Series Data Research Articles

Features of anthropometric indicators of the feet of adolescents of Zhambyl region

The comfort of shoes is one of the main indicators of the quality of shoes, which ensures the normal functioning and development of the foot in the process of growth and in general. In turn, the normal functioning and development of the foot determines the normal state of the whole organism, since the appearance of deviations in the foot leads to disturbances throughout the body. In the work, measurements of the feet of young men of the Zhambyl region were carried out in order to develop a size range of shoes, design shoe lasts and shoes with rational dimensional indicators. The measurements of the young men's feet were carried out using both standard and modern 3D scanning methods. The measurements were carried out among schoolchildren and students of higher educational institutions aged 15 to 18 years. As a result of measurements of young men's feet, variational series of dimensional characteristics, statistical data, and correlation-regression equations were calculated. The analysis of the obtained data was calculated using the methods of mathematical statistics and programming. The results of the study of the size of the feet will improve the socio-economic situation, which is expressed in providing the population of Kazakhstan with comfortable shoes that would take into account the anatomical, physiological and psychological characteristics of young men in Kazakhstan. The given data on the size of the feet of young men can be used in shoe factories, organizations for the tailoring of orthopedic and special shoes.

Quantifying intra‐ and inter‐annual dynamics of river‐floodplain connectivity and wetland inundation with remote sensing and wavelet analysis

AbstractWe used imagery from remote sensing (FORCE Time Series Analysis submodule (combining Landsat and Sentinel‐2 imagery) to derive spatially distributed times series (8 years) of NDWI data to infer patterns of floodplain inundation and river‐floodplain connectivity in two contrasting polders in the Lower Oder Valley National Park. The upstream Polder A (14.4 km2) was extensively flooded for prolonged periods most winters. Wavelet analysis showed that this strong seasonality was primarily driven by winter water levels in the river Oder that could enter and leave the polder through two opened floodgates. Subsequent drainage was slow and aided by a pumping station. Inundation of the downstream Polder 10 (17.7km2) was lower and had less marked seasonality. This reflected the impact of flood attenuation by storage in Polder A upstream, but also the greater connectivity (via 10 floodgates) to the Oder and a functional network of channels, which facilitated rapid drainage after flood peaks. In Polder A, secondary periods of transient inundation could also occur in response to local intense summer rainfall. Wavelet analysis also showed that groundwater recharge in and around Polder A is primarily induced by floodwater, whilst Polder 10 also reflects the influence of local rainfall‐driven recharge. The flood regimes of the two polders showed marked inter‐annual variation, largely dependent on flows from the upper Oder catchment. Understanding these patterns and processes of inundation is important for both managing flows and sustaining valuable wetland habitats within the National Park. Given projected climate change in eastern Europe and possible management alterations to the flow regime of the Oder, the potential implications for these habitats needs urgent attention.

120-years of ecological monitoring data shows that the risk of overhunting is increased by environmental degradation for an isolated marine mammal population: The Baltic grey seal.

The Baltic Sea is home to a genetically isolated and morphologically distinct grey seal population. This population has been the subject of 120-years of careful documentation, from detailed records of bounty statistics to annual monitoring of health and abundance. It has also been exposed to a range of well-documented stressors, including hunting, pollution and climate change. To investigate the vulnerability of marine mammal populations to multiple stressors, data series relating to the Baltic grey seal population size, hunt and health were compiled, vital demographic rates were estimated, and a detailed population model was constructed. The Baltic grey seal population fell from approximately 90,000 to as few as 3000 individuals during the 1900s as the result of hunting and pollution. Subsequently, the population has recovered to approximately 55,000 individuals. Fertility levels for mature females have increased from 9% in the 1970s to 86% at present. The recovery of the population has led to demands for increased hunting, resulting in a sudden increase in annual quotas from a few hundred to 3550 in 2020. Simultaneously, environmental changes, such as warmer winters and reduced prey availability due to overfishing, are likely impacting fecundity and health. Future population development is projected for a range of hunting and environmental stress scenarios, illustrating how hunting, in combination with environmental degradation, can lead to population collapse. The current combined hunting quotas of all Baltic Nations caused a 10% population decline within three generations in 100% of simulations. To enable continued recovery of the population, combined annual quotas of less than 1900 are needed, although this quota should be re-evaluated annually as monitoring of population size and seal health continues. Sustainable management of long-lived slowly growing species requires an understanding of the drivers of population growth and the repercussions of management decisions over many decades. The case of the Baltic grey seal illustrates how long-term ecological time series are pivotal in establishing historical baselines in population abundance and demography to inform sustainable management.

Integrating historical and recent information to understand chondrichthyan dynamics in the central Mediterranean

Chondrichthyans (sharks, rays, and chimaeras) are highly susceptible to the impacts of fisheries due to their vulnerable life-history traits. Over the last 100 years, several cases of local extinction have been documented in heavily fished areas across the Mediterranean Sea. In the Strait of Sicily (SoS), one of the main demersal fishing grounds of the Mediterranean, chondrichthyans constitute a significant component of both commercial and discarded bycatch. In this area, the lack of long-term data series on these species hinders our ability to fully comprehend the extent of changes due to both overfishing and climate variations. Here we aim to use historical data from the end of the 19th century, provided by Döderlein, to uncover evidence of long-term changes in the occurrence and diversity of these fishes. We employ a semi-quantitative approach to compare past data with recent frequency of occurrence estimates, to improve our ability to propose management advice. We report a decline in both the number of species and the frequency of occurrence of sharks and ray species in the study region over the past 150 years. Our findings shed light on the current status of sharks and rays compared to the historical data from the 19th century and highlight the urgent need to develop management strategies to mitigate the impact of harvesting on these vulnerable species.

Rat ventral caudal nerve as a model for long distance regeneration

In the rat, tail nerves are the longest peripheral nerves in their body. We suggest that ventral caudal nerve (VCN) may serve as a model for studying nerve injury and long distance regeneration. For this purpose, we have studied the anatomy and morphometry of the VCN in control animals. 10 cm long segment of the VCN was removed, and transversal sections were collected at 10 mm distances. The myelinated axons were counted, and the series of data were used to characterize the craniocaudal tapering of the nerve. In a separate group of animals, retrograde tracing with Fluorogold was used to localize and quantitate the spinal neurons projecting their axons into the VCN. After complete nerve transection, the time course of histopathological changes in the distal segment was studied. The primary goal was to define the time needed for axonal disintegration. In later periods, axonal debris removal and rearrangement of tissue elements was documented. After compression injury (axonotmesis), Wallerian degeneration was followed by spontaneous regeneration of axons. We show that the growing axons will span the 10 cm distance within 4–8 weeks. After different survival periods, the numbers of regenerating axons were counted at 10 mm distances. These data were used to characterize the dynamics of axonal regeneration during 4 months’ survival period. In the present study we show that axonal regeneration across 10 cm distance can be studied and quantitatively analyzed in a small laboratory animal.

Molecular Epidemiology of HIV-1 Subtypes and Primary Antiretroviral Resistance Profiles in Northern Cyprus: First Data Series.

The distribution of human immunodeficiency virus-1 (HIV-1) subtypes indicates difference from region to region and in risk groups acquiring the disease worldwide. Although subtype C is more in terms of total cases, subtype B is dominant in certain regions, especially in western and central Europe. Molecular epidemiological studies are essential for the control, effective treatment, and understanding in transmission routes of HIV-1 infection. This study aims to determine the molecular epidemiology and antiretroviral drug resistance profiles of HIV-1 in northern Cyprus. The study involved 71 naive HIV-positive patients diagnosed in northern Cyprus between 2016 and 2022. HIV-1 subtypes and circulating recombinant forms (CRFs) were identified by phylogenetic analysis (neighbor-joining method) of pol gene sequences. Drug resistance mutations were analyzed using the World Health Organization (WHO) lists of mutations for surveillance. The Stanford University HIVdb program was used to interpret drug resistance mutations. In our study, 40 of 71 samples were successfully sequenced. Subtype B of HIV-1 was dominant with a rate of 52.5%, followed by CRF02_AG (20%) and G (7.5%) subtypes. The rate of subtype B (71.4%) in northern Cyprus was significantly higher than in the other country of origin (p = .028). Antiretroviral drug resistance was found in 15% of the sequenced serum samples. Nucleoside/nucleotide reverse transcriptase inhibitor (NRTI), non-nucleoside nucleotide reverse transcriptase inhibitor (NNRTI), and protease inhibitor (PI) resistance rates were 10% (4/40), 7.5% (3/40), and 2.5% (1/40), respectively. According to the results, it is noteworthy that the dominant subtype circulating in northern Cyprus is the B subtype, and CRFs were detected at a higher rate than expected.

Verification of tidal trends in Cananeia (SP) and Santos (SP)

Recent studies indicate an imminent global rise in mean sea level. However, comprehending variations in tidal patterns is imperative before analyzing the scenario of extreme events, typically associated with the combination of high tides and intense meteorological influences. This study presents local trends in sea level, amplitude, and phase of the two main tidal components in Cananeia (SP) and Santos (SP), utilizing tide gauge data from records of sufficient length to avoid the need for nodal correction in the tide components. Using more up-to-date tide gauge data allowed the investigation of observed trends. Long-term tidal data series revealed an upward trend in mean level of approximately 4,324 mm/year in Cananeia and 0,538 mm/year in Santos. Both locations were affected by human activities along their estuaries, with Santos experiencing significant variations in the amplitude and phase values of the tidal constituents annually.

Abstract 6472: Response to PARP inhibitors in patients with breast cancer metastatic to the central nervous system

Abstract Background: Central nervous system (CNS) metastasis from breast cancer can be challenging to treat due to the limited blood brain barrier penetration of many systemic therapies. PARP inhibitors (PARPi) block single-strand DNA break repairs and have activity in cancers with homologous recombination repair deficiency; they are FDA approved for patients with metastatic HER2 negative breast cancer with germline BRCA1/2 mutations. While preclinical studies suggest that PARPi have CNS penetration, clinical data is limited. The goal of our study is to describe the clinical benefit of PARPi in patients with breast cancer CNS metastasis. Methods: This retrospective case series was conducted at three academic cancer centers (Johns Hopkins, Dana-Farber, and Duke) and included patients with the following criteria: (1) age≥18 years with a breast cancer diagnosis (any subtype); (2) diagnosis of parenchymal brain metastasis or leptomeningeal disease (LMD); and (3) received PARPi (olaparib, talazoparib) for CNS metastasis. Clinical and pathologic information were analyzed with descriptive statistics (median, range) and Kruskal-Wallis rank sum tests. Survival analysis was performed using Kaplan-Meier curves with log-rank p-values. Results: Although this analysis includes one center’s experience, we will present a combined dataset (N = 45) at the main conference. 11 patients were identified at Johns Hopkins. 4 (36.4%) were Black and 6 (54.5%) were White; 6 (54.5%) had ER+HER2- disease and 5 (45.5%) had TNBC at time of brain metastasis; 5 (45.5%) had BRCA1 mutations, 5 (45.5%) had a BRCA2 mutations, and 1 patient (9%) had a BARD1 mutation; 7 (63.6%) had brain metastasis and 4 (36.4%) had LMD. Median lines of therapy prior to PARPi was 6 [1 - 11]; 8 patients (72.7%) had previous CNS radiation (5 SRS and 3 WBRT) and 3 (27.3%) had previous CNS surgery. On average, patients remained on PARPi for 5 months [0.5 - 66], and overall survival (OS) time from PARPi to death was 16 months [2 - 66]. Time on PARPi was 5 months [2 - 66] for patients with brain metastasis and 3 months [0.5 - 10] for those with LMD (p=0.22). Duration of PARPi and OS did not differ significantly between ER+HER2- and TNBC (p=0.74 and 0.69, respectively), BRCA 1 and 2 (p=0.78 and 0.72, respectively), or brain and LMD metastasis (p=0.22 and 0.91, respectively). Black patients had significantly shorter PARPi duration and survival than White patients (PARPi 2 vs. 8 months, p=0.028 and OS 4 vs 18 months, p=0.028). Prior CNS radiation was significantly associated with longer PARPi duration and survival (PARPi 5 vs 1 month, p=0.02 and OS 17 vs. 3 months, p=0.032). Prior CNS surgery was significantly associated with longer PARPi duration, but not overall survival (PARPi 18 vs 3 months, p=0.05 and OS 28 vs. 7 months, p=0.14). Conclusions: PARPi are associated with significant clinical benefit in patients with breast cancer CNS metastasis. Larger data series will help confirm these observations. Citation Format: Seoho Lee, Rani Bansal, Melissa E. Hughes, Amanda E. Van Swearingen, Heather N. Moore, David O. Kamson, Solmaz Sahebjam, Greg Kirkner, Anna Gorfinkel, Sarah Sammons, Nancy U. Lin, Carey Anders, Cesar A. Santa-Maria. Response to PARP inhibitors in patients with breast cancer metastatic to the central nervous system [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6472.

Spectral-temporal convolutional approach for PV systems output power forecasting: Case studies in single-site and multi-site

Accurate predictions of photovoltaic (PV) and wind power outputs are indispensable for integrating additional renewable energy sources into the grid. Photovoltaic energy is influenced by weather conditions and cloud movement, constituting the primary factors contributing to stochastic characteristics and uncertainty in predictive accuracy. Consequently, recent studies have focused on developing forecasting methods that utilize weather factors or nearby farms as multi-variable inputs. This study introduces several challenges, and one of the most significant goals is to capture the correlation between data series (spatial feature) and temporal correlation within each series (temporal feature) simultaneously. However, most previous work has concentrated solely on the time or frequency domain. This work presents a novel approach based on the spectral and frequency domain, which efficiently captures spatial–temporal correlations via Graph Fourier Transform (GFT) and Discrete Fourier Transform (DFT). In this manner, spatial correlations are clearly represented via the adjacency matrix of GFT, and temporal correlations are clarified via DFT. The study provides specific evidence concerning the interpretability and extraction efficiency of the adjacency matrix in the context of multi-variable, single-site, and multi-site data. Simultaneously, it demonstrates the effectiveness of the representation approach in the spectral domain. The results pointed out the forecasting method proposed has higher forecasting accuracy than the benchmark model.

The impact of carbon emissions from lag fertilization on wheat production.

This study examines the influence of lag fertilization techniques on Pakistani wheat production, highlighting the need to understand and mitigate the environmental impacts of farming methods. The basic purpose of this study is to investigate the impact of CO2 emission from fertilization and other factors on wheat production in Pakistan, using a time series of data from 1990 to 2020. CO2 emission from fertilization (CO2EF) is estimated using the default values provided by the IPCC guidelines. The ARDL approach analyses the short-run and long-run effects of CO2EF, technology level, energy use, agricultural land, and agricultural labor on wheat production. The results show that all factors have significantly impacted wheat production in Pakistan at levels of 1% and 5% significance, both in the short and long run. These findings suggest that reducing CO2EF, technology level, energy use, agricultural land, and agricultural labor on wheat production can help to increase wheat production in Pakistan. The study also highlights the importance of adopting sustainable and efficient fertilization practices, exploring alternative fertilizers, and using crop rotation systems to mitigate the adverse effects of carbon emissions from nitrogen fertilization, energy use, and the use of technology. These measures can contribute to a more sustainable and climate-resilient agriculture sector in Pakistan.

Scalepopgen: Bioinformatic Workflow Resources Implemented in Nextflow for Comprehensive Population Genomic Analyses.

Population genomic analyses such as inference of population structure and identifying signatures of selection usually involve the application of a plethora of tools. The installation of tools and their dependencies, data transformation, or series of data preprocessing in a particular order sometimes makes the analyses challenging. While the usage of container-based technologies has significantly resolved the problems associated with the installation of tools and their dependencies, population genomic analyses requiring multistep pipelines or complex data transformation can greatly be facilitated by the application of workflow management systems such as Nextflow and Snakemake. Here, we present scalepopgen, a collection of fully automated workflows that can carry out widely used population genomic analyses on the biallelic single nucleotide polymorphism data stored in either variant calling format files or the plink-generated binary files. scalepopgen is developed in Nextflow and can be run locally or on high-performance computing systems using either Conda, Singularity, or Docker. The automated workflow includes procedures such as (i) filtering of individuals and genotypes; (ii) principal component analysis, admixture with identifying optimal K-values; (iii) running TreeMix analysis with or without bootstrapping and migration edges, followed by identification of an optimal number of migration edges; (iv) implementing single-population and pair-wise population comparison-based procedures to identify genomic signatures of selection. The pipeline uses various open-source tools; additionally, several Python and R scripts are also provided to collect and visualize the results. The tool is freely available at https://github.com/Popgen48/scalepopgen.

Feature Optimization-Based Machine Learning Approach for Czech Land Cover Classification Using Sentinel-2 Images

The Czech Republic is one of the countries along the Belt and Road Initiative, and classifying land cover in the Czech Republic helps to understand the distribution of its forest resources, laying the foundation for forestry cooperation between China and the Czech Republic. This study aims to develop a practical approach for land cover classification in the Czech Republic, with the goal of efficiently acquiring spatial distribution information regarding its forest resources. This approach is based on multi-level feature extraction and selection, integrated with advanced machine learning or deep learning models. To accomplish this goal, the study concentrated on two typical experimental regions in the Czech Republic and conducted a series of classification experiments, using Sentinel-2 and DEM data in 2018 as the main data sources. Initially, this study extracted various features, including spectral, vegetation, and terrain features, from the study area, then assessed and selected key features based on their importance. Additionally, this study also explored multi-level spatial contextual features to improve classification performance. The extracted features include texture and morphological features, as well as deep semantic information learned by utilizing a deep learning model, 3D CNN. Finally, an AdaBoost ensemble learning model with the random forest as the base classifier is designed to produce land cover classification maps, thus obtaining the spatial distribution of forest resources. The experimental results demonstrate that feature optimization significantly enhances the extraction of high-quality features of surface objects, thereby improving classification performance. Specifically, morphological and texture features can effectively enhance the discriminability between different features of surface objects, thereby improving classification accuracy. Utilizing deep learning networks enables more efficient extraction of deep feature information, further enhancing classification accuracy. Moreover, employing an ensemble learning model effectively boosts the accuracy of the original classification results from different individual classifiers. Ultimately, the classification accuracy of the two experimental areas reaches 92.84% and 93.83%, respectively. The user accuracies for forests are 92.24% and 93.14%, while the producer accuracies are 97.71% and 97.02%. This study applies the proposed approach for nationwide classification in the Czech Republic, resulting in an overall classification accuracy of 90.98%, with forest user accuracy at 91.97% and producer accuracy at 96.2%. The results in this study demonstrate the feasibility of combining feature optimization with the 3D Convolutional Neural Network (3DCNN) model for land cover classification. This study can serve as a reference for research methods in deep learning for land cover classification, utilizing optimized features.

Modelling Profitability Determinants in the Banking Sector: The Case of the Eurozone

The aim of this study is to analyze which factors affect the profitability of banks in the eurozone and to make recommendations for supporting them to achieve higher levels of profitability in particular eurozone countries. The banks operating in the eurozone are specific that they are under one monetary policy. The main purpose of the banks’ profitability analysis is to identify main bank-specific and macroeconomic determinants and help bank management to more fully comprehend their importance of bank-specific determinants and macroeconomic determinants’ influence when measuring and evaluating bank profitability. For the purpose of this research, we analyze the impact of bank-specific determinants (NPL, CIR, NIM, NIF and NIT) and macroeconomic determinants (GDP, INF, UNM and DEBT) on bank profitability in the eurozone for the period of 2015–2020 using a random effects model, fixed effects model, and the general method of moments (GMM). This empirical research analyzed quarterly data series from Eurostat for eighteen countries in the eurozone. We came to the results that on the eurozone-level NPL, the cost-to-income ratio has a negative impact on the banks’ profitability, while the net interest income to the operating income, the net income for trading assets to the operating income and the net fee and commission income to the operating income have a positive impact on the banks’ profitability. Considering the macroeconomic variables, we found a positive impact only in the case of GDP, while the inflation rate, unemployment rate and gross government debt have shown a negative impact on the banks’ profitability. The main contribution of this study implies different panel techniques with two uncommonly used macroeconomic variables such as the unemployment rate and debt ratio. The results on the country level differ from country to country and these findings can give a lead to policy makers on the national level on how to enhance the banks’ profitability levels.

A comparative evaluation of spatial interpolation techniques for maximum temperature series in the Montreal region, Canada

This study aims to provide a comparative analysis of two of the most used methods of spatial interpolation – Thiessen Polygons (TP) and Inverse Distance Weighting (IDW) with a spatio-temporal approach – Spatio-temporal kriging (STK) on a data series from Canada. The IDW parameter is optimized to obtain the best fitting for the studied series, based on the Root Mean Squared Errors (RMSE) and Mean Absolute Percentage Error (MAPE). The advantages and disadvantages of each algorithm are emphasized. Although TP registered the lowest RMSE and a MAPE, the analysis favors the STK use for modeling Montreal’s maximum temperature series.

Principal Component Analysis of Yield and Its Attributing Traits in Recombinant Inbred Lines of Rice Under Submerged Condition (Oryza sativa L.)

Rice, Oryza sativa L., is the world's most important staple crop, feeding more than half of the world's population. The phenotype of plant is the result of interaction of many factors and final yield is the sum of total effect of several component factors. Therefore evaluation of genetic variability forms the basis for any crop improvement programme, the success of which depends on sufficient genetic variability among genotypes so as to permit effective selection. Hence Evaluation of Principle Component Analysis (PCA)of recombinant inbred lines (RILs) was done at phenotypic level under submerged conditions to reduce a large series of data into smaller number of components by looking for groups that have very strong inter-correlation in a set of variables and each component explained per cent variation to the total variability. The RIL population was derived from an inter-specific cross between BPT5204 and HPR14 parents. A study was conducted using 1256 Recombinant Inbreed Lines submerged condition in the two seasons at College of Agriculture V.C. Farm, Mandya with nine agro-morphological traits and a principle component analysis was carried out. Out of nine principle components, four exhibited Eigenvalue more than one governing 77.74% variance and 69.86% variance in the summer and kharif seasons respectively. The highest positive Eigenvalue was observed for total number of tillers, productive tillers, non-productive tillers and fallowed by single plant yield in PC1 in the summer and kharif season respectively. The highest positive Eigenvalue was observed for five panicle weight, single panicle length, single plant yield and plant height in PC2 of summer and kharif season respectively. Indicating their pronounced effect on the overall variation in the Recombinant Inbreed Lines of Rice.

UNCERTAINTY IN THE RICE SUPPLY CHAIN DURING PRE AND POST PANDEMIC - A CROSS CASE OF AGRICULTURAL COOPERATIVES IN INDONESIA

Even though the social order is starting to recover from the risk of Covid-19 transmission, but the performance of food security is still constrained in some countries, including Indonesia, where the majority of the population consumes rice. If the infection rate spikes again, it can hamper the supply chain for food commodities such as rice. From this paper, the research target focuses on the structure of the supply chain in rice under government supervision operated by a national company. In distribution capacity, domestic rice is a local type of superior quality to every interisland agricultural cooperative in Indonesia. Overall, this scientific paper calculates the multidimensional disruption in the rice supply chain from across the major islands in Indonesia During a normal situation and after a pandemic. A series of annual report data sourced from the Central Bureau of Statistics (BPS) are tabulated using parametric regression. The research sample is framed in a combination of agricultural cooperatives in 6 objects in Indonesia based on 12 key variables. The time panel is divided into two compositions: 2017–2019 (pre–Covid) and 2020–2022 (post–Covid). The output of the study clarifies that there is a significant relationship between pre–Covid and post–Covid to the manufacturing industry, quality control, logistics, land infrastructure, and sales significantly. Then, there was a significant link between pre–Covid and post–Covid from paddy production to the manufacturing industry mediated by supply, logistics to agricultural cooperatives mediated by land and marine infrastructure, then agricultural cooperatives to consumers mediated by sales. In relation to this research, the participation of stakeholders is suggested to adopt schemes and controls that are integrated with the transition of the rice supply chain.

Research on out-of-sample prediction method of water quality parameters based on dual-attention mechanism

Predicting water quality data is an important measure for ecological environment protection in watersheds. Aiming at the problem that existing prediction algorithms rarely analyze the characteristics of future changes in water quality indicators, this paper proposes an out-of-sample prediction model for water quality parameters based on the dual-attention mechanism. The model adopts the Encoder-Decoder architecture to realize the prediction of data series, and combines the dual attention of dimension and time step to improve the prediction performance of out-of-sample data. The model is used to predict the water quality parameters of a multi-parameter river, analyze the trend of the out-of-sample data, and compare the prediction results with the traditional LSTM network and Encoder-Decoder LSTM network, the prediction accuracies of the water quality indicators are improved, and the prediction accuracy of the out-of-sample data of the water quality indicators reaches 80%. This will be of great significance to the comprehensive management of river waters and the high-quality development of ecological environment.

Performance assessment of rainfall forecasting models for urban Guwahati City using machine learning techniques and singular spectrum analysis

Abstract Rainfall forecasting is pivotal for issuing flood warnings and flood management. Machine learning (ML) models are popular as they can effectively manage extensive data and non-stationarity of the data series with improved performance and cost-effective solutions. However, more studies are required to understand the dynamic characteristics of rainfall. This study proposes a hybrid model and demonstrates its efficiency in improving the daily rainfall forecast. Singular spectrum analysis (SSA) was used as a data pre-processing technique (successfully removing and identifying the nature of noise) and coupled with ML models (artificial neural network (ANN) and support vector machine (SVM)) improving daily scale forecast. Since the current response of the hydrological system depends on previous responses, rainfall at the next time step was derived with the previous 2-, 3-, 5- and 7-day rainfall. Study shows that the first eigen vector derived through SSA is the trend component which has a maximum contribution of 18.75%, suggesting it can explain 18.75% of the given rainfall series. The 16.42% (eigen vector 2-9) contributes to periodicity, with period of 1 year, 6 months, and 4 months within the data. Conclusively, the hybrid SSA-ML model outperformed the single model for daily rainfall forecasts.

Deep Learning-Based Spatiotemporal Fusion Architecture of Landsat 8 and Sentinel-2 Data for 10 m Series Imagery

Medium- to high-resolution imagery is indispensable for various applications. Combining images from Landsat 8 and Sentinel-2 can improve the accuracy of observing dynamic changes on the Earth’s surface. Many researchers use Sentinel-2 10 m resolution data in conjunction with Landsat 8 30 m resolution data to generate 10 m resolution data series. However, current fusion techniques have some algorithmic weaknesses, such as simple processing of coarse or fine images, which fail to extract image features to the fullest extent, especially in rapidly changing land cover areas. Facing the aforementioned limitations, we proposed a multiscale and attention mechanism-based residual spatiotemporal fusion network (MARSTFN) that utilizes Sentinel-2 10 m resolution data and Landsat 8 15 m resolution data as auxiliary data to upgrade Landsat 8 30 m resolution data to 10 m resolution. In this network, we utilized multiscale and attention mechanisms to extract features from coarse and fine images separately. Subsequently, the features outputted from all input branches are combined and further feature information is extracted through residual networks and skip connections. Finally, the features obtained from the residual network are merged with the feature information of the coarsely processed images from the multiscale mechanism to generate accurate prediction images. To assess the efficacy of our model, we compared it with existing models on two datasets. Results demonstrated that our fusion model outperformed baseline methods across various evaluation indicators, highlighting its ability to integrate Sentinel-2 and Landsat 8 data to produce 10 m resolution data.

Improving the institutional environment of enterprises' innovative activity based on proactivity

Subject. The article addresses availability of resources, institutional environment, scientific and technical potential of enterprises in various industries. Objectives. The purpose is to classify enterprises by type of innovation strategy. Methods. We employ methods of horizontal and vertical comparative analysis of data series. Results. The study established that proactive enterprises showed a significant increase in revenue and profit for 2011–2022. For all types of enterprises, R&D and development is unprofitable. For proactive businesses, the risk of business liquidation is 36% lower than for other businesses. Conclusions. Multilateral institutional arrangements in the form of sectoral transactions are an effective tool for disseminating proactive behavior among enterprises.