Automated survey of selected common plant species in Thai homegardens using Google Street View imagery and a deep neural network

AbstractMost previous studies of homegardens have used labor-intensive boots-on-the-ground plant surveys, owner questionnaires, and interviews, limiting them to at most a few hundred homegardens. We show that automated analysis of publicly available imagery can enable surveys of much greater scale that can augment these traditional data sources. Specifically, we demonstrate the feasibility of using the high-resolution street-level photographs in Google Street View and an object-detection network (RetinaNet) to create a large-scale high-resolution survey of the prevalence of at least six plant species widely grown in road-facing homegardens in Thailand. Our research team examined 4000 images facing perpendicular to the street and located within 10 m of a homestead, and manually outlined all perceived instances of eleven common plant species. A neural network trained on these tagged images was used to detect instances of these species in approximately 150,000 images constituting views of roughly one in every ten homesteads in five provinces of northern Thailand. The results for six of the plant species were visualized as heatmaps of both the average number of target species detected in each image and individual species prevalence, with spatial averaging performed at scales of 500 m and 2.5 km. Urban-rural contrasts in the average number of target species in each image are quantified, and large variations are observed even among neighboring villages. Spatial heterogeneity is seen to be more pronounced for banana and coconut than for other species. Star gooseberry and papaya are more frequently present immediately outside of towns while dracaena and mango persist into the cores of towns.

Download Full-text

Application of Polypodiopsida Class in Nanotechnology–Potential towards Development of More Effective Bioactive Solutions

Antioxidants ◽

10.3390/antiox10050748 ◽

2021 ◽

Vol 10 (5) ◽

pp. 748

Author(s):

Irina Fierascu ◽

Radu Claudiu Fierascu ◽

Camelia Ungureanu ◽

Oana Alexandra Draghiceanu ◽

Liliana Cristina Soare

Keyword(s):

Health Care ◽

Plant Species ◽

Plant Extracts ◽

Antioxidant Properties ◽

Drug Resistant ◽

Future Perspectives ◽

Real Potential ◽

Toxic Potential ◽

Common Plant ◽

Common Plant Species

The area of phytosynthesized nanomaterials is rapidly developing, with numerous studies being published yearly. The use of plant extracts is an alternative method to reduce the toxic potential of the nanomaterials and the interest in obtaining phytosynthesized nanoparticles is usually directed towards accessible and common plant species, ferns not being explored to their real potential in this field. The developed nanoparticles could benefit from their superior antimicrobial and antioxidant properties (compared with the nanoparticles obtained by other routes), thus proposing an important alternative against health care-associated and drug-resistant infections, as well as in other types of applications. The present review aims to summarize the explored application of ferns in nanotechnology and related areas, as well as the current bottlenecks and future perspectives, as emerging from the literature data.

Download Full-text

Air pollution tolerance, anticipated performance, and metal accumulation capacity of common plant species for green belt development

Environmental Science and Pollution Research ◽

10.1007/s11356-021-17716-8 ◽

2021 ◽

Author(s):

Shilpi Mondal ◽

Gurdeep Singh

Keyword(s):

Air Pollution ◽

Plant Species ◽

Metal Accumulation ◽

Green Belt ◽

Pollution Tolerance ◽

Accumulation Capacity ◽

Common Plant ◽

Common Plant Species

Download Full-text

Large-scale atmospheric forcing and topographic modification of precipitation rates over High Asia – a neural-network-based approach

Earth System Dynamics ◽

10.5194/esd-6-61-2015 ◽

2015 ◽

Vol 6 (1) ◽

pp. 61-81 ◽

Cited By ~ 28

Author(s):

L. Gerlitz ◽

O. Conrad ◽

J. Böhner

Keyword(s):

Neural Network ◽

High Resolution ◽

Spatial Resolution ◽

Large Scale ◽

Local Scale ◽

Predictor Variables ◽

High Mountain ◽

Target Area ◽

Monthly Precipitation ◽

Highly Nonlinear

Abstract. The heterogeneity of precipitation rates in high-mountain regions is not sufficiently captured by state-of-the-art climate reanalysis products due to their limited spatial resolution. Thus there exists a large gap between the available data sets and the demands of climate impact studies. The presented approach aims to generate spatially high resolution precipitation fields for a target area in central Asia, covering the Tibetan Plateau and the adjacent mountain ranges and lowlands. Based on the assumption that observed local-scale precipitation amounts are triggered by varying large-scale atmospheric situations and modified by local-scale topographic characteristics, the statistical downscaling approach estimates local-scale precipitation rates as a function of large-scale atmospheric conditions, derived from the ERA-Interim reanalysis and high-resolution terrain parameters. Since the relationships of the predictor variables with local-scale observations are rather unknown and highly nonlinear, an artificial neural network (ANN) was utilized for the development of adequate transfer functions. Different ANN architectures were evaluated with regard to their predictive performance. The final downscaling model was used for the cellwise estimation of monthly precipitation sums, the number of rainy days and the maximum daily precipitation amount with a spatial resolution of 1 km2. The model was found to sufficiently capture the temporal and spatial variations in precipitation rates in the highly structured target area and allows for a detailed analysis of the precipitation distribution. A concluding sensitivity analysis of the ANN model reveals the effect of the atmospheric and topographic predictor variables on the precipitation estimations in the climatically diverse subregions.

Download Full-text

The most common plant species in temperate Europe based on frequency of occurrences in the national grid mapping projects

Feddes Repertorium ◽

10.1002/fedr.201000013 ◽

2010 ◽

Vol 121 (5-6) ◽

pp. 194-208 ◽

Cited By ~ 2

Author(s):

Alexey P. Seregin

Keyword(s):

Plant Species ◽

Grid Mapping ◽

Temperate Europe ◽

Common Plant ◽

Common Plant Species

Download Full-text

Infection of Melanoplus sanguinipes Grasshoppers following Ingestion of Rangeland Plant Species Harboring Vesicular Stomatitis Virus

Applied and Environmental Microbiology ◽

10.1128/aem.02368-08 ◽

2009 ◽

Vol 75 (10) ◽

pp. 3029-3033 ◽

Cited By ~ 9

Author(s):

Barbara S. Drolet ◽

Melissa A. Stuart ◽

Justin D. Derner

Keyword(s):

Plant Species ◽

Vesicular Stomatitis Virus ◽

Melanoplus Sanguinipes ◽

Northern Plains ◽

Transmission Cycle ◽

Vesicular Stomatitis ◽

The Stability ◽

Common Plant ◽

Plant Surfaces ◽

Common Plant Species

ABSTRACT Knowledge of the many mechanisms of vesicular stomatitis virus (VSV) transmission is critical for understanding of the epidemiology of sporadic disease outbreaks in the western United States. Migratory grasshoppers [Melanoplus sanguinipes (Fabricius)] have been implicated as reservoirs and mechanical vectors of VSV. The grasshopper-cattle-grasshopper transmission cycle is based on the assumptions that (i) virus shed from clinically infected animals would contaminate pasture plants and remain infectious on plant surfaces and (ii) grasshoppers would become infected by eating the virus-contaminated plants. Our objectives were to determine the stability of VSV on common plant species of U.S. Northern Plains rangelands and to assess the potential of these plant species as a source of virus for grasshoppers. Fourteen plant species were exposed to VSV and assayed for infectious virus over time (0 to 24 h). The frequency of viable virus recovery at 24 h postexposure was as high as 73%. The two most common plant species in Northern Plains rangelands (western wheatgrass [Pascopyrum smithii] and needle and thread [Hesperostipa comata]) were fed to groups of grasshoppers. At 3 weeks postfeeding, the grasshopper infection rate was 44 to 50%. Exposure of VSV to a commonly used grasshopper pesticide resulted in complete viral inactivation. This is the first report demonstrating the stability of VSV on rangeland plant surfaces, and it suggests that a significant window of opportunity exists for grasshoppers to ingest VSV from contaminated plants. The use of grasshopper pesticides on pastures would decrease the incidence of a virus-amplifying mechanical vector and might also decontaminate pastures, thereby decreasing the inter- and intraherd spread of VSV.

Download Full-text