irano-Turanian mountain range of southwest Asia

Much of the world's biodiversity lies in heterogeneous mountain areas with their diverse environments.As an example,Iranian montane ranges are highly diverse,particularly in the Irano-Turanian phytogeographical region.Understanding plant diversity patterns with increasing elevation is of high significance,not least for conservation planning.We studied the pattern of species richness,Shannon diversity,endemic richness,endemics ratio,and richness of life forms along a 3900 m elevational transect in Mount Palvar,overlooking the Lut Desert in Southeast Iran.We also analyzed the effect of environmental variables on species turnover along the vertical gradient.A total of 120 vegetation plots(10 m×10 m)were sampled along the elevational transect containing species and environmental data.To discover plant diversity pattern along the elevational gradient,generalized additive model(GAM)was used.Non-metric multidimensional scaling(NMDS)was applied for illustrating the correlation between species composition and environmental variables.We found hump-shaped pattern for species richness,Shannon diversity,endemic richness,and species richness of different life forms,but a monotonic increasing pattern for ratio of endemic species from low to high elevations.Our study confirms the humped pattern of species richness peaking at intermediate elevations along a complete elevational gradient in a semi-arid mountain.The monotonic increase of endemics ratio with elevation in our area as a case study is consistent with global increase of endemism with elevation.According to our results,temperature and precipitation are two important climatic variables that drive elevational plant diversity,particularly in seasonally dry areas.Our study suggests that effective conservation and management are needed for this low latitude mountain area along with calling for long-term monitoring for species redistribution.

Modeling the effect of stand and site characteristics on the probability of mistletoe infestation in Scots pine stands using remote sensing data

Over the past decade,the presence of mistletoe(Viscum album ssp.austriacum)in Scots pine stands has increased in many European countries.Understanding the factors that influence the occurrence of mistletoe in stands is key to making appropriate forest management decisions to limit damage and prevent the spread of mistletoe in the future.Therefore,the main objective of this study was to determine the probability of mistletoe occurrence in Scots pine stands in relation to stand-related endogenous factors such as age,top height,and stand density,as well as topographic and edaphic factors.We used unmanned aerial vehicle(UAV)imagery from 2,247 stands to detect mistletoe in Scots pine stands,while majority stand and site characteristics were calculated from airborne laser scanning(ALS)data.Information on stand age and site type from the State Forest database were also used.We found that mistletoe infestation in Scots pine stands is influenced by stand and site characteristics.We documented that the densest,tallest,and oldest stands were more susceptible to mistletoe infestation.Site type and specific microsite conditions associated with topography were also important factors driving mistletoe occurrence.In addition,climatic water balance was a significant factor in increasing the probability of mistletoe occurrence,which is important in the context of predicted temperature increases associated with climate change.Our results are important for better understanding patterns of mistletoe infestation and ecosystem functioning under climate change.In an era of climate change and technological development,the use of remote sensing methods to determine the risk of mistletoe infestation can be a very useful tool for managing forest ecosystems to maintain forest sustainability and prevent forest disturbance.

Benchmarking deep learning-based models on nanophotonic inverse design problems

Photonic inverse design concerns the problem of finding photonic structures with target optical properties.However,traditional methods based on optimization algorithms are time-consuming and computationally expensive.Recently,deep learning-based approaches have been developed to tackle the problem of inverse design efficiently.Although most of these neural network models have demonstrated high accuracy in different inverse design problems,no previous study has examined the potential effects under given constraints in nanomanufacturing.Additionally,the relative strength of different deep learning-based inverse design approaches has not been fully investigated.Here,we benchmark three commonly used deep learning models in inverse design:Tandem networks,Variational Auto-Encoders,and Generative Adversarial Networks.We provide detailed comparisons in terms of their accuracy,diversity,and robustness.We find that tandem networks and Variational Auto-Encoders give the best accuracy,while Generative Adversarial Networks lead to the most diverse predictions.Our findings could serve as a guideline for researchers to select the model that can best suit their design criteria and fabrication considerations.In addition,our code and data are publicly available,which could be used for future inverse design model development and benchmarking.

Grouping tree species to estimate basal area increment in temperate multispecies forests in Durango,Mexico

Multispecies forests have received increased scientific attention,driven by the hypothesis that biodiversity improves ecological resilience.However,a greater species diversity presents challenges for forest management and research.Our study aims to develop basal area growth models for tree species cohorts.The analysis is based on a dataset of 423 permanent plots(2,500 m^(2))located in temperate forests in Durango,Mexico.First,we define tree species cohorts based on individual and neighborhood-based variables using a combination of principal component and cluster analyses.Then,we estimate the basal area increment of each cohort through the generalized additive model to describe the effect of tree size,competition,stand density and site quality.The principal component and cluster analyses assign a total of 37 tree species to eight cohorts that differed primarily with regard to the distribution of tree size and vertical position within the community.The generalized additive models provide satisfactory estimates of tree growth for the species cohorts,explaining between 19 and 53 percent of the total variation of basal area increment,and highlight the following results:i)most cohorts show a"rise-and-fall"effect of tree size on tree growth;ii)surprisingly,the competition index"basal area of larger trees"had showed a positive effect in four of the eight cohorts;iii)stand density had a negative effect on basal area increment,though the effect was minor in medium-and high-density stands,and iv)basal area growth was positively correlated with site quality except for an oak cohort.The developed species cohorts and growth models provide insight into their particular ecological features and growth patterns that may support the development of sustainable management strategies for temperate multispecies forests.

Prediction and driving factors of forest fire occurrence in Jilin Province,China

Forest fires are natural disasters that can occur suddenly and can be very damaging,burning thousands of square kilometers.Prevention is better than suppression and prediction models of forest fire occurrence have developed from the logistic regression model,the geographical weighted logistic regression model,the Lasso regression model,the random forest model,and the support vector machine model based on historical forest fire data from 2000 to 2019 in Jilin Province.The models,along with a distribution map are presented in this paper to provide a theoretical basis for forest fire management in this area.Existing studies show that the prediction accuracies of the two machine learning models are higher than those of the three generalized linear regression models.The accuracies of the random forest model,the support vector machine model,geographical weighted logistic regression model,the Lasso regression model,and logistic model were 88.7%,87.7%,86.0%,85.0%and 84.6%,respectively.Weather is the main factor affecting forest fires,while the impacts of topography factors,human and social-economic factors on fire occurrence were similar.

Spatio-temporal variation of depth to groundwater level and its driving factors in arid and semi-arid regions of India

Climate change and increasing anthropogenic activities,such as over-exploitation of groundwater,are exerting unavoidable stress on groundwater resources.This study investigated the spatio-temporal variation of depth to groundwater level(DGWL)and the impacts of climatic(precipitation,maximum temperature,and minimum temperature)and anthropogenic(gross district product(GDP),population,and net irrigated area(NIA))variables on DGWL during 1994-2020.The study considered DGWL in 113 observation wells and piezometers located in arid western plains(Barmer and Jodhpur districts)and semi-arid eastern plains(Jaipur,Ajmer,Dausa,and Tonk districts)of Rajasthan State,India.Statistical methods were employed to examine the annual and seasonal patterns of DGWL,and the generalized additive model(GAM)was used to determine the impacts of climatic and anthropogenic variables on DGWL.During 1994-2020,except for Barmer District,where the mean annual DGWL was almost constant(around 26.50 m),all other districts exhibited increase in DGWL,with Ajmer District experiencing the most increase.The results also revealed that 36 observation wells and piezometers showed a statistically significant annual increasing trend in DGWL and 34 observation wells and piezometers exhibited a statistically significant decreasing trend in DGWL.Similarly,32 observation wells and piezometers showed an statistically significant increasing trend and 37 observation wells and piezometers showed a statistically significant decreasing trend in winter;33 observation wells and piezometers indicated a statistically significant increasing trend and 34 had a statistically significant decreasing trend in post-monsoon;35 observation wells and piezometers exhibited a statistically significant increasing trend and 32 observation wells and piezometers showed a statistically significant decreasing trend in pre-monsoon;and 36 observation wells and piezometers reflected a statistically significant increasing trend and 30 observation wells and piezometers reflected a statistically significant decreasing trend in monsoon.Interestingly,most of the observation wells and piezometers with increasing trends of DGWL were located in Dausa and Jaipur districts.Furthermore,the GAM analysis revealed that climatic variables,such as precipitation,significantly affected DGWL in Barmer District,and DGWL in all other districts was influenced by anthropogenic variables,including GDP,NIA,and population.As a result,stringent regulations should be implemented to curb excessive groundwater extraction,manage agricultural water demand,initiate proactive aquifer recharge programs,and strengthen sustainable management in these water-scarce regions.

Generative Neural Network Based Spectrum Sharing Using Linear Sum Assignment Problems

Spectrum management and resource allocation(RA)problems are challenging and critical in a vast number of research areas such as wireless communications and computer networks.The traditional approaches for solving such problems usually consume time and memory,especially for large-size problems.Recently different machine learning approaches have been considered as potential promising techniques for combinatorial optimization problems,especially the generative model of the deep neural networks.In this work,we propose a resource allocation deep autoencoder network,as one of the promising generative models,for enabling spectrum sharing in underlay device-to-device(D2D)communication by solving linear sum assignment problems(LSAPs).Specifically,we investigate the performance of three different architectures for the conditional variational autoencoders(CVAE).The three proposed architecture are the convolutional neural network(CVAECNN)autoencoder,the feed-forward neural network(CVAE-FNN)autoencoder,and the hybrid(H-CVAE)autoencoder.The simulation results show that the proposed approach could be used as a replacement of the conventional RA techniques,such as the Hungarian algorithm,due to its ability to find solutions of LASPs of different sizes with high accuracy and very fast execution time.Moreover,the simulation results reveal that the accuracy of the proposed hybrid autoencoder architecture outperforms the other proposed architectures and the state-of-the-art DNN techniques.

Coverless Steganography for Digital Images Based on a Generative Model

In this paper,we propose a novel coverless image steganographic scheme based on a generative model.In our scheme,the secret image is first fed to the generative model database,to generate a meaning-normal and independent image different from the secret image.The generated image is then transmitted to the receiver and fed to the generative model database to generate another image visually the same as the secret image.Thus,we only need to transmit the meaning-normal image which is not related to the secret image,and we can achieve the same effect as the transmission of the secret image.This is the first time to propose the coverless image information steganographic scheme based on generative model,compared with the traditional image steganography.The transmitted image is not embedded with any information of the secret image in this method,therefore,can effectively resist steganalysis tools.Experimental results show that our scheme has high capacity,security and reliability.

Multi-source information fused generative adversarial network model and data assimilation based history matching for reservoir with complex geologies

For reservoirs with complex non-Gaussian geological characteristics,such as carbonate reservoirs or reservoirs with sedimentary facies distribution,it is difficult to implement history matching directly,especially for the ensemble-based data assimilation methods.In this paper,we propose a multi-source information fused generative adversarial network(MSIGAN)model,which is used for parameterization of the complex geologies.In MSIGAN,various information such as facies distribution,microseismic,and inter-well connectivity,can be integrated to learn the geological features.And two major generative models in deep learning,variational autoencoder(VAE)and generative adversarial network(GAN)are combined in our model.Then the proposed MSIGAN model is integrated into the ensemble smoother with multiple data assimilation(ESMDA)method to conduct history matching.We tested the proposed method on two reservoir models with fluvial facies.The experimental results show that the proposed MSIGAN model can effectively learn the complex geological features,which can promote the accuracy of history matching.

Predicting Lung Cancers Using Epidemiological Data:A Generative-Discriminative Framework

Predictive models for assessing the risk of developing lung cancers can help identify high-risk individuals with the aim of recommending further screening and early intervention.To facilitate pre-hospital self-assessments,some studies have exploited predictive models trained on non-clinical data(e.g.,smoking status and family history).The performance of these models is limited due to not considering clinical data(e.g.,blood test and medical imaging results).Deep learning has shown the potential in processing complex data that combine both clinical and non-clinical information.However,predicting lung cancers remains difficult due to the severe lack of positive samples among follow-ups.To tackle this problem,this paper presents a generative-discriminative framework for improving the ability of deep learning models to generalize.According to the proposed framework,two nonlinear generative models,one based on the generative adversarial network and another on the variational autoencoder,are used to synthesize auxiliary positive samples for the training set.Then,several discriminative models,including a deep neural network(DNN),are used to assess the lung cancer risk based on a comprehensive list of risk factors.The framework was evaluated on over 55000 subjects questioned between January 2014 and December 2017,with 699 subjects being clinically diagnosed with lung cancer between January 2014 and August 2019.According to the results,the best performing predictive model built using the proposed framework was based on DNN.It achieved an average sensitivity of 76.54%and an area under the curve of 69.24%in distinguishing between the cases of lung cancer and normal cases on test sets.

Additions of landscape metrics improve predictions of occurrence of species distribution models

Species distribution models are used to aid our understanding of the processes driving the spatial patterns of species’ habitats. This approach has received criticism, however, largely because it neglects landscape metrics. We examined the relative impacts of landscape predictors on the accuracy of habitat models by constructing distribution models at regional scales incorporating environmental variables (climate, topography, vegetation, and soil types) and secondary species occurrence data, and using them to predict the occurrence of 36 species in 15 forest fragments where we conducted rapid surveys. We then selected six landscape predictors at the landscape scale and ran general linear models of species presence/absence with either a single scale predictor (the probabilities of occurrence of the distribution models or landscape variables) or multiple scale predictors (distribution models + one landscape variable). Our results indicated that distribution models alone had poor predictive abilities but were improved when landscape predictors were added; the species responses were not, however, similar to the multiple scale predictors. Our study thus highlights the importance of considering landscape metrics to generate more accurate habitat suitability models.

A Comparison of Two Canopy Radiative Models in Land Surface Processes

This paper compares the predictions by two radiative transfer models-the two-stream approximation model and the generalized layered model （developed by the authors） in land surface processes -for different canopies under direct or diffuse radiation conditions. The comparison indicates that there are significant differences between the two models, especially in the near infrared （NIR） band. Results of canopy reflectance from the two-stream model are larger than those from the generalized model. However, results of canopy absorptance from the two-stream model are larger in some cases and smaller in others compared to those from the generalized model, depending on the cases involved. In the visible （VIS） band, canopy reflectance is smaller and canopy absorptance larger from the two-stream model compared to the generalized model when the Leaf Area Index （LAI） is low and soil reflectance is high. In cases of canopies with vertical leaf angles, the differences of reflectance and absorptance in the VIS and NIR bands between the two models are especially large. Two commonly occurring cases, with which the two-stream model cannot deal accurately, are also investigated. One is for a canopy with different adaxial and abaxial leaf optical properties; and the other is for incident sky diffuse radiation with a non-uniform distribution. Comparison of the generalized model within the same canopy for both uniform and non-uniform incident diffuse radiation inputs shows smaller differences in general. However, there is a measurable difference between these radiation inputs for a canopy with high leaf angle. This indicates that the application of the two-stream model to a canopy with different adaxial and abaxial leaf optical properties will introduce non-negligible errors.

Generative Trapdoors for Public Key Cryptography Based on Automatic Entropy Optimization

Trapdoor is a key component of public key cryptography design which is the essential security foundation of modern cryptography.Normally,the traditional way in designing a trapdoor is to identify a computationally hard problem,such as the NPC problems.So the trapdoor in a public key encryption mechanism turns out to be a type of limited resource.In this paper,we generalize the methodology of adversarial learning model in artificial intelligence and introduce a novel way to conveniently obtain sub-optimal and computationally hard trapdoors based on the automatic information theoretic search technique.The basic routine is constructing a generative architecture to search and discover a probabilistic reversible generator which can correctly encoding and decoding any input messages.The architecture includes a trapdoor generator built on a variational autoencoder(VAE)responsible for searching the appropriate trapdoors satisfying a maximum of entropy,a random message generator yielding random noise,and a dynamic classifier taking the results of the two generator.The evaluation of our construction shows the architecture satisfying basic indistinguishability of outputs under chosen-plaintext attack model(CPA)and high efficiency in generating cheap trapdoors.

TESTING FOR VARYING DISPERSION IN DISCRETE EXPONENTIAL FAMILY NONLINEAR MODELS

It is necessary to test for varying dispersion in generalized nonlinear models.Wei,et al(1998) developed a likelihood ratio test,a score test and their adjustments to test for varying dispersion in continuous exponential family nonlinear models.This type of problem in the framework of general discrete exponential family nonlinear models is discussed.Two types of varying dispersion,which are random coefficients model and random effects model,are proposed,and corresponding score test statistics are constructed and expressed in simple,easy to use,matrix formulas.

Quantum Generative Model with Variable-Depth Circuit

In recent years,an increasing number of studies about quantum machine learning not only provide powerful tools for quantum chemistry and quantum physics but also improve the classical learning algorithm.The hybrid quantum-classical framework,which is constructed by a variational quantum circuit(VQC)and an optimizer,plays a key role in the latest quantum machine learning studies.Nevertheless,in these hybrid-framework-based quantum machine learning models,the VQC is mainly constructed with a fixed structure and this structure causes inflexibility problems.There are also few studies focused on comparing the performance of quantum generative models with different loss functions.In this study,we address the inflexibility problem by adopting the variable-depth VQC model to automatically change the structure of the quantum circuit according to the qBAS score.The basic idea behind the variable-depth VQC is to consider the depth of the quantum circuit as a parameter during the training.Meanwhile,we compared the performance of the variable-depth VQC model based on four widely used statistical distances set as the loss functions,including Kullback-Leibler divergence(KL-divergence),Jensen-Shannon divergence(JS-divergence),total variation distance,and maximum mean discrepancy.Our numerical experiment shows a promising result that the variable-depth VQC model works better than the original VQC in the generative learning tasks.

Simulating Potential Distribution of Tamarix chinensis in Yellow River Delta by Generalized Additive Models

There are typical ecosystems of littoral wetlands in the Yellow River Delta.In order to study the relationships between Tamarix chinensis and environmental variables and to predict T.chinensis potential distribution in the Yellow River Delta,641 vegetation samples and 964 soil samples were collected in the area in October of 2004,2005,2006 and 2007.The contents of soil organic matter,total phosphorus,salt,and soluble potassium were determined.Then,the analyzed data were interpolated into spatial raster data by Kriging interpolation method.Meanwhile,the digital elevation model,soil type map and landform unit map of the Yellow River Delta were also collected.Generalized Additive Models(GAMs) were employed to build species-environment model and then simulate the potential distribution of T.chinensis.The results indicated that the distribution of T.chinensis was mainly limited by soil salt content,total soil phosphorus content,soluble potassium content,soil type,landform unit,and elevation.The distribution probability of T.chinensis was produced with a lookup table generated by Grasp Module(based on GAMs) in software ArcView GIS 3.2.The AUC(Area Under Curve) value of validation and cross-validation of ROC(Receive Operating Characteristic) were both higher than 0.8,which suggested that the established model had a high precision for predicting species distribution.

Asymptotic Normality of Multi-Dimension Quasi Maximum Likelihood Estimate in Generalized Linear Models withAdaptive Design

We study the quasi likelihood equation in Generalized Linear Models（GLM） with adaptive design ∑（i=1）^n xi（yi-h（x＇iβ））=0, where yi is a q=vector, and xi is a p×q random matrix. Under some assumptions, it is shown that the Quasi- Likelihood equation for the GLM has a solution which is asymptotic normal.