Search

Fire radiative power (FRP) is a key indicator for evaluating the intensity of wildfires, unlike traditional real-time fire lines or combustion areas that only provide binary information, and its accurate prediction is more important for firefighting actions and environmental pollution assessment. To this end, we used a combination of data from geostationary satellites and polar orbit satellites to correct the FRP data. Incorporating various factors that affect wildfire spread, such as meteorological conditions, topography, vegetation indexes, and population density, we constructed a comprehensive California wildfire spread dataset, covering information since 2017. Then, we established a deep learning framework that integrates various modules to analyze multimodal data for the accurate prediction of FRP imagery. We investigated the impact of input sequence length and loss function design on model predictive performance, leading to subsequent model optimization. Furthermore, our model has demonstrated acceptable performance in transfer learning and multistep prediction, emphasizing its application value in wildfire prediction and management. It can provide more detailed information about wildfire spread, showcasing the powerful capability of deep learning to process multimodal data and its potential in the emerging field of real-time FRP prediction.

Forest fire is one of the dominant disturbances in the forests of Heilongjiang Province, China, and is one of the most rapid response predictors that indicate the impact of climate change on forests. This study calculated the Canadian FWI (Fire Weather Index) and its components from meteorological record over past years, and a linear model was built from the monthly mean FWI and monthly fire numbers. The significance test showed that fire numbers and FWI had a very pronounced correlation, and monthly mean FWI was suitable for predicting the monthly fire numbers in this region. Then FWI and its components were calculated from the SRES (IPCC Special Report on Emission Scenarios) A2 and B2 climatic scenarios, and the linear model was rebuilt to be suitable for the climatic scenarios. The results indicated that fire numbers would increase by 2.98–129.97% and −2.86–103.30% in the A2 and B2 climatic scenarios during 2020–2090, respectively. The monthly variation tendency of the FWI components is similar in the A2 and B2 climatic scenarios. The increasing fire risk is uneven across months in these two climatic scenarios. The monthly analysis showed that the FFMC (Fine Fuel Moisture Code) would increase dramatically in summer, and the decreasing precipitation in summer would contribute greatly to this tendency. The FWI would increase rapidly from the spring fire season to the autumn fire season, and the FWI would have the most rapid increase in speed in the spring fire season. DMC (Duff Moisture Code) and DC (Drought Code) have relatively balanced rates of increasing from spring to autumn. The change in the FWI in this region is uneven in space as well. In early 21st century, the FWI of the north of Heilongjiang Province would increase more rapidly than the south, whereas the FWI of the middle and south of Heilongjiang Province would gradually catch up with the increasing speed of the north from the middle of 21st century. The changes in the FWI across seasons and space would influence the fire management policy in this region, and the increasing fire numbers and variations in the FWI scross season and space suggest that suitable development of the management of fire sources and forest fuel should be conducted.

Since forest fuel decomposes slowly and increases the risk of forest fires by accumulating over the years, forest fuel management to accelerate the decomposition process is essential to prevent forest fires and protect forest resources. In this study, we conducted experiments on forest fuels (Pinus sylvestris var. mongholica, Larix gmelinii, Quercus mongolica and Fraxinus mandshurica) in four typical plantation forests in northeast China by adding Trichoderma spp. to investigate the decomposition process and the changes in cellulose, hemicellulose and the water-holding capacity of the fuels. The addition of Trichoderma spp. accelerated the decomposition of cellulose, hemicellulose and lignin in the fuel. Trichoderma spp. promoted the ratio of water absorption and loss, as well as the water-holding capacity of the fuels. The ratio of water absorption and loss reached equilibrium when the decomposition time was up to 35 days, and the addition of Trichoderma spp. increased the maximal water-holding capacity of the fuel. The residual ratio of the four types of fuel degraded by the different treatments was inversely proportional to their maximal water-holding capacities and to the residual ratios of cellulose, hemicellulose and lignin. The residual ratios of degradation of the four fuels under different treatments were linearly related to their maximum water-holding capacity, cellulose, hemicellulose and lignin residual ratios. Trichoderma spp. had a positive effect on the degradation effect and water-holding capacity of fuel on the ground surface of four typical plantation forests. The study is of positive significance for the decomposition of fuel in forests, it promotes the development of biological fire prevention technology and provides a basis for the reinforcement of the management of fuel in forests and the protection of forest resources.

Bistatic and multistatic SAR technology, with its multi-dimensional, ultra-wide swath, and high-resolution advantages, is widely used in earth observation, military reconnaissance, deep space exploration, and other fields. The LuTan-1 (LT-1) mission employs two full-polarimetric L-band SAR satellites for the BiSAR system. The bistatic mode introduces phase errors in echo reception paths due to different transmission links, making echo compensation a key factor in ensuring BiSAR performance. This paper proposes a novel bistatic internal calibration strategy that combines ground temperature compensation, in-orbit internal calibration, and pulsed alternate synchronization to achieve echo compensation. Prior to launch, temperature compensation data for the internal calibration system are obtained via temperature experiments. During in-orbit operation, calibration data are acquired by executing the internal calibration pulse sequence and noninterrupted pulsed alternate synchronization. In ground processing, echo compensation is completed based on the above two parts of calibration data. A comprehensive analysis of the entire calibration chain reveals a temperature compensation accuracy of 0.10 dB/1.38°. Additionally, a ground verification system is established to conduct BiSAR experiments, achieving a phase synchronization accuracy of 0.16°. Furthermore, the in-orbit test obtained DSM products with an average error of 1.3 m. This strategy provides a valuable reference for future spaceborne bistatic and multistatic SAR systems.

There was an error in the original publication [...]

Forest fires ignited by lightning accounted for 68.28% of all forest fires in the Greater Khingan Mountains (GKM) region of northeast China. Forecasting the incidence of lightning-triggered forest fires in the region is imperative for mitigating deforestation, preserving biodiversity, and safeguarding distinctive natural habitats and resources. Lightning monitoring data and vegetation moisture content have emerged as pivotal factors among the various influences on lightning-induced fires. This study employed innovative satellite remote sensing technology to swiftly acquire vegetation moisture content data across extensive forested regions. Firstly, the most suitable method to identify the lightning strikes that resulted in fires and two crucial lightning parameters correlated with fire occurrence are confirmed. Secondly, a logistic regression method is proposed for predicting the likelihood of fires triggered by lightning strikes. Finally, the method underwent verification using five years of fire data from the GKM area, resulting in an AUC value of 0.849 and identifying the primary factors contributing to lightning-induced fires in the region.

The drastic increase of forest fire occurrence, which in recent years has posed severe threat and damage worldwide to the natural environment and human society, necessitates smoke detection of the early forest fire. First, a semantic segmentation method based on multiple color spaces feature fusion is put forward for forest fire smoke detection. Considering that smoke images in different color spaces may contain varied and distinctive smoke features which are beneficial for improving the detection ability of a model, the proposed model integrates the function of multi-scale and multi-type self-adaptive weighted feature fusion with attention augmentation to extract the enriched and complementary fused features of smoke, utilizing smoke images from multi-color spaces as inputs. Second, the model is trained and evaluated on part of the FIgLib dataset containing high-quality smoke images from watchtowers in the forests, incorporating various smoke types and complex background conditions, with a satisfactory smoke segmentation result for forest fire detection. Finally, the optimal color space combination and the fusion strategy for the model is determined through elaborate and extensive experiments with a superior segmentation result of 86.14 IoU of smoke obtained.

Due to the complex vegetation and topography conditioning the plateau mountainous area, forest fire is difficult to put out in this area once it occurred. The research on forest fire danger prediction is very significant for fire prevention and fire fighting in plateau mountain area. Based on fire dataset from 1997 to 2018 in Lijiang area, this paper applied the spatial overlay analysis, Kriging interpolation analysis and Logistic regression model to study the relationship between forest fire occurrence and elevation, vegetation types and meteorological factors. An optimal Logistic model was selected to predict the probability of forest fire occurrence and fire danger rating in Lijiang area. The results showed that elevation, slope, aspect, daily average temperature and daily average relative humidity were significantly correlated with forest fire occurrence. The prediction accuracy of the Logistic model is averagely 86.9%. According to the results of fire danger prediction, forest fires in Lijiang occurred mainly concentrated in the north of Yulong county, the south of Ninglang county and the central area of Huaping county. The results are of great significance for forest fire prevention in Lijiang area.

Condyloma acuminatum (CA) is a sexually transmitted disease (STD) caused by human papillomavirus (HPV) infection. It is important to study the prevalence and distribution of HPV genotypes before implementing the HPV vaccination program. Therefore, the aim of this study was to evaluate the epidemiological characteristics of CA cases and the distribution of HPV genotypes in Shandong Province, China. One-to-one questionnaire surveys were conducted on all patients diagnosed with CA in sentinel hospitals from Shandong Province, China. HPV genotypes were determined using the polymerase chain reaction (PCR)-reverse dot blot hybridization method. The study enrolled 1185 patients (870 males and 315 females) and found that CA patients are mainly males and sexually active people between the ages of 20 and 40. Recurrence occurred in 34.7% patients. Among the 880 CA patients who underwent HPV typing, the HPV test positivity rate was 91.4%. In these cases, low-risk (LR) HPV infection was predominant, with an infection rate of 91.3%, while high-risk (HR) HPV genotypes were found in 53.5% patients. The most frequent HPV genotypes encountered were HPV6 (57.8%), HPV11 (37.2%), HPV16 (13.7%), and HPV42 (10.3%). HPV6 and/or HPV11 are the main infections in all patients, and more than half of the patients are coinfected with HR-HPV. However, unlike other regions, HPV42 has a higher prevalence rate among CA patients in Shandong Province and is a nonvaccine HPV genotype. Therefore, regular HPV typing helps to understand the characteristics of specific genotypes and the choice of the best type for vaccine coverage.

Cerenkov Luminescence Tomography (CLT) is a novel and potential imaging modality which can display the three-dimensional distribution of radioactive probes. However, due to severe ill-posed inverse problem, obtaining accurate reconstruction results is still a challenge for traditional model-based methods. The recently emerged deep learning-based methods can directly learn the mapping relation between the surface photon intensity and the distribution of the radioactive source, which effectively improves the performance of CLT reconstruction. However, the previously proposed deep learning-based methods cannot work well when the order of input is disarranged. In this paper, a novel 3D graph convolution-based residual network, GCR-Net, is proposed, which can obtain a robust and accurate reconstruction result from the photon intensity of the surface. Additionally, it is proved that the network is insensitive to the order of input. The performance of this method was evaluated with numerical simulations and in vivo experiments. The results demonstrated that compared with the existing methods, the proposed method can achieve efficient and accurate reconstruction in localization and shape recovery by utilizing three-dimensional information.

Volatile oils in forest fuel can significantly affect forest fire behavior, especially extreme fire behavior, e.g., deflagration, fire storms, blowups, eruptive fires and crown fires. However, how these oils influence fire behavior remains unclear, as few qualitative studies have been performed globally. In the present study, we compared the volatile oil contents and components in live branches and surface dead fuel of Pinus yunnanensis Franch, which is widely distributed in Southwest China, to explore their potential effects on extreme fire behavior. Fifteen samples of live branches and fifteen samples of surface dead fuel were collected. Volatile oils were extracted from the samples using steam distillation, and their components were identified and analyzed using gas chromatography–mass spectrometry (GC-MS). The results show that the volatile oil content in live branches was as high as 8.28 mL·kg−1 (dry weight) and was significantly higher than that in surface dead fuel (3.55 mL·kg−1). The volatile oil content in the P. yunnanensis forest was 126.12 kg per hectare. The main volatile oil components were terpenoids, of which monoterpenes accounted for the highest proportion based on their content (62.63%), followed by sesquiterpenes (22.44%). The terpenoid compounds in live branches were more abundant than those in surface dead fuel. Monoterpenes and sesquiterpenes in volatile oils in forest fuel have low boiling points, high calorific values and a lower explosion limit (LEL; 38.4 g·m−3), which are important characteristics in the manifestation of extreme fire behavior such as deflagration. The analysis results indicate that when heated, the oily gases from P. yunnanensis forest could fill 3284.26 m3 per hectare, with a gas concentration reaching the LEL. We conclude that volatile oil in P. yunnanensis has an important influence on the manifestation of extreme fire behavior, and live branches have a greater effect than surface dead fuel.

Polarimetric decomposition is an effective way for synthetic aperture radar (SAR) data interpretation. As for hybrid compact polarimetric (HCP) SAR, there are mainly two different types of decomposition methods, including wave-dichotomy-theorem-based and model-based. However, the existing methods are not universal because they cannot estimate volume scattering component accurately in different scenes. In order to solve this problem, a general two-stage model-based three-component HCP decomposition method (GTM) is proposed by involving Arii volume scattering model. In the first stage, a method is designed to identify the dominant scattering mechanism (surface, dihedral, and volume scattering mechanism) of each pixel according to the characteristics of the three scattering models. Then, the GTM method is solved when the three basic scattering mechanisms are dominant, respectively, in the second stage. Two simulated HCP datasets are used to verify the performance of the decomposition method. The results show that GTM can more accurately identify the dominant scattering mechanism in different regions than existing methods, and it can obtain closer results to the quad-polarimetric method.

Purpose: This study aimed to compare the performance of radiomics and deep learning in predicting EGFR mutation status in patients with lung cancer based on PET/CT images, and tried to explore a model with excellent prediction performance to accurately predict EGFR mutation status in patients with non-small cell lung cancer (NSCLC).Method: PET/CT images of 194 NSCLC patients from Xijing Hospital were collected and divided into a training set and a validation set according to the ratio of 7:3. Statistics were made on patients’ clinical characteristics, and a large number of features were extracted based on their PET/CT images (4306 radiomics features and 2048 deep learning features per person) with the pyradiomics toolkit and 3D convolutional neural network. Then a radiomics model (RM), a deep learning model (DLM), and a hybrid model (HM) were established. The performance of the three models was compared by receiver operating characteristic (ROC) curves, sensitivity, specificity, accuracy, calibration curves, and decision curves. In addition, a nomogram based on a deep learning score (DS) and the most significant clinical characteristic was plotted.Result: In the training set composed of 138 patients (64 with EGFR mutation and 74 without EGFR mutation), the area under the ROC curve (AUC) of HM (0.91, 95% CI: 0.86–0.96) was higher than that of RM (0.82, 95% CI: 0.75–0.89) and DLM (0.90, 95% CI: 0.85–0.95). In the validation set composed of 57 patients (32 with EGFR mutation and 25 without EGFR mutation), the AUC of HM (0.85, 95% CI: 0.77–0.93) was also higher than that of RM (0.68, 95% CI: 0.52–0.84) and DLM (0.79, 95% CI: 0.67–0.91). In all, HM achieved better diagnostic performance in predicting EGFR mutation status in NSCLC patients than two other models.Conclusion: Our study showed that the deep learning model based on PET/CT images had better performance than radiomics model in diagnosing EGFR mutation status of NSCLC patients based on PET/CT images. Combined with the most statistically significant clinical characteristic (smoking) and deep learning features, our hybrid model had better performance in predicting EGFR mutation types of patients than two other models, which could enable NSCLC patients to choose more personalized treatment schemes.

Video Synthetic Aperture Radar (ViSAR) operating in spotlight mode has received widespread attention in recent years because of its ability to form a sequence of SAR images for a region of interest (ROI). However, due to the heavy computational burden of data processing, the application of ViSAR is limited in practice. Although back projection (BP) can avoid unnecessary repetitive processing of overlapping parts between consecutive video frames, it is still time-consuming for high-resolution video-SAR data processing. In this article, in order to achieve the same or a similar effect to BP and reduce the computational burden as much as possible, a novel time-frequency sub-aperture technology (TFST) is proposed. Firstly, based on azimuth resampling and full aperture azimuth scaling, a time domain sub-aperture (TDS) processing algorithm is proposed to process ViSAR data with large coherent integration angles to ensure the continuity of ViSAR monitoring. Furthermore, through frequency domain sub-aperture (FDS) processing, multiple high-resolution video frames can be generated efficiently without sub-aperture reconstruction. In addition, TFST is based on the range migration algorithm (RMA), which can take into account the accuracy while ensuring efficiency. The results of simulation and X-band airborne SAR experimental data verify the effectiveness of the proposed method.

Identification of forest burn severity is essential for fire assessments and a necessary procedure in modern forest management. Due to the low efficiency and labor intensity of the current post-fire field survey in China’s Forestry Standards, the limitation of temporal resolution of satellite imagery, and poor objectivity of manual interpretations, a new method for automatic extraction of forest burn severity based on small visible unmanned aerial vehicle (UAV) images is proposed. Taking the forest fires which occurred in Anning city of Yunnan Province in 2019 as the study objects, post-fire imagery was obtained by a small, multi-rotor near-ground UAV. Some image recognition indices reflecting the variations in chlorophyll loss effects in different damaged forests were developed with spectral characteristics customized in A and C, and the texture features such as the mean, standard deviation, homogeneity, and shape index of the length–width ratio. An object-oriented method is used to determine the optimal segmentation scale for forest burn severity and a multilevel rule classification and extraction model is established to achieve the automatic identification and mapping. The results show that the method mentioned above can recognize different types of forest burn severity: unburned, damaged, dead, and burnt. The overall accuracy is 87.76%, and the Kappa coefficient is 0.8402, which implies that the small visible UAV can be used as a substitution for the current forest burn severity survey standards. This research is of great practical significance for improving the efficiency and precision of forest fire investigation, expanding applications of small UAVs in forestry, and developing an alternative for forest fire loss assessments in the forestry industry.

Accurate delineation of cardiac structures in CTA images remains challenging, due to the similar appearance of different components, the highly variable shape and intensity among individuals, and especially the vicinity of heart volumes and backgrounds (including fat tissues, great vessels, and livers). Therefore, we proposed an accurate heart volume segmentation method with landmark-based registration (LMR) and 3D fully convolutional network (3D-FCN). First, we defined uniformity constrained landmarks in the training images and then trained a regression forest model (RFM) to detect these landmarks in the testing image. Second, the registration between the landmarks in each training image and the test image was performed by a shallow neural network, which guided the label propagation from atlases to the test image. After the label fusion with majority voting, we finally constructed a 3D-FCN to further refine the boundary voxels with low voting values. In 22 cardiac CTA images, we compared our method with multi-atlas segmentation, active shape model, DeepMedic, LMR + DeepMedic, and the separately implemented LMR and 3D-FCN. The results demonstrated the superiority of our method for the segmentation of heart volumes, with the average accuracy, dice coefficient, and mean Hausdorff distance as 96.25%, 93.98%, and 2.12 voxels, respectively. Furthermore, the training efficiency of the constructed 3D-FCN was higher than that of the DeepMedic through the comparison of training time and convergence of loss. The proposed heart segmentation could provide an accurate region of interest (ROI) for not only the four heart chambers but also the major trunks of vessels and coronary arteries.

Polarimetric synthetic aperture radar (PolSAR) data provide an alternative way for topography retrieval, especially when limited PolSAR data are available. This article proposes a novel topography retrieval algorithm based on the Lambertian backscatter model that further improves the vertical precision of digital elevation model (DEM) generation and requires only one flight. The key idea of the proposed algorithm is to avoid data fluctuations caused by the ratio of the azimuth slope angle to the polarimetric orientation angle (POA). The previous research has confirmed the feasibility of generating a DEM based on single-pass PolSAR data, but its effect on the quality of reference DEM has not been well-explained. To analyze this effect, a large number of experiments on DEM with different resolutions are conducted. In addition, an in-depth analysis of non-linear and terrain-dependent errors is performed. The L-band PolSAR data of NASA/JPL TOPSAR and ALOS-2 PALSAR-2 and interferometric SAR (InSAR) DEM data are used to verify the proposed algorithm. The experimental results show that PolSAR data can be used as an additional reliable information source for DEM fusion under certain conditions to improve the quality of public DEM.

Traditionally, potholes are mainly paved for maintenance, and the asphalt mixture needs to be compacted. But due to the construction quality problem, the compacting degree of asphalt mixture may not be enough and the void ratio of asphalt mixture may not meet the requirements, resulting in the premature damage of the potholes after repair. If the repair material can be prefabricated, this problem will be well solved. So, based on the structure form of the prefabricated rapid maintenance of asphalt pavement, this paper aims to determine the most unfavorable loading position in pothole repair, which was established by the ANSYS software with the finite element model. The results show that the most unfavorable loading position of tensile stress for patch materials and joint filling material is C1-1 (A2-2) and the most unfavorable loading position of shear stress for joint filling material and leveling layer is B2-1 and C1-5. Subsequently, the influences of the material modulus, size, thickness, and modulus of the old pavement material on the potholes are calculated by using the finite element model under the most unfavorable loading position.

China has a low level of fertility after many years of births control by government intervention. Challenged by an aging and low-fertility population, China’s one-child policy was abolished in 2013 and two Quantitative Easing Population Policies (QEPP) implemented in its stead. Based on a study of population evolutions in two eastern provinces in China, this paper analyzes the local factors affecting birthrate and shows that social development and certain other control variables significantly impact fertility rates. Thus, QEPP alone cannot reverse the sinking fertility rate; other public services relating to health and family planning should be considered as well.

Calibration using corner reflectors is an effective way to estimate the distortion parameters of hybrid compact polarimetric (HCP) synthetic aperture radar (SAR) systems. However, the existing literature lacks a discussion on the inconsistency of the amplitude and phase coefficients between measured scattering vectors of different corner reflectors. In response to this problem, this paper first proves that this inconsistency will seriously deteriorate the estimation accuracy of polarimetric distortion parameters. Based on the optimization algorithm, two calibration schemes for simultaneously estimating the traditional distortion parameters and the amplitude/phase coefficients are proposed while ignoring crosstalk (ICT) and considering crosstalk (CCT). In the process of distortion parameter estimation, the idea of “optimizing while compensating” is adopted to eliminate the problem of uneven echo intensity. Simulation results show that both schemes can eliminate the influence of the inconsistency of amplitude and phase coefficients, and estimate distortion parameters accurately. When the received crosstalk level is lower than −30 dB, the ICT scheme can accurately estimate polarimetric distortion parameters. The CCT scheme has a wider application range of crosstalk and can work well when the crosstalk level is lower than −20 dB, but it also has a higher requirement for the signal-to-clutter ratio (SCR). When SCR is greater than 35 dB, the CCT scheme yields higher estimation accuracy than the ICT scheme. In addition, the effectiveness of the calibration schemes is verified based on the L-band measured data acquired by the Aerospace Information Research Institute, Chinese Academy of Sciences.

Due to the tortuosity and the complexity of cerebral vasculature and the similar intensity distribution with the background, it remains challenging to accurately segment cerebral vessels from magnetic resonance angiography (MRA). The previous rule-based methods have limitations when applied to accurate clinical diagnosis, such as the under-segmentation on complex vessels, the dependence on domain knowledge, and the lack of quantification estimation. In this paper, we proposed a semi-supervised cerebrovascular segmentation method with a hierarchical convolutional neural network (H-CNN) that transfers the exquisite model/feature design in rule-based methods to solve the mapping from MRA images to cerebral vessels. First, we generated the tube-level labels of cerebral vessels with centerlines and estimated radii. Second, we constructed and trained an H-CNN with the MRA images and corresponding tube-level labels. Third, the stopping criterion of the proposed H-CNN was determined by the comprehensive index (CI) that was defined based on partially annotated voxel-level ground truth. The comparison of our H-CNN with the vesselness, bi-Gaussian, optimally oriented flux, vessel enhancing diffusion, hybrid diffusion with continuous switch, Mimics software, convolutional neutral network2D (CNN)2D, and CNN3D were conducted on six testing images. The mean sensitivity, accuracy, and the CI of our H-CNN are 94.69%, 97.85%, and 2.99%, respectively, outperforming the other methods. The curved planar reformation also visualized the performance of H-CNN for cerebrovascular segmentation. Given only the tube-level labels, the proposed H-CNN method accomplished the voxel-level vessel segmentation via the hierarchical update of CNN. The H-CNN can potentially to be applied for the accurate diagnosis of cerebrovascular diseases and other medical image segmentation with only partially correct labels.

Micro-computed tomography (micro-CT) provides an in vivo high-resolution preclinical imaging for murine kidneys. However, due to the relatively low dosage of X-rays, accurate and efficient segmentation of murine kidneys in micro-CT imaging remains challenging. In this paper, we proposed an efficient kidney segmentation method in micro-CT images based on multi-atlas registration (MAR) and random forests (RFs). First, we constructed a probability map of kidneys by the MAR and obtained an initial shape estimation of kidneys. We acquired the transformations of MAR based on high-contrast organs and then mapped kidneys to the new micro-CT images. Second, we extracted multiple features (including intensity, texture, and context features) from the voxels with lower probabilities and fed these features to a RF classifier. The role of RF is to fine-tune kidney boundaries after MAR. Finally, combining the initial shape with high probabilities and the fine-tuning of RF, we obtained the final segmentation of kidneys. The experiments were conducted on datasets acquired by micro-CT imaging of mice with and without the administration of contrast agent (Dataset1 and Dataset2). The results demonstrated the proposed MAR-RF outperformed the level sets, statistical-atlas registration, active shape model, and other supervised learning methods, with the Dice coefficients of 0.9766 and 0.9255, and the mean surface distances of 1.25 and 0.98 mm on Dataset1 and Dataset2, respectively. The training and prediction time of our MAR-RF were only 37.04% and 17.68% of the compared method, respectively. The proposed method has great potential for applications in other segmentation tasks of computer-aided diagnosis.

As an essential step in the restoration of Terracotta Warriors, the results of fragments classification will directly affect the performance of fragments matching and splicing. However, most of the existing methods are based on traditional technology and have low accuracy in classification. A practical and effective classification method for fragments is an urgent need. In this case, an attention-based multi-scale neural network named AMS-Net is proposed to extract significant geometric and semantic features. AMS-Net is a hierarchical structure consisting of a multi-scale set abstraction block (MS-BLOCK) and a fully connected (FC) layer. MS-BLOCK consists of a local-global layer (LGLayer) and an improved multi-layer perceptron (IMLP). With a multi-scale strategy, LGLayer can parallel extract the local and global features from different scales. IMLP can concatenate the high-level and low-level features for classification tasks. Extensive experiments on the public data set (ModelNet40/10) and the real-world Terracotta Warrior fragments data set are conducted. The accuracy results with normal can achieve 93.52% and 96.22%, respectively. For real-world data sets, the accuracy is best among the existing methods. The robustness and effectiveness of the performance on the task of 3D point cloud classification are also investigated. It proves that the proposed end-to-end learning network is more effective and suitable for the classification of the Terracotta Warrior fragments.

As one of China′s most precious cultural relics, the excavation and protection of the Terracotta Warriors pose significant challenges to archaeologists. A fairly common situation in the excavation is that the Terracotta Warriors are mostly found in the form of fragments, and manual reassembly among numerous fragments is laborious and time-consuming. This work presents a fracture-surface-based reassembling method, which is composed of SiamesePointNet, principal component analysis (PCA), and deep closest point (DCP), and is named SPPD. Firstly, SiamesePointNet is proposed to determine whether a pair of point clouds of 3D Terracotta Warrior fragments can be reassembled. Then, a coarse-to-fine registration method based on PCA and DCP is proposed to register the two fragments into a reassembled one. The above two steps iterate until the termination condition is met. A series of experiments on real-world examples are conducted, and the results demonstrate that the proposed method performs better than the conventional reassembling methods. We hope this work can provide a valuable tool for the virtual restoration of three-dimension cultural heritage artifacts.

Lightning-ignited fire is sensitive to climatic change and responsible for large fires in boreal forests. In addition to global-warming caused fire increase, large-scale climate oscillations have significantly contributed to fire variability. However, the leading climate oscillation driving lightning-ignited fire and the mechanisms connecting regional and large-scale climate in the boreal forest of Northeast China, the most fire-prone biome of China, are still unclear. By compositing fire, climate, and atmospheric data, we found that the previous Atlantic Multidecadal Oscillation (AMO) was significantly coherent with the May to August temperature–evapotranspiration variability and lightning-ignited fire occurrence. These connections were valid at both the interannual and multidecadal time scales. Different from previous viewpoints, we found no connection of fire occurrence with the El Niño-Southern Oscillation and Pacific Decadal Oscillation. A warm AMO was followed by high sea level pressure and geopotential height over the study region. We assume these atmospheric anomalies are associated with descending atmospheric motion, producing adiabatic warming and less precipitation on the land surface, both of which favour high fuel aridity and lightning ignition. Therefore, we believe that the winter AMO could be a promising predictor for lightning-ignited fire occurrences in the following summer.

The air quality and human health impacts of wildfires depend on fire, meteorology, and demography. These properties vary substantially from one region to another in China. This study compared smoke from more than a dozen wildfires in Northeast, North, and Southwest China to understand the regional differences in smoke transport and the air quality and human health impacts. Smoke was simulated using the Hybrid Single Particle Lagrangian Integrated Trajectory Model (HYSPLIT) with fire emissions obtained from the Global Fire Emission Database (GFED). Although the simulated PM2.5 concentrations reached unhealthy or more severe levels at regional scale for some largest fires in Northeast China, smoke from only one fire was transported to densely populated areas (population density greater than 100 people/km2). In comparison, the PM2.5 concentrations reached unhealthy level in local densely populated areas for a few fires in North and Southwest China, though they were very low at regional scale. Thus, individual fires with very large sizes in Northeast China had a large amount of emissions but with a small chance to affect air quality in densely populated areas, while those in North and Southwest China had a small amount of emissions but with a certain chance to affect local densely populated areas. The results suggest that the fire and air quality management should focus on the regional air quality and human health impacts of very large fires under southward/southeastward winds toward densely populated areas in Northeast China and local air pollution near fire sites in North and Southwest China.

With widely availed clinically used radionuclides, Cerenkov luminescence imaging (CLI) has become a potential tool in the field of optical molecular imaging. However, the impulse noises introduced by high-energy gamma rays that are generated during the decay of radionuclide reduce the image quality significantly, which affects the accuracy of quantitative analysis, as well as the three-dimensional reconstruction. In this work, a novel denoising framework based on fuzzy clustering and curvature-driven diffusion (CDD) is proposed to remove this kind of impulse noises. To improve the accuracy, the Fuzzy Local Information C-Means algorithm, where spatial information is evolved, is used. We evaluate the performance of the proposed framework systematically with a series of experiments, and the corresponding results demonstrate a better denoising effect than those from the commonly used median filter method. We hope this work may provide a useful data pre-processing tool for CLI and its following studies.

As an emerging molecular imaging modality, cone-beam X-ray luminescence computed tomography (CB-XLCT) uses X-ray-excitable probes to produce near-infrared (NIR) luminescence and then reconstructs three-dimensional (3D) distribution of the probes from surface measurements. A proper photon-transportation model is critical to accuracy of XLCT. Here, we presented a systematic comparison between the common-used Monte Carlo model and simplified spherical harmonics (SPN). The performance of the two methods was evaluated over several main spectrums using a known XLCT material. We designed both a global measurement based on the cosine similarity and a locally-averaged relative error, to quantitatively assess these methods. The results show that the SP3 could reach a good balance between the modeling accuracy and computational efficiency for all of the tested emission spectrums. Besides, the SP1 (which is equivalent to the diffusion equation (DE)) can be a reasonable alternative model for emission wavelength over 692nm. In vivo experiment further demonstrates the reconstruction performance of the SP3 and DE. This study would provide a valuable guidance for modeling the photon-transportation in CB-XLCT.