The field of ecology has been greatly enhanced by the integration of computational tools and statistical methods, with the programming language R emerging as a pivotal and flexible tool for ecological inquiry. As ecological research accelerates, understanding the prevalent trends and specific usage patterns of R in recent studies is crucial. Our investigation explored the use of R and its packages in 125,494 scholarly articles across 40 ecology journals from 2008 to 2023. A considerable number of articles, 52,658 (41.96%), designated R as their principal analytical tool, demonstrating a steady linear growth in its utilization from 10.31% in 2008 to 66.88% in 2023. Twelve R packages, including "lme4," "vegan," "nlme," "MuMIn," "ape," "ggplot2," "car," "mgcv," "MASS," "raster," "multcomp," and "lmerTest," each played a pivotal role in contributing to more than 1,000 scholarly articles. The highest usage rate of the lme4 package indicates that mixed-effect models have a particularly important role in ecological research, and the application of these models has helped ecologists solve many important scientific problems. Journal-specific package preferences aligned with their scientific domains, while the rise in the average number of R packages per article signals a trend towards more complex analytical methods in ecology. Our findings indicate a reciprocal relationship between the development of R and ecological research, underscoring the need for collaboration among quantitative ecologists, R developers, and ecologists to further advance both the language and the field.

Using remote sensing images to identify crop plots and estimate crop planting area is an important part of agricultural remote sensing monitoring. High-resolution remote sensing images can provide rich information regarding texture, tone, shape, and spectrum of ground objects. With the advancement of sensor and information technologies, it is now possible to categorize crops with pinpoint accuracy. This study defines crop mapping as a semantic segmentation problem; therefore, a deep learning method is proposed to identify the distribution of corn and soybean using the differences in the spatial and spectral features of crops. The study area is located in the southwest of the Great Lakes in the United States, where corn and soybean cultivation is concentrated. The proposed attention mechanism deep learning model, A₂SegNet, was trained and evaluated using three years of Sentinel-2 data, collected between 2019 and 2021. The experimental results show that this method is able to fully extract the spatial and spectral characteristics of crops, and its classification effect is significantly better than that of the baseline method, and it has better classification performance than other deep learning models. We cross verified the trained model on the test sets of different years through transfer learning in both spatiotemporal and spatial dimensions. Proving the effectiveness of the attention mechanism in the process of knowledge transfer, A₂SegNet showed better adaptability.

The metacommunity theory enhances our understanding of how ecological processes regulate community structure. Yet, unraveling the complexities of soil nematode metacommunity structures across various spatial scales and determining the factors influencing these patterns remains challenging. Therefore, we conducted an investigation on soil nematode metacommunities spanning from north to south in the Northeastern China. Our aim was to test whether nematode metacommunities were structured by different drivers under three land covers (i.e., farmland, grassland and woodland) at the local and regional scales. The results revealed that the Clementsian, Gleasonian and their quasi‐structures of soil nematodes collectively accounted for 93% of the variation across the three land covers at the local and regional scales. These structures suggest that the soil nematode metacommunities in the Northeast China responded to fluctuations in environmental gradients. At the local scale, metacommunities were primarily shaped by biological interactions. At the regional scale, environmental heterogeneity, dispersal limitation and biological interactions all contributed to nematode metacommunities. Meanwhile, biological interactions under three land covers were represented within different trophic groups, with plant parasites predominant in farmlands and bacterivores in grasslands and woodlands. In conclusion, the metacommunity structures of soil nematodes remain stable at different spatial scales and land covers. Biological interactions are widespread among nematodes regardless of changes in spatial scales and land covers. This study reveals the importance of nematode sensitivity to the environment and biological interactions in shaping the nematode metacommunities, potentially enhancing our understanding of the spatial patterns of nematode metacommunities.

Ground‐dwelling invertebrates are vital for soil biodiversity and function maintenance. Contemporary biodiversity assessment necessitates novel and automatic monitoring methods because of the threat of sharp reductions in soil biodiversity in farmlands worldwide. Using infrared camera traps (ICTs) is an effective method for assessing richness and abundance of ground‐dwelling invertebrates. However, the influence that the shooting area of ICTs has on the diversity of ground‐dwelling invertebrates has not been strongly considered during survey design. In this study, data from six ICTs with two shooting areas (A1, 38.48 cm²; A2, 400 cm²) were used to investigate ground‐dwelling invertebrates in a farm in a city on the Eastern Coast of China from 20: 00 on July 31 to 00:00 on September 29, 2022. Over the course of 59 days and 1420 h, invertebrates within 9 taxa, 2447 individuals, and 112,909 ind./m² were observed from 222,912 images. Our results show that ICTs with relatively large shooting areas recorded relatively high taxonomic richness and abundance of total ground‐dwelling invertebrates, relatively high abundance of the dominant taxon, and relatively high daily and hourly abundance of most taxa. The shooting areas of ICTs significantly affected the recorded taxonomic richness and abundance of ground‐dwelling invertebrates throughout the experimental period and at fine temporal resolutions. Overall, these results suggest that the shooting areas of ICTs should be considered when designing experiments, and ICTs with relatively large shooting areas are more favorable for monitoring the diversity of ground‐dwelling invertebrates. This study further provides an automatic tool and high‐quality data for biodiversity monitoring and protection in farmlands.