Sustainable agriculture is currently being challenged under climate change scenarios since extreme environmental processes disrupt and diminish global food production. For example, drought-induced increases in plant diseases and rainfall caused a decrease in food production. Machine Learning and Agricultural Big Data are high-performance computing technologies that allow analyzing a large amount of data to understand agricultural production. Machine Learning and Agricultural Big Data are high-performance computing technologies that allow the processing and analysis of large amounts of heterogeneous data for which intelligent IT and high-resolution remote sensing techniques are required. However, the selection of ML algorithms depends on the types of data to be used. Therefore, agricultural scientists need to understand the data and the sources from which they are derived. These data can be structured, such as temperature and humidity data, which are usually numerical (e.g., float); semi-structured, such as those from spreadsheets and information repositories, since these data types are not previously defined and are stored in No-SQL databases; and unstructured, such as those from files such as PDF, TIFF, and satellite images, since they have not been processed and therefore are not stored in any database but in repositories (e.g., Hadoop). This study provides insight into the data types used in Agricultural Big Data along with their main challenges and trends. It analyzes 43 papers selected through the protocol proposed by Kitchenham and Charters and validated with the PRISMA criteria. It was found that the primary data sources are Databases, Sensors, Cameras, GPS, and Remote Sensing, which capture data stored in Platforms such as Hadoop, Cloud Computing, and Google Earth Engine. In the future, Data Lakes will allow for data integration across different platforms, as they provide representation models of other data types and the relationships between them, improving the quality of the data to be integrated.

The nuclear architecture of meiotic prophase spermatocytes is based on higher-order patterns of spatial associations among chromosomal domains from different bivalents. The meiotic nuclear architecture depends on the chromosome characteristics and consequently is prone to modification by chromosomal rearrangements. In this work, we consider Mus domesticus spermatocytes with diploid chromosome number 2n = 40, all telocentric, and investigate a possible modification of the ancestral nuclear architecture due to the emergence of derived Rb chromosomes, which may be present in the homozygous or heterozygous condition. In the 2n = 40 spermatocyte nuclei random associations mediated by pericentromeric heterochromatin among the 19 telocentric bivalents ocurr at the nuclear periphery. The observed frequency of associations among them, made distinguishable by specific probes and FISH, seems to be the same for pairs that may or may not form Rb chromosomes. In the homozygote Rb 2n = 24 spermatocytes, associations also mediated by pericentromeric heterochromatin occur mainly between the three telocentric or the eight metacentric bivalents themselves. In heterozygote Rb 2n = 32 spermatocytes all heterochromatin is localized at the nuclear periphery, yet associations are mainly observed among the three telocentric bivalents and between the asynaptic axes of the trivalents. The Rb chromosomes pose sharp restrictions for interactions in the 2n = 24 and 2n = 32 spermatocytes, as compared to the ample possibilities for interactions between bivalents in the 2n = 40 spermatocytes. Undoubtedly the emergence of Rb chromosomes changes the ancestral nuclear architecture of 2n = 40 spermatocytes since they establish new types of interactions among chromosomal domains, particularly through centromeric and heterochromatic regions at the nuclear periphery among telocentric and at the nuclear center among Rb metacentric ones.

Understanding the spatial organization of the chromosomes in meiotic nuclei is crucial to our knowledge of the genome's functional regulation, stability and evolution. This study examined the nuclear architecture of Mus domesticus 2n=40 pachytene spermatocytes, analyzing the associations among autosomal bivalents via their Centromere Telomere Complexes (CTC). The study developed a nuclear model in which each CTC was represented as a 3D computer object. The probability of a given combination of associations among CTC was estimated by simulating a random distribution of 19 indistinguishable CTC over n indistinguishable "cells" on the nuclear envelope. The estimated association frequencies resulting from this numerical approach were similar to those obtained by quantifying actual associations in pachytene spermatocyte spreads. The nuclear localization and associations of CTC through the meiotic prophase in well-preserved nuclei were also analyzed. We concluded that throughout the meiotic prophase: 1) the CTC of autosomal bivalents are not randomly distributed in the nuclear space; 2) the CTC associate amongst themselves, probably at random, over a small surface of the nuclear envelope, at the beginning of the meiotic prophase; 3) the initial aggregation of centromere regions occurring in lepto-zygotene likely resolves into several smaller aggregates according to patterns of preferential partitioning; 4) these smaller aggregates spread over the inner face of the nuclear envelope, remaining stable until advanced stages of the meiotic prophase or even until the first meiotic division.

While some areas of software engineering knowledge present great advances with respect to the automation of processes, tools, and practices, areas such as software maintenance have scarcely been addressed by either industry or academia, thus delegating the solution of technical tasks or human capital to manual or semiautomatic forms. In this context, machine learning (ML) techniques play an important role when it comes to improving maintenance processes and automation practices that can accelerate delegated but highly critical stages when the software launches. The aim of this article is to gain a global understanding of the state of ML-based software maintenance by using the compilation, classification, and analysis of a set of studies related to the topic. The study was conducted by applying a systematic mapping study protocol, which was characterized by the use of a set of stages that strengthen its replicability. The review identified a total of 3776 research articles that were subjected to four filtering stages, ultimately selecting 81 articles that were analyzed thematically. The results reveal an abundance of proposals that use neural networks applied to preventive maintenance and case studies that incorporate ML in subjects of maintenance management and management of the people who carry out these tasks. In the same way, a significant number of studies lack the minimum characteristics of replicability.