Using Machine Learning Methods Combined with Vegetation Indices and Growth Indicators to Predict Seed Yield of Bromus inermis

Smooth bromegrass (Bromus inermis) is a perennial, high-quality forage grass. However, its seed yield is influenced by agronomic practices, climatic conditions, and the growing year. The rapid and effective prediction of seed yield can assist growers in making informed production decisions and reducing agricultural risks. Our field trial design followed a completely randomized block design with four blocks and three nitrogen levels (0, 100, and 200 kg·N·ha-1) during 2022 and 2023. Data on the remote vegetation index (RVI), the normalized difference vegetation index (NDVI), the leaf nitrogen content (LNC), and the leaf area index (LAI) were collected at heading, anthesis, and milk stages. Multiple linear regression (MLR), support vector machine (SVM), and random forest (RF) regression models were utilized to predict seed yield. In 2022, the results indicated that nitrogen application provided a sufficiently large range of variation of seed yield (ranging from 45.79 to 379.45 kg ha⁻¹). Correlation analysis showed that the indices of the RVI, the NDVI, the LNC, and the LAI in 2022 presented significant positive correlation with seed yield, and the highest correlation coefficient was observed at the heading stage. The data from 2022 were utilized to formulate a predictive model for seed yield. The results suggested that utilizing data from the heading stage produced the best prediction performance. SVM and RF outperformed MLR in prediction, with RF demonstrating the highest performance (R2 = 0.75, RMSE = 51.93 kg ha-1, MAE = 29.43 kg ha-1, and MAPE = 0.17). Notably, the accuracy of predicting seed yield for the year 2023 using this model had decreased. Feature importance analysis of the RF model revealed that LNC was a crucial indicator for predicting smooth bromegrass seed yield. Further studies with an expanded dataset and integration of weather data are needed to improve the accuracy and generalizability of the model and adaptability for the growing year.

Impacts and Drivers of Smooth Brome (Bromus inermis Leyss.) Invasion in Native Ecosystems

Smooth brome (Bromus inermis Leyss.) is an invasive cool-season grass that has spread throughout the Great Plains of North America. The species is considered one of the most widespread exotic grasses that has successfully invaded both cool-season and warm-season native prairies. In the prairies where it has invaded, there has often been a total elimination of native species and an overall homogenization of ecosystems. Smooth brome has greater competitive abilities compared to many native grasses and can foster their total elimination in many instances. The greater competitiveness can be partially attributed to its ability to alter the soil and hydrological properties of a site. It is a deep-rooted rhizomatous grass species that thrives in nitrogen-enriched soil, and since its leaf tissue decomposes faster than native species, it in turn increases the soil nitrogen level, causing positive plant-soil feedback. Moreover, smooth brome is able to transport the required nutrients from older plants to the newer progenies invading new nutrient-depleted areas, making it a potent invader. However, the impact of smooth brome is not limited to soil biochemistry alone; it also affects other ecosystem components such as the movement and behavior of many native arthropods, thereby altering the overall population dynamics of such species. Thus, smooth brome invasion poses a serious threat to the remnant prairies of the Great Plains, and efficient management strategies are urgently needed to control its invasion. Control measures such as mowing, grazing, burning, and herbicide application have been effectively used to manage this species. However, due to the widespread distribution of smooth brome across North America and its adaptability to a wide range of environmental conditions, it is challenging to translate the management strategies from one area to another.

A global inventory of animal diversity measured in different grazing treatments

Grazing by wild and domesticated grazers occurs within many terrestrial ecosystems worldwide, with positive and negative impacts on biodiversity. Management of grazed lands in support of biological conservation could benefit from a compiled dataset of animal biodiversity within and adjacent to grazed sites. In this database, we have assembled data from the peer-reviewed literature that included all forms of grazing, co-occurring species, and site information. We reviewed 3,489 published articles and found 245 studies in 41 countries that surveyed animal biodiversity co-occurring with grazers. We extracted 16,105 observations of animal surveys for over 1,200 species in all terrestrial ecosystems and on all continents except Antarctica. We then compiled 28 different grazing variables that focus on management systems, assemblages of grazer species, ecosystem characteristics, and survey type. Our database provides the most comprehensive summary of animal biodiversity patterns that co-occur with wild and domesticated grazers. This database could be used in future conservation initiatives and grazing management to enhance the prolonged maintenance of ecosystems and ecosystem services.

Measurement(s)	Kingdom • Phylum • Class • Order • Taxon • Family • Genus • Species • Year of observation • Survey time period • Grazing estimate • Grazing species • Grazer domestication • Last grazing event • Latitude • Longitude • Elevation • Country • Number of sites • Survey technique • Survey type • Presence of wild grazers • Presence of domesticated grazers • Plant community • Ecosystem class • Fence presence • Tilled status • Herbivores present • Fertilization • Fire history • Land ownership • Year of study initiation • Year of study finished
Technology Type(s)	Data extraction
Sample Characteristic - Organism	Vertebrate • Invertebrate • Plants • Fungi
Sample Characteristic - Environment	Grassland ecosystem • Forest ecosystem • Shrubland ecosystem • Wetland ecosystem • Desert ecosystem • Tundra ecosystem • Coastal ecosystem
Sample Characteristic - Location	Argentina • Australia • Austria • Canada • China • Kingdom of Denmark • England • Ethiopia • Finland • French Republic • Germany • Hong Kong • Hungary • India • Iran • Ireland • Israel • Italy • Kazakhstan • Kenya • Lesotho • Mongolia • Kingdom of the Netherlands • New Zealand • Kingdom of Norway • Poland • Portuguese Republic • Romania • Scotland • Senegal • Republic of South Africa • Kingdom of Spain • Sweden • Switzerland • Tanzania • Tunisia • Uganda • United Kingdom • United States of America

Marker-trait association analysis for drought tolerance in smooth bromegrass

BACKGROUND

Little information is available on the application of marker-trait association (MTA) analysis for traits related to drought tolerance in smooth bromegrass. The objectives of this study were to identify marker loci associated with important agronomic traits and drought tolerance indices as well as fining stable associations in a diverse panel of polycross derived genotypes of smooth bromegrass. Phenotypic evaluations were performed at two irrigation regimes (normal and deficit irrigation) during 2 years; and association analysis was done with 626 SRAP markers.

RESULTS

The results of population structure analysis identified three main subpopulations possessing significant genetic differences. Under normal irrigation, 68 and 57 marker-trait associations were identified using general linear model (GLM) and mixed linear mode1 (MLM), respectively. While under deficit irrigation, 61 and 54 markers were associated with the genes controlling the studied traits, based on these two models, respectively. Some of the markers were associated with more than one trait. It was revealed that markers Me1/Em5-11, Me1/Em3-15, and Me5/Em4-7 were consistently linked with drought-tolerance indices.

CONCLUSION

Following marker validation, the MTAs reported in this panel could be useful tools to initiate marker-assisted selection (MAS) and targeted trait introgression of smooth bromegrass under normal and deficit irrigation regimes, and possibly fine mapping and cloning of the underlying genes and QTLs.

A survey of invasive plants on grassland soil microbial communities and ecosystem services

Invasive plants can cause changes in the structure and function of the ecosystem being invaded. Any changes in ecosystem diversity and community composition will likely alter ecosystem services provided by that ecosystem. However, how these ecosystem services may change is poorly understood. To elucidate how these ecosystem services will change with invasion, we sampled 561 plots undergoing invasion by smooth brome (Bromus inermis) and four other invasive species at a native Rough Fescue prairie located near Saskatoon, Saskatchewan, Canada. Soil and plant surveys were undertaken weekly for 26 weeks between May of 2014 and November of 2014, or the growing season. We measured a suite of ecosystem services, including greenhouse gasses, extracellular enzyme function, forage production, glyphosate degradation and decomposition. Furthermore, soil physical and chemical properties were measured, and soil bacterial and fungal communities were sequenced. This is a large and multifaceted dataset with complex temporal and spatial attributes which can be used to answer numerous questions regarding the functioning of prairie ecosystems and how invasive species will impact that functioning.

Measurement(s)	invasive species • native species • ecosystem decay • greenhouse gas • DNA
Technology Type(s)	Survey • monitoring device • DNA sequencing
Factor Type(s)	geographic location • sampling date
Sample Characteristic - Environment	prairie • soil
Sample Characteristic - Location	Saskatoon

Machine-accessible metadata file describing the reported data: 10.6084/m9.figshare.11898213