Automatic Algorithm Research Articles

Research on the application of automatic control theory in automatic driving technology

Autonomous driving technology has been widely used and studied in depth in recent years, and has become a hot field in the automotive industry. As one of the core methods to realize automatic driving, automatic control theory provides an important theoretical basis and practical guidance for automatic driving systems. This paper aims to explore the application of automatic control theory to autonomous driving and analyze its potential impact on improving driving safety, comfort and efficiency. This paper first introduces the basic principles and components of the autonomous driving system. Among them, automatic control theory plays an important role in decision-making and execution. Secondly, this paper discusses the specific application of automatic control theory in automatic driving. These include PID controller-based vehicle stability control, model predictive control (MPC) for path planning and trajectory tracking. These applications enable autonomous driving systems to respond in real time to environmental changes and maintain vehicle stability and safety. Finally, the paper discusses the challenges and future directions of automatic control theory in autonomous driving. Future research should focus on further improving the robustness and adaptability of automatic control algorithms to cope with complex driving scenarios and uncertainties. To sum up, automatic control theory plays an important role in automatic driving and has broad application prospects. Through continuous improvement and innovation, automatic control theory will make an important contribution to the realization of safer, more efficient, and more intelligent autonomous driving technology.

Multi-Objective Automatic Clustering Algorithm Based on Evolutionary Multi-Tasking Optimization

Data mining technology is the process of extracting hidden knowledge and potentially useful information from a large number of incomplete, noisy, and random practical application data. The clustering algorithm based on multi-objective evolution has obvious advantages compared with the traditional single-objective method. In order to further improve the performance of evolutionary multi-objective clustering algorithms, this paper proposes a multi-objective automatic clustering model based on evolutionary multi-task optimization. Based on the multi-objective clustering algorithm that automatically determines the value of k, evolutionary multi-task optimization is introduced to deal with multiple clustering tasks simultaneously. A set of non-dominated solutions for clustering results is obtained by concurrently optimizing the overall deviation and connectivity index. Multi-task adjacency coding based on a locus adjacency graph was designed to encode the clustered data. Additionally, an evolutionary operator based on relevance learning was designed to facilitate the evolution of individuals within the population. It also facilitates information transfer between individuals with different tasks, effectively avoiding negative transfer. Finally, the proposed algorithm was applied to both artificial datasets and UCI datasets for testing. It was then compared with traditional clustering algorithms and other multi-objective clustering algorithms. The results verify the advantages of the proposed algorithm in clustering accuracy and algorithm convergence.

REPOLARIZATION GRADIENT CAUSES LOCAL DEPOLARIZATION ABNORMALITIES IN BRUGADA SYNDROME

Abstract Background Transmural voltage gradient in RVOT induces ECG–phenotype in Brugada syndrome(BrS). Moreover,RVOT depolarization abnormalities have been described as contributors to BrS phenotype and arrhythmogenesis. Purpose To investigate the effect of ajmaline administration on J–elevation of RVOT unipolar signals in BrS patients. Moreover,we wanted to assess whether ajmaline–induced unipolar J–point elevation variations induced local depolarization abnormalities. Methods 21 BrS patients with spontaneous type–1 ECG pattern were enrolled. Due to the absence of BrS ECG pattern at the study, patients underwent RV endocardial mapping with the CARTO3 system, before (PRE) and after (POST) ajmaline administration. The data were exported from CARTO and converted into Matlab format using OpenEP. J–elevation for each point was calculated as the amplitude of the unipolar signal at J wave with respect to baseline. Activation time (AT) of each point was defined as the difference between local depolarization (minimum dV/dt of the unipolar signal) and surface ECG depolarization(time of the minimum signal on V2). With an automatic algorithm, corresponding PRE and POST points were selected. The difference between POST and PRE of each parameter was calculated to obtain the differential values delta–J and delta–AT. Differential values were then interpolated on the mesh of each subject to obtain 3D maps. The deltaJ map was divided into four intervals based on quartiles. We then selected a ROI ‘IN‘ on a region with the greatest deltaJ variation, and a second ROI ‘OUT‘ on the zone of lowest variation. The same ROIs were applied to the deltaAT map. The mean value of the respective differential parameters was extracted in each ROI. Results Greatest delta–J values were found in the RVOT/anterior wall. delta–J in the ROI ‘IN‘ was greater than in the ROI ‘OUT‘ (1.68 [1.11–2.28] vs 0.56 [0.38–0.93] mV, p<0.001). delta–AT in the ROI ‘IN’ was greater than in the ROI ‘OUT’ (27.96 [20.39–44.89] vs 7.62 [4.24–16.69] ms, p<0.001). A good correlation was found between delta–J and delta–AT, considering the data for the two ROIs together (Spearman R coefficient=0.71, p<0.001). Conclusions: Our study shows that the repolarization gradient, evaluated by localized delta–J increase in RVOT, justifies BrS ECG phenotype and local depolarization abnormalities. A strong correlation was present in these RVOT areas between J–elevation variation and slow conducting zones.

Crater Detection and Population Statistics in Tianwen-1 Landing Area Based on Segment Anything Model (SAM)

Crater detection is useful for research into dating a planetary surface’s age and geological mapping. The high-resolution imaging camera (HiRIC) carried by the Tianwen-1 rover provides digital image model (DIM) datasets with a resolution of 0.7 m/pixel, which are suitable for detecting meter-scale craters. The existing deep-learning-based automatic crater detection algorithms require a large number of crater annotation datasets for training. However, there is currently a lack of datasets of optical images of small-sized craters. In this study, we propose a model based on the Segment Anything Model (SAM) to detect craters in Tianwen-1’s landing area and perform statistical analysis. The SAM network was used to obtain a segmentation mask of the craters from the DIM images. Then non-circular filtering was used to filter out irregular craters. Finally, deduplication and removal of false positives were performed to obtain accurate circular craters, and their center’s position and diameter were obtained through circular fitting analysis. We extracted 841,727 craters in total, with diameters ranging from 1.57 m to 7910.47 m. These data are useful for further Martian crater catalogs and crater datasets. Additionally, the crater size–frequency distribution (CSFD) was also analyzed, indicating that the surface ages of the Tianwen-1 landing area are ~3.25 billion years, with subsequent surface resurfacing events occurring ~1.67 billion years ago.

Research on and Application of Feature Recognition and Intelligent Retrieval Method for Multi-Component Alloy Powder Injection Molding Gear Based on Partition Templates

The forming process of multi-alloy gears by metal powder injection molding is tedious, and the current design process mainly depends on the experience of designers, which seriously affects the product development cycle and forming quality. In order to solve the problem of the gear feature expression being missing, which hinders the automatic retrieval of similar parts in the analogical design process, a feature recognition and intelligent retrieval method for a multi-alloy powder injection molding gear based on partition templates is proposed in this paper. The partition templates of the gear are defined, and gear digitization is completed by using the automatic recognition algorithm. Searching for similar gear parts in the knowledge base, designers can analogically design the forming process for new parts according to the mature process of the parts in the knowledge base. The automatic identification and intelligent retrieval system developed according to this method has been implemented in two MIM (metal injection molding) product manufacturing enterprises. Case studies and industrial applications have proved the effectiveness of the system, the efficiency of identification and retrieval has been improved by more than 97%, and the number of mold tests has been reduced by 60%.

Self-Adaptive Incremental PCA-Based DBSCAN of Acoustic Features for Anomalous Sound Detection

In modern industry, maintaining continuous machine operations is important for improving production efficiency and reducing costs. Therefore, the smart technology of acoustic monitoring to detect anomalous machine conditions earlier before breakdowns works as part of predictive maintenance and is applied not only in industry fault detection but also in safety monitoring and surveillance systems. This paper proposes a self-adaptive unsupervised machine learning algorithm with dimension-reduction technology to detect anomalous sounds after extracting acoustic machine features. Technically, the automatic EPS calculation algorithm-based genetic algorithm optimizes the automatic clustering algorithm’s configuration for incremental principal component analysis and density-based spatial clustering algorithms with noise. IPCA is enhanced by the sequential Karhunen–Loeve (SKL) algorithm, and the condensation algorithm works as the second layer of the algorithm to reduce the number of effective components. This architecture could select an optimized set of parameters based on different test environments and keeps performance quality with fewer computational requirements. In the experiments, 228 sets of normal sounds and 100 sets of anomaly sounds are used. The sound files are collected from the same machine type (stepper motors) at a real plant site. We compare the proposed algorithm with K-means++, one-class SVM, agglomerative clustering, DCGAN and DCNN-Autoencoder, and this new algorithm performs best, with an AUC of 0.84 and the shortest execution time. The algorithm is generic and can be applied to detect anomalies in machines to provide early warning to people to avoid serious accidents or disasters.

An optimized framework for processing multicentric polysomnographic data incorporating expert human oversight

IntroductionPolysomnographic recordings are essential for diagnosing many sleep disorders, yet their detailed analysis presents considerable challenges. With the rise of machine learning methodologies, researchers have created various algorithms to automatically score and extract clinically relevant features from polysomnography, but less research has been devoted to how exactly the algorithms should be incorporated into the workflow of sleep technologists. This paper presents a sophisticated data collection platform developed under the Sleep Revolution project, to harness polysomnographic data from multiple European centers.MethodsA tripartite platform is presented: a user-friendly web platform for uploading three-night polysomnographic recordings, a dedicated splitter that segments these into individual one-night recordings, and an advanced processor that enhances the one-night polysomnography with contemporary automatic scoring algorithms. The platform is evaluated using real-life data and human scorers, whereby scoring time, accuracy, and trust are quantified. Additionally, the scorers were interviewed about their trust in the platform, along with the impact of its integration into their workflow.ResultsWe found that incorporating AI into the workflow of sleep technologists both decreased the time to score by up to 65 min and increased the agreement between technologists by as much as 0.17 κ.DiscussionWe conclude that while the inclusion of AI into the workflow of sleep technologists can have a positive impact in terms of speed and agreement, there is a need for trust in the algorithms.

Intelligent in-process enhancement technique for machining efficiency in CNC machine tools based on spindle power

In the realm of mechanical machining, adaptive machining techniques offer an efficient method. However, existing adaptive machining technologies cannot automatically identify the type of workpiece to be machined, nor can they set different control targets based on tool load-bearing capacity. This often requires manual and cumbersome operations, making the application of adaptive machining technology difficult to popularize. To address these challenges, this paper proposes an intelligent and efficient adaptive machining method. Specifically, a workpiece automatic classification algorithm based on machine tool spindle power is introduced. This algorithm classifies the machined workpieces according to the collected spindle power data, enhancing the convenience of adaptive machining technology. Also based on spindle power data, a time-series segmentation method is proposed, dividing spindle power into different subsequences according to the tools used in machining, which enhances the accuracy of adaptive machining technology. Furthermore, an adaptive feed rate control algorithm is designed based on fuzzy control theory, realizing intelligent and efficient adaptive machining of workpieces to improve machining efficiency. Finally, experiments are conducted to validate the effectiveness of the intelligent and efficient adaptive machining method. The proposed method effectively addresses the drawbacks of existing adaptive machining method, which require complex parameter settings. It simplifies the operational process, enhances the intelligence, and improves the practical applicability of adaptive machining techniques. This represents an innovative contribution to the field of adaptive machining techniques.

Enhancing Brain Tumor Classification: A CNN-Based Approach with InceptionV3 and Xception

Brain tumors are among the most aggressive and deadly diseases, with a very short life expectancy at the highest grade. To combat this, early detection and treatment are crucial.In this approach, MRI images are used to analyze brain abnormalities. The manual investigation of brain tumor classification is a time-consuming task, and there might be possibilities of human errors. Hence, accurate analysis in a short span of time is essential. This approach presents the automatic brain tumor classification algorithm using a highly accurate Convolutional Neural Network (CNN), InceptionV3 and Xception algorithm for classification of Glioma, Meningioma and No tumor. The brain part is initially segmented by a thresholding approach followed by a morphological operation. The brain MRI is classified using CNN, Inceptionv3, and Xceptionv3 algorithms. The system's performance is evaluated using precision, recall, F1 score, and accuracy parameters.

Automated sleep staging on reduced channels in children with epilepsy

ObjectivesThis study aimed to validate a sleep staging algorithm using in-hospital video-electroencephalogram (EEG) in children without epilepsy, with well-controlled epilepsy (WCE), and with drug-resistant epilepsy (DRE).MethodsOvernight video-EEG, along with electrooculogram (EOG) and chin electromyogram (EMG), was recorded in children between 4 and 18 years of age. Classical sleep staging was performed manually as a ground truth. An end-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging (SeqSleepNet) was used to perform automated sleep staging using three channels: C4-A1, EOG, and chin EMG.ResultsIn 176 children sleep stages were manually scored: 47 children without epilepsy, 74 with WCE, and 55 with DRE. The 5-class sleep staging accuracy of the automatic sleep staging algorithm was 84.7% for the children without epilepsy, 83.5% for those with WCE, and 80.8% for those with DRE (Kappa of 0.79, 0.77, and 0.73 respectively). Performance per sleep stage was assessed with an F1 score of 0.91 for wake, 0.50 for N1, 0.83 for N2, 0.84 for N3, and 0.86 for rapid eye movement (REM) sleep.ConclusionWe concluded that the tested algorithm has a high accuracy in children without epilepsy and with WCE. Performance in children with DRE was acceptable, but significantly lower, which could be explained by a tendency of more time spent in N1, and by abundant interictal epileptiform discharges and intellectual disability leading to less recognizable sleep stages. REM sleep time, however, significantly affected in children with DRE, can be detected reliably by the algorithm.Clinical trial registration: ClinicalTrials.gov, identifier NCT04584385.

Deep learning for automatic segmentation of vestibular schwannoma: a retrospective study from multi-center routine MRI

Automatic segmentation of vestibular schwannoma (VS) from routine clinical MRI has potential to improve clinical workflow, facilitate treatment decisions, and assist patient management. Previous work demonstrated reliable automatic segmentation performance on datasets of standardized MRI images acquired for stereotactic surgery planning. However, diagnostic clinical datasets are generally more diverse and pose a larger challenge to automatic segmentation algorithms, especially when post-operative images are included. In this work, we show for the first time that automatic segmentation of VS on routine MRI datasets is also possible with high accuracy. We acquired and publicly release a curated multi-center routine clinical (MC-RC) dataset of 160 patients with a single sporadic VS. For each patient up to three longitudinal MRI exams with contrast-enhanced T1-weighted (ceT1w) (n = 124) and T2-weighted (T2w) (n = 363) images were included and the VS manually annotated. Segmentations were produced and verified in an iterative process: (1) initial segmentations by a specialized company; (2) review by one of three trained radiologists; and (3) validation by an expert team. Inter- and intra-observer reliability experiments were performed on a subset of the dataset. A state-of-the-art deep learning framework was used to train segmentation models for VS. Model performance was evaluated on a MC-RC hold-out testing set, another public VS datasets, and a partially public dataset. The generalizability and robustness of the VS deep learning segmentation models increased significantly when trained on the MC-RC dataset. Dice similarity coefficients (DSC) achieved by our model are comparable to those achieved by trained radiologists in the inter-observer experiment. On the MC-RC testing set, median DSCs were 86.2(9.5) for ceT1w, 89.4(7.0) for T2w, and 86.4(8.6) for combined ceT1w+T2w input images. On another public dataset acquired for Gamma Knife stereotactic radiosurgery our model achieved median DSCs of 95.3(2.9), 92.8(3.8), and 95.5(3.3), respectively. In contrast, models trained on the Gamma Knife dataset did not generalize well as illustrated by significant underperformance on the MC-RC routine MRI dataset, highlighting the importance of data variability in the development of robust VS segmentation models. The MC-RC dataset and all trained deep learning models were made available online.

Adaptive parameter local consistency automatic outlier removal algorithm for area-based matching

Abstract. Due to the influence of image differences and matching methods, geometric calibration of remote sensing images often results in the extraction of control points with inevitable outliers. Moreover, it is susceptible to limitations imposed by locally constrained outlier rejection methods, making it challenging to automatically remove relatively small gross errors. This paper introduces an adaptive parameter local consistency automatic outlier removal algorithm, referred to as APLC. Initially, we construct k-nearest neighbors for each pair of matching points, deriving distance and topological uncertainty based on the accuracy of point matching. Subsequently, we conduct cross-validation on the uncertainty between the two pairs of vectors formed by points within the neighborhood, aiming for parameter adaptation. Finally, a cost-defined function is introduced to assess the consistency of local structures. Through a two-stage outlier removal strategy, matching points that do not maintain local structural consistency are eliminated. To assess the effectiveness of the proposed algorithm, we conduct experimental comparisons using region-based initial matching results from the FY-3D remote sensing dataset, demonstrating its superiority compared to three state-of-the-art methods.

Automatic generation of pipelines from 2D CAD drawings to 3D IFC models using a parametric method

Creating 3D models of pipelines is essential for effective digital building management. However, generating 3D pipeline models from 2D CAD drawings still heavily depends on human-computer interaction at the design stage. This paper addresses this challenge by proposing a method to generate parametric 3D pipeline models from CAD drawings automatically. The framework includes three parts. Firstly, automatic layer recognition algorithms are used to extract data from CAD drawings, and algorithms are designed to match pipeline coordinates and diameters. Then, data on straight pipes is processed, including judging types of pipe fittings and calculating relevant parameters to realize the automatic generation of 3D BIM models. Finally, IFC is utilized to express the geometry and topology of models for BIM model generation. The process is implemented by writing a C++ program in Visio Studio 2019. Experimental results on a building water supply and drainage system demonstrate that the proposed method can significantly improve the generation efficiency and automation level of pipeline models.

Realtime Selection of Optimal Source Parameters Using Ground Motion Envelopes

It is increasingly common for seismic networks to operate multiple independent automatic algorithms to characterise earthquakes in real-time, such as in earthquake early warning (EEW) or even standard network practice. Commonly used methods to select the best solution at a given time are simple and use ad hoc rules. An absolute measure of how well a solution (event origin and magnitude) matches the observations by the goodness-of-fit between the observed and predicted envelopes is a robust and independent metric to select optimal solutions. We propose such a measure that is calculated as a combination of amplitude and cross-correlation fit. This metric can be used to determine when a preferred solution reaches an appropriate confidence level for alerting, or indeed to compare two (or more) different event characterisations directly. We demonstrate that our approach can also be used to suppress false alarms commonly seen at seismic networks. Tests using the 10 largest earthquakes in Switzerland between 2013 and 2020, and events that caused false alarms demonstrate that our approach can effectively prefer solutions with small errors in location and magnitude, and can clearly identify and discard false origins or incorrect magnitudes, at all time scales, starting with the first event characterisation.

Compact pixelated scintillator detector investigation for gamma ray detection

Objective. A scintillator is a luminescent material that converts high-energy photons into visible light and is widely used in medical imaging. Different scintillators are applied to gamma imaging in proton therapy and boron neutron capture therapy (BNCT). A pixelated scintillator is suitable for position measurement. The energy resolution, detection efficiency and position measurement of pixelated scintillators coupled to a SiPM were investigated via two kinds of detectors. The goal of this manuscript was to accurately measure the gamma source position through spectrum analysis in selection of energy windows for characteristic gamma lines. Approach. Scintillators were effectively manufactured and encapsulated before testing, especially for the easily deliquescent LaBr3. The compact front-end electronic prototype modules with 2 × 2 array SiPMs in stacked form and 1 × 10 array SiPMs in parallel form were developed for gamma ray energy resolution and efficiency measurements with a radioactive source of 22Na, which had two energy gamma lines at 511 keV and 1274 keV. Energy calibration was used for accurate energy window selection when measuring the position of the gamma source. Main results. Evident inconsistencies were present between different pixels of the same type of scintillator. Thus, an energy calibration method was needed. LaBr3 was the first candidate scintillator for the gamma ray spectrum measurement since it exhibited the best performance with an energy resolution of ∼5%. The recommended size of LaBr3 was 5 × 5 mm2, which had a higher efficiency than the 3 × 3 mm2 size. The gamma count of the multiple mode of the 2 × 2 array was much higher than that of the single mode, while the energy resolution was poorer. Thus, multiple mode was not suitable for gamma ray detection. The 1 × 10 array detector had the potential to measure the gamma ray source position and could be used for proton therapy and BNCT. A small deviation of 0.22 cm was observed in the measurement of the source center position with Energy Window 1 for 511 keV and Energy Window 2 for 1274 keV before the energy calibration. No deviation was observed after energy calibration. Thus, to achieve a higher accuracy position measurement, automatic energy calibration algorithm was coded into data acquisition software. Significance. The characteristic gamma lines produced by particle therapy are abundant and useful for imaging technology. Our developed compact pixelated scintillator detector coupled with SiPMs could measure the gamma spectrum with high resolution. The energy calibration and window selection method could measure the position of the source with high accuracy. Therefore, an advanced imaging device based on the energy spectrum for particle therapy could be potentially attainable.

Automatic detection method of bladder tumor cells based on color and shape features

Bladder urothelial carcinoma is the most common malignant tumor disease in urinary system, and its incidence rate ranks ninth in the world. In recent years, the continuous development of hyperspectral imaging technology has provided a new tool for the auxiliary diagnosis of bladder cancer. In this study, based on microscopic hyperspectral data, an automatic detection algorithm of bladder tumor cells combining color features and shape features is proposed. Support vector machine (SVM) is used to build classification models and compare the classification performance of spectral feature, spectral and shape fusion feature, and the fusion feature proposed in this paper on the same classifier. The results show that the sensitivity, specificity, and accuracy of our classification algorithm based on shape and color fusion features are 0.952, 0.897, and 0.920, respectively, which are better than the classification algorithm only using spectral features. Therefore, this study can effectively extract the cell features of bladder urothelial carcinoma smear, thus achieving automatic, real-time, and noninvasive detection of bladder tumor cells, and then helping doctors improve the efficiency of pathological diagnosis of bladder urothelial cancer, and providing a reliable basis for doctors to choose treatment plans and judge the prognosis of the disease.

Exploring mm-Wavelength Radar Capabilities for Raindrop Size Distribution Retrieval: Estimating Mass-weighted Mean Diameter from the Differential Backscatter Phase

Abstract Accurate precipitation characterization relies on the estimation of raindrop size distribution (RDSD) from observations. While various techniques using cm-wavelength radars have been proposed for RDSD retrieval, the potential of mm-wavelength polarimetric radars, offering enhanced spatial and temporal resolution while capturing light to moderate rain, remains unexplored. This study focuses on retrieving the mass-weighted mean volume diameter (Dm) using a dual frequency cloud radar. Since the differential reflectivity (Zdr) is ineffective for Dm retrieval at 94 GHz, and simulations demonstrate a strong dependence of the differential backscatter phase (δco) on Dm, the estimation of δco takes precedence in this paper. Notably, δco remains unaffected by attenuation and polarimetric calibration. Addressing the initial requirement of disentangling backscattering and propagation effects at mm-wavelength, an automatic algorithm is proposed to detect Rayleigh plateaus in the spectral domain. Subsequently, a methodology for estimating δco and its associated error is presented. Leveraging simulation results, confidence intervals for Dm that align with δco confidence intervals are retrieved. The assessment of Dm and its confidence interval at 35 and 94 GHz is conducted employing disdrometer-derived Dm. The results demonstrate a comprehensive concordance within a margin of 0.2 mm, underscoring the cloud radar's efficacy in delineating nuanced variations in raindrop mean diameter versus altitude. The validation process encounters difficulties for Dm below 1 mm, as the disdrometer-derived Dm may exhibit an overestimation, while the cloud radar-derived Dm may exhibit an underestimation. The combination of 35 and 94 GHz serves to diminish the confidence interval associated with the retrieved Dm.

Mapping global lake aquatic vegetation dynamics using 10-m resolution satellite observations

Aquatic vegetation is crucial for improving water quality, supporting fisheries and preserving biodiversity in lakes. Monitoring the spatiotemporal dynamics of aquatic vegetation is indispensable for the assessment and protection of lake ecosystems. Nevertheless, a comprehensive global assessment of lacustrine aquatic vegetation is lacking. This study introduces an automatic identification algorithm (with a total accuracy of 94.4%) for Sentinel-2 MSI, enabling the first-ever global mapping of aquatic vegetation distribution in 1.4 million lakes using 14.8 million images from 2019 to 2022. Results show aquatic vegetation occurred in 81,116 lakes across six continents over past four years, covering a cumulative maximum aquatic vegetation area (MVA) of 16,111.8 km2. Global median aquatic vegetation occurrence (VO, in %) is 3.0%, with notable higher values observed in South America (7.4%) and Africa (4.1%) compared to Asia (2.7%) and North America (2.4%). High VO is also observed in lakes near major rivers such as the Yangtze, Ob, and Paraná Rivers. Integrating historical data with our calculated MVA, aquatic vegetation changes in 170 lakes worldwide were analyzed. It shows that 72.4% (123/170) of lakes witnessed a decline in aquatic vegetation from the early 1980s to 2022, encompassing both submerged and total aquatic vegetation. The most substantial decrease is found in Asia and Africa. Our findings suggest that, beyond lake algal blooms and temperature, the physical characteristics of the lakes and their surrounding environments could also influence aquatic vegetation distribution. Our research provides valuable information for the lacustrine aquatic vegetation conservation and restoration.

Discovering optimal kinetic pathways for self-assembly using automatic differentiation

Macromolecular complexes are often composed of diverse subunits. The self-assembly of these subunits is inherently nonequilibrium and must avoid kinetic traps to achieve high yield over feasible timescales. We show how the kinetics of self-assembly benefits from diversity in subunits because it generates an expansive parameter space that naturally improves the "expressivity" of self-assembly, much like a deeper neural network. By using automatic differentiation algorithms commonly used in deep learning, we searched the parameter spaces of mass-action kinetic models to identify classes of kinetic protocols that mimic biological solutions for productive self-assembly. Our results reveal how high-yield complexes that easily become kinetically trapped in incomplete intermediates can instead be steered by internal design of rate-constants or external and active control of subunits to efficiently assemble. Internal design of a hierarchy of subunit binding rates generates self-assembly that can robustly avoid kinetic traps for all concentrations and energetics, but it places strict constraints on selection of relative rates. External control via subunit titration is more versatile, avoiding kinetic traps for any system without requiring molecular engineering of binding rates, albeit less efficiently and robustly. We derive theoretical expressions for the timescales of kinetic traps, and we demonstrate our optimization method applies not just for design but inference, extracting intersubunit binding rates from observations of yield-vs.-time for a heterotetramer. Overall, we identify optimal kinetic protocols for self-assembly as a powerful mechanism to achieve efficient and high-yield assembly in synthetic systems whether robustness or ease of "designability" is preferred.

A New Automatic Hydrological Station Relocation Algorithm (ASRA) for Moving Hydrological Stations Onto a Simulated Digital River Network

A New Automatic Hydrological Station Relocation Algorithm (ASRA) for Moving Hydrological Stations Onto a Simulated Digital River Network