Data Pool Research Articles

Data-driven design for enhanced efficiency of Sn-based perovskite solar cells using machine learning

In this study, a novel three-step learning-based machine learning (ML) methodology is developed utilizing 26 000 experimental records from The Perovskite Database Project. A comprehensive set of 29 features encompassing both categorical and numerical data was utilized to train various ML models for various solar cell performance metrics, including open-circuit voltage (VOC), short-circuit current (JSC), fill factor (FF), and power conversion efficiency (PCE). The model accuracy was assessed using four key metrics: mean absolute error, mean square error, root mean square error, and R2 score. Among the constructed models, random forest (RF) emerged as the standout performer, boasting an R2 score of 0.70 for PCE. This RF model was then used for prediction on the large, optimized design pool of Sn-based perovskite data with intent to probe a viable non-toxic substitute to the standard Pb-based absorber. A three-step algorithm was tailored, which led to the discovery of a new set of feature combinations, showcasing a PCE improvement over the existing peak performance of Sn-based devices. The key aspects identified were device architecture, dimensionality, and deposition procedures for essential layers, including the electron transport layer, the hole transport layer, the perovskite absorber layer, and the back-contact. Through consideration of these features, an impressive increase in PCE was achieved. There was a 28.35% increase in PCE from 12.24% to 15.71% for architecture optimization and a 24.6% increase in PCE from 12.24% to 15.25% for deposition method optimization. This study additionally addresses the effective implementation of target encoding applied to a diverse set of categorical feature labels. The data-driven methodology proposed in this study allows scientists to efficiently identify an optimal architecture and deposition parameters for non-toxic Sn-based perovskite materials with a much higher anticipated device PCE compared to traditional trial-and-error analyses. Further exploration and exploitation of the current investigation is expected to lead to successful and sustainable development of highly efficient Sn-based perovskite solar cells.

Evaluation of early skin cancer detection in Germany with cancer registry data - challenges, solutions and current trends.

The evidence for the benefit of the skin cancer screening introduced in Germany in 2008 is weak. We investigate to what extent data from the German epidemiological cancer registries are suitable to contribute to the evaluation of skin cancer screening and report these evaluation results. Skin cancer-related cancer registry data from 1999-2019 were described in terms of completeness and comprehensiveness. Regional pools with data of different validity were defined, missing data were multiply imputed where appropriate, and temporal trends were analyzed. In addition, data from the cause of death statistics were used. Reliable estimates of completeness are only available for malignant melanoma (ICD-10: C43). Based on a regional data pool covering approximately 21% of the German population, melanoma-related incidence can be validly described since 2005. Sufficient information for multiple imputation is available for T-stage and localization. The trend analyses show incidence changes that can be expected in the short term in the temporal context of the introduction of early detection, which changes into a long-lasting high incidence. The rate of advanced stages does not decrease significantly. From 2014 onwards, the melanoma mortality rate, which had been rising until then, decreases. Adequately selected and processed cancer registry data are suitable for population-based evaluation of skin cancer screening. An explanation of the persistently high incidence level is not possible based on the cancer registry data. Overdiagnosis or an increase in the background incidence can be considered. The benefit of skin cancer screening remains open.

Estimation of uplift and erosion in the Miri area of northwest Sarawak, Malaysia: A multidisciplinary approach

The question of uplift in the Sarawak Foreland is addressed in a multi-disciplinary approach, namely by assigning surface vitrinite reflectance measurements to depth, and by vitrinite reflectance-to-depth conversion using functions from two previous studies. Additional erosion and uplift data were obtained by comparing eroded anticlinal crests with adjacent synclines and their preserved sediments. The combined data pool suggests two types of uplift (I) a regional uplift in the Neogene affecting the entire coastal area, and (II) a tectonically focused uplift. The amount of the latter uplift and erosion is directly linked to rise of anticlinal structures during the Upper Pliocene, with a total uplift ranging from 700 to 4,000 m in areas along prominent regional faults. Within a very short time window major sedimentation, folding, trap formation and trap destruction took place both as a consequence of folding and erosion. Only anticlines in the offshore and the proximal onshore appear to have survived without major crestal erosion. Since the end of the Pleistocene, a rise of foreland sections by some 132 m is recognized. The rapid Pliocene burial and the erosion that consequently removed the overburden thereafter may have negatively affected the petroleum system and hydrocarbon accumulation within the Miri area, which was left largely intact only in the Siwa-Seria anticlinal trend. All anticlines were targeted by petroleum exploration. However, only the Siwa-Seria trend has proved to be economically successful. This has highlighted the significance of overburden in relation to depth of burial and the thermal effect needed to mature the source rocks capable to generate hydrocarbons.

Machine learning code snippets semantic classification

Program code has recently become a valuable active data source for training various data science models, from code classification to controlled code synthesis. Annotating code snippets play an essential role in such tasks. This article presents a novel approach that leverages CodeBERT, a powerful transformer-based model, to classify code snippets extracted from Code4ML automatically. Code4ML is a comprehensive machine learning code corpus compiled from Kaggle, a renowned data science competition platform. The corpus includes code snippets and information about the respective kernels and competitions, but it is limited in the quality of the tagged data, which is ~0.2%. Our method addresses the lack of labeled snippets for supervised model training by exploiting the internal ambiguity in particular labeled snippets where multiple class labels are combined. Using a specially designed algorithm, we effectively separate these ambiguous fragments, thereby expanding the pool of training data. This data augmentation approach greatly increases the amount of labeled data and improves the overall quality of the trained models. The experimental results demonstrate the prowess of the proposed code classifier, achieving an impressive F1 test score of ~89%. This achievement not only enhances the practicality of CodeBERT for classifying code snippets but also highlights the importance of enriching large-scale annotated machine learning code datasets such as Code4ML. With a significant increase in accurately annotated code snippets, Code4ML is becoming an even more valuable resource for learning and improving various data processing models.

Financial sentiment analysis: Classic methods vs. deep learning models

Sentiment Analysis, also known as Opinion Mining, gained prominence in the early 2000s alongside the emergence of internet forums, blogs, and social media platforms. Researchers and businesses recognized the imperative to automate the extraction of valuable insights from the vast pool of textual data generated online. Its utility in the business domain is undeniable, offering actionable insights into customer opinions and attitudes, empowering data-driven decisions that enhance products, services, and customer satisfaction. The expansion of Sentiment Analysis into the financial sector came as a direct consequence, prompting the adaptation of powerful Natural Language Processing models to these contexts. In this study, we rigorously test numerous classical Machine Learning classification algorithms and ensembles against five contemporary Deep Learning Pre-Trained models, like BERT, RoBERTa, and three variants of FinBERT. However, its aim extends beyond evaluating the performance of modern methods, especially those designed for financial tasks, to a comparison of them with classical ones. We also explore how different text representation and data augmentation techniques impact classification outcomes when classical methods are employed. The study yields a wealth of intriguing results, which are thoroughly discussed.

Active learning for data streams: a survey

Online active learning is a paradigm in machine learning that aims to select the most informative data points to label from a data stream. The problem of minimizing the cost associated with collecting labeled observations has gained a lot of attention in recent years, particularly in real-world applications where data is only available in an unlabeled form. Annotating each observation can be time-consuming and costly, making it difficult to obtain large amounts of labeled data. To overcome this issue, many active learning strategies have been proposed in the last decades, aiming to select the most informative observations for labeling in order to improve the performance of machine learning models. These approaches can be broadly divided into two categories: static pool-based and stream-based active learning. Pool-based active learning involves selecting a subset of observations from a closed pool of unlabeled data, and it has been the focus of many surveys and literature reviews. However, the growing availability of data streams has led to an increase in the number of approaches that focus on online active learning, which involves continuously selecting and labeling observations as they arrive in a stream. This work aims to provide an overview of the most recently proposed approaches for selecting the most informative observations from data streams in real time. We review the various techniques that have been proposed and discuss their strengths and limitations, as well as the challenges and opportunities that exist in this area of research.

Analyzing Sentiment with Self-Organizing Map and Long Short-Term Memory Algorithms

This research delves into the impact of Chat Generative Pre-trained Transformer, one of Open Artificial Intelligence Generative Pretrained Transformer models. This model underwent extensive training on a vast corpus of internet text to gain insights into the mechanics of human language and its role in forming phrases, sentences, and paragraphs. The urgency of this inquiry arises from Chat Generative Pre-trained Transformer emergence, which has stirred significant debate and captured widespread attention in both research and educational circles. Since its debut in November 2022, Chat Generative Pre-trained Transformer has demonstrated substantial potential across numerous domains. However, concerns voiced on Twitter have centered on potential negative consequences, such as increasedforgery and misinformation. Consequently, understanding public sentiment toward Chat Generative Pre-trained Transformer technology through sentiment analysis has become crucial. The research’s primary objective is to conduct Sentiment Analysis Classification of Chat Generative Pre-trained Transformer regarding public opinions on Twitter in Indonesia. This goal involves quantifying and categorizing public sentiment from Twitter’s vast data pool into three clusters: positive, negative, or neutral. In the data clustering stage, the Self-Organizing Map technique is used. After the text data has been weighted and clustered, the next step involves using the classification technique with LongShort-Term Memory to determine the public sentiment outcomes resulting from the presence of Chat Generative Pre-trained Transformer technology. Rigorous testing has demonstrated the robust performance of the model, with optimal parameters: relu activation function, som size of 5, num epoch som and num epoch lstm both at 128, yielding an impressive 95.07% accuracy rate.

Internal migration and economic mobility in Chile

ABSTRACT We identify internal migration flows between Chilean regions and analyse migrants’ economic mobility. A data pool from National Socioeconomic Characterization Survey (CASEN) surveys was used to determine migrants’ economic position according to their income quintile. Internal migrants were matched with non-migrants of similar status from their region of origin to compare their economic mobility. Results show that the majority of internal migrants did not achieve economic advancement in the short and medium terms, which challenges the neoclassical and functionalist assumptions of a positive relationship between migration and social mobility. Finally, we identify three interregional elevators in Chile: the Austral, Norte Grande and Metropolitan macro-regions.

Data-driven prediction of the shear capacity of ETS-FRP-strengthened beams in the hybrid 2PKT–ML approach

A new approach that combines analytical two-parameter kinematic theory (2PKT) with machine learning (ML) models for estimating the shear capacity of embedded through-section (ETS)-strengthened reinforced concrete (RC) beams is proposed. The 2PKT was first developed to validate its representativeness and confidence against the available experimental data of ETS-retrofitted RC beams. Given the deficiency of the test data, the developed 2PKT was utilized to generate a large data pool with 2643 samples. The aim was to optimize the ML algorithms, namely, the random forest, extreme gradient boosting (XGBoost), light gradient boosting machine, and artificial neural network (ANN) algorithm. The optimized ANN model exhibited the highest accuracy in predicting the total shear strength of ETS-strengthened beams and ETS shear contribution. In terms of predicting the total shear strength of ETS-strengthened beams, the ANN model achieved R2 values of 0.99, 0.98, and 0.96 for the training, validation, and testing data, respectively. By contrast, the ANN model could predict ETS shear contribution with high accuracy, with R2 values of 0.99, 0.99, and 0.97 for the training, validation, and testing data, respectively. Then, the effects of all design variables on the shear capacity of the ETS-strengthened beams were investigated using the hybrid 2PKT–ML. The obtained trends could well appraise the reasonability of the proposed approach.

Advancing Used Car Price Prediction in South Africa: An Empirical Examination of Machine Learning Techniques

The purpose of this study was to compile historical data from Demo automobiles in South Africa to build a prediction model that could predict the prices of second-hand vehicles. The developed approach was designed to serve as a facilitator for sellers and buyers in the used car industry. The dataset for this study was obtained from the Demo automobiles website. Several machine learning approaches were utilized in creating the prediction model, with the best algorithm chosen based on the R-Squared and RMSE (Root Mean Squared Error) performance metrics. Prior to modelling, data cleaning was conducted, which involved identifying null values, filling in gaps, and eliminating outliers. Data normalization was then performed on the collected data during data preprocessing. The data pool was subsequently divided into a training subset (comprising 80% of the data) and a testing subset (comprising the remaining 20% of the data). The RMSE and R-Squared measures were used to evaluate each machine learning method employed in this study, including Linear Regression, Decision Tree, Random Forest, Gradient Boosted Trees Regressor, Artificial Neural Network, and K-Nearest Neighbors. The Random Forest method demonstrated significant superiority in terms of algorithm performance results, with an R-Squared value of 0.988 and an RMSE value of 0.019, but the other algorithms also yielded excellent results.

One size fits all? Adaptation of trained CNNs to new marine acoustic environments

Convolutional neural networks (CNNs) have the potential to enable a revolution in bioacoustics, allowing robust detection and classification of marine sound sources. As global Passive Acoustic Monitoring (PAM) datasets continue to expand it is critical we improve our confidence in the performance of models across different marine environments, if we are to exploit the full ecological value of information within the data. This work demonstrates the transferability of developed CNN models to new acoustic environments by using a pre-trained model developed for one location (West of Scotland, UK) and deploying it in a distinctly different soundscape (Gulf of Mexico, USA). In this work transfer learning is used to fine-tune an existing open-source ‘small-scale’ CNN, which detects odontocete tonal and broadband call types and vessel noise (operating between 0 and 48 kHz). The CNN is fine-tuned on training sets of differing sizes, from the unseen site, to understand the adaptability of a network to new marine acoustic environments. Fine-tuning with a small sample of site-specific data significantly improves the performance of the CNN in the new environment, across all classes. We demonstrate an improved performance in area-under-curve (AUC) score of 0.30, across four classes by fine-training with only 50 spectrograms per class, with a 5% improvement in accuracy between 50 frames and 500 frames. This work shows that only a small amount of site-specific data is needed to retrain a CNN, enabling researchers to harness the power of existing pre-trained models for their own datasets. The marine bioacoustic domain will benefit from a larger pool of global data for training large deep learning models, but we illustrate in this work that domain adaptation can be improved with limited site-specific exemplars.

Development of Korean Representative Headforms for the Total Inward Leakage Testing on Filtering Facepiece Respirators

BackgroundThe lack of headforms that accurately reflect the head characteristics of Koreans and the demographic composition of the Korean population can lead to inadequate FFR testing and reduced effectiveness of FFRs. MethodDirect measurements of 5,110 individuals and 3D measurements of 2,044 individuals, aged between 9 and 69 years, were sampled from the data pool of Size Korea surveys based on the age and gender ratios of the Korean resident demographics. Seven head dimensions were selected based on the ISO 16976-2, availability of Size Korea measurements, and their relevance to the fit performance of FFRs. A principal component analysis (PCA) was performed using the direct measurements to extract the main factors explaining the head characteristics and then the main factors were standardized and remapped to 3D measurements, creating five size categories representing Korean head shapes. Lastly, representative 3D headforms were constructed by averaging five head shapes for each size category. ResultsThe study identified two main factors explaining Korean head characteristics by the PCA procedure specified in ISO 16976-2 and developed five representative headforms reflecting the anthropometric features of Korean heads: medium, small, large, short & wide, and long & narrow. ConclusionThis study developed representative headforms tailored to the Korean population for conducting total inward leakage (TIL) tests on filtering facepiece respirators (FFRs). The representative headforms can be used for TIL testing by employing robotic headforms to enhance the performance of FFRs for the Korean target population.

Economic comparison of reactive distillation (RD) to a benchmark conventional flowsheet: Regions of RD applicability and trends in column design

A novel methodology for the techno-economic assessment of Reactive Distillation (RD) is presented. The developed methodology benchmarks reactive distillation (RD) to a conventional reactor + distillation train flowsheet (R+D) on a cost-optimized basis, with the optimization being performed on the process unit level (reactor sizing, number of stages, feed point(s)) and the internals level (reactive tray design). This methodology is applied to the ideal quaternary system A+B↔C+D with the conventional boiling point order of TC < TA < TB < TD (αAD = 4, αBD = 2, αCD = 8). From this pool of data, a regime map of RD vs. R+D is established in which the attractive regions of either flowsheet option are identified in terms of the chemical reaction rate and chemical equilibrium. It is found that RD can arise as the cost optimal option for a large range of residence time requirements by virtue of overcoming the external recycle requirements of R+D. This is achieved through optimized reactive tray design. Contrary to conventional distillation design practices, it was found that the preferred use of bubble-cap trays over sieve trays to allow elevated weir heights and designing the column diameter below 80% of flooding become relevant design choices when accommodating high liquid holdup.

COSMIC:a curated database of somatic variants and clinical data for cancer.

The Catalogue Of Somatic Mutations In Cancer (COSMIC), https://cancer.sanger.ac.uk/cosmic, is an expert-curated knowledgebase providing data on somatic variants in cancer, supported by a comprehensive suite of tools for interpreting genomic data, discerning the impact of somatic alterations on disease, and facilitating translational research. The catalogue is accessed and used by thousands of cancer researchers and clinicians daily, allowing them to quickly access information from an immense pool of data curated from over 29 thousand scientific publications and large studies. Within the last 4 years, COSMIC has substantially expanded its utility by adding new resources: the Mutational Signatures catalogue, the Cancer Mutation Census, and Actionability. To improve data accessibility and interoperability, somatic variants have received stable genomic identifiers that are associated with their genomic coordinates in GRCh37 and GRCh38, and new export files with reduced data redundancy have been made available for download.

Diagnostic criteria for odontogenic sinusitis: narrative review of relevant literature data

Background. Specific tendency could be observed regarding increasing number of odontogenic sinusitis related publications within decades between 1990 and 2019, but even with upgrowing pool of literature data regarding odontogenic sinusitis evidences reported within it remains of low quality. Also, it should be noted that yet no evidence-based consensus decision have been made regarding strict diagnostic criteria of maxillary odontogenic sinusitis.&#x0D; Objective. To systematize relevant data regarding odontogenic maxillary sinusitis diagnostic criteria based on available guidelines, consensus reports, CBCT-based and clinical researches.&#x0D; Materials and Methods. Study was provided in the form of retrospective literature review. Seach of publications related with the objective of the research was held within PubMed Central database (https://www.ncbi.nlm.nih.gov/pmc/) by applying Mesh-terms combinations. Articles included into study group were processed due to the following categories of content-analysis: signs and symptoms which may be used to prove odontogenic origin of maxillary sinusitis; diagnostic significance of different manifestations which may be used to prove odontogenic origin of maxillary sinusitis; approaches which should be followed to provide correct diagnostics of odontogenic maxillary sinusitis.&#x0D; Results. Out of 15 targeted publications, which formed study group, 2 were represented in the form of systematic review, 1 – in the form of online-survey study, 6 – in the form of literature/comprehensive/state-of-art review, 4 – in the form of retrospective study, 1 – in the form of international multidisciplinary consensus statement, 1 – in the form of experimental imaging study. Considering only one available international multidisciplinary consensus statement regarding odontogenic sinusitis diagnosis next approach should be followed in mentioned order for correct diagnostics of such pathology: 1) suspect odontogenic maxillary sinusitis; 2) confirm sinusitis; 3) confirm odontogenic pathology.&#x0D; Conclusion. Tomographical methods of examination are more accurate for the odontogenic maxillary sinusitis diagnostics, nevertheless if multidisciplinary diagnostic approach (endoscopy, tomography and clinical examination) is possible for realization it should be held as a primary diagnostic strategy. Cases of asymptomatic maxillary odontogenic sinusitis, while also symptomatic ones developing without background of recent dental treatment, may also be observed in clinical practice, and thus should be correctly diagnosed for appropriate treatment planning.

On the use of machine learning to generate in-silico data for batch process monitoring under small-data scenarios

Batch process monitoring using principal component analysis requires sufficient historical manufacturing data to model the normal operating conditions of the process. However, when a new product is to be manufactured for the first time in a given facility, very limited historical data are available, thus entailing a small-data scenario. We thoroughly investigate and improve a data-driven methodology, previously reported in the literature (Tulsyan, Garvin & Ündey (2019). J. Process Control,77, 114–133), that enables batch process monitoring under such type of scenarios. The methodology exploits machine learning algorithms (based on Gaussian process state-space models) to generate in-silico batch trajectory data from the few available historical ones, and then uses the overall pool of real and in-silico data to build a process monitoring model. We develop automatic procedures to tune the values of several parameters of this machine-learning framework, in such a way that the generation of consistent in-silico batch trajectory data can be streamlined, thus facilitating the deployment of the framework at an industrial level. Furthermore, we develop indicators and a metric to assist the in-silico data generation activity from a process monitoring-relevant perspective. Finally, using datasets from a benchmark simulated semi-batch process for the manufacturing of penicillin, we thoroughly investigate the appropriateness of the in-silico generated data for the purpose of process monitoring.

Construction of agricultural product consumer group portrait and analysis of precision marketing strategies based on K-means cluster analysis

&lt;p&gt;In today’s technologically advanced landscape, where data flows in unparalleled volumes, the power of data mining stands out as a transformative force. Its capabilities extend beyond mere analysis; data mining can be harnessed to create intricate and detailed profiles of various consumer groups. This is particularly pertinent to the agricultural sector, which has long grappled with challenges of reaching its consumers effectively. The quest to refine and elevate marketing strategies for agricultural products amidst this data deluge led us to a methodical approach. We initiated this by sourcing and cleansing customer analysis datasets from Baidu AI, a leading platform in the realm of artificial intelligence and data analytics. Such a foundational step ensured that the data underpinning our analysis was robust and free of inconsistencies. The subsequent analytical journey, comprising rigorous data exploration and the utilization of the &lt;em&gt;K&lt;/em&gt;-means clustering method, allowed us to dissect and segment the vast data pool. Through this, we crafted a comprehensive consumer profile that is tailor-made for agricultural product consumption. Such segmentation offers invaluable insights, paving the way for marketers and producers to understand their audience’s nuances. Our research findings highlight the remarkable prowess of the &lt;em&gt;K&lt;/em&gt;-means clustering technique. When underpinned by sophisticated intelligent algorithms, it doesn’t just cluster data; it offers a pathway to identify distinct customer segments, shed light on core product offerings that resonate with them, and sculpt effective marketing strategies. By integrating these insights with modern media channels, we can craft marketing narratives that echo the desires and needs of the target demographic. Such a precision-driven approach ensures a symbiotic relationship where products align seamlessly with customer preferences. Beyond meeting immediate needs, this alignment has broader implications. It allows enterprises to tap into the vast opportunities presented by the digital era, positioning them on a trajectory of sustained growth and relevance in an ever-evolving market landscape.&lt;/p&gt;

The Role of Global Longitudinal Strain in Subclinical Hypothyroid Patients With Heart Failure.

Introduction There is considerable evidence to suggest the role of thyroid hormone in acute coronary syndrome (ACS), but less is known about its prognostic role in heart failure (HF). We aimed to assess the role of global longitudinal strain (GLS) in patients hospitalized with HF and underlying subclinical hypothyroidism (SCHS). Methods A retrospective analysis of 161 subjects was conducted by dichotomizing them into HF with preserved ejection fraction (HFpEF) and HF with reduced ejection fraction (HFrEF) subgroups. SCHS was defined as a thyroid stimulating hormone level >4.50 mIU/L with a normal thyroxine level based on the evaluation of limits for lab markers from prior studies. HFpEF and HFrEF were defined as left ventricular ejection fraction (LVEF)>40% and LVEF≤40%, respectively, based on American College of Cardiology (ACC) guidelines. An abnormal speckled transthoracic echocardiographic (TTE) strain was defined as a left ventricular global longitudinal strain (LVGLS) value of >-15%. Results The mean age of the population was 62±8 years, and 55% were female. LVGLS was present in 121 patients with underlying SCHS (p<0.05). The patients with SCHS andabnormal LVGLS were found to have deranged left ventricular echocardiographic parameters (p<0.05). The derangements were greater for SCHS patients with HFrEF and abnormal LVGLS (p<0.05). Readmission rates at 30 days and in-hospital mortality were higher in SCHS patients with abnormal LVGLS (p<0.05). Conclusion The SCHS is associated with abnormal GLS in HF patients (either HFpEF or HFrEF) that results in remodeling and adverse outcomes, including mortality and readmission rates. Further studies are warranted to validate these findings in a larger population data pool.

Atom-Based Machine Learning Model for Quantitative Property-Structure Relationship of Electronic Properties of Fusenes and Substituted Fusenes.

This study presents the development of machine-learning-based quantitative structure-property relationship (QSPR) models for predicting electron affinity, ionization potential, and band gap of fusenes from different chemical classes. Three variants of the atom-based Weisfeiler-Lehman (WL) graph kernel method and the machine learning model Gaussian process regressor (GPR) were used. The data pool comprises polycyclic aromatic hydrocarbons (PAHs), thienoacenes, cyano-substituted PAHs, and nitro-substituted PAHs computed with density functional theory (DFT) at the B3LYP-D3/6-31+G(d) level of theory. The results demonstrate that the GPR/WL kernel methods can accurately predict the electronic properties of PAHs and their derivatives with root-mean-square deviations of 0.15 eV. Additionally, we also demonstrate the effectiveness of the active learning protocol for the GPR/WL kernel methods pipeline, particularly for data sets with greater diversity. The interpretation of the model for contributions of individual atoms to the predicted electronic properties provides reasons for the success of our previous degree of π-orbital overlap model.

Research Progress and Application Analysis of the Returning Straw Decomposition Process Based on CiteSpace

Straw returning is an important measurement to determine the utilization of straw resources. Understanding the decomposition process and nutrient release process of straw is of great significance to the efficient utilization of straw resources and the sustainable development of the agricultural economy. In this study, the literature published in the CNKI and WOS from 2002 to 2022 was used as the data pool, and a keyword co-occurrence network map was drawn with the CiteSpace (6.2.R4) software. Visual analyses were based on the straw returning literature (1998 articles) and straw decomposition agent literature (125 articles), and the decomposition and nutrient release of straw under the action of a decomposition agent were analyzed using a straw decomposition characterization experiment. In general, returning straw can effectively improve soil fertility conditions and provide nutrients for crop growth, and the use of a straw decomposition agent can further improve soil conditions and increase crop yield. The straw decomposition characterization experiment further showed that Pseudomonas could effectively increase the decomposition rate and increase the nutrient release rate of straw. According to the above results, determining how to improve the utilization efficiency of straw resources via decomposable bacteriological agents according to local conditions will become a research hotspot in the future.