Constarium
← Search

Data · dataset · 2026

Multi-modal dataset of frequently occurring birds in power grid

Listed in ScienceDB

To address the shortage of multimodal data for frequently occurring bird species in the precise prevention and control of bird-related faults in power grids, this study constructed and released a multimodal dataset of frequently occurring birds in power grids.

Description

The dataset focuses on 11 species of concern for power grid bird hazards, including Eurasian Goshawk, Black Stork, Common Crane, Common Kestrel, Eurasian Magpie, Black-winged Kite, Oriental Stork, Large-billed Crow, Carrion Crow, Little Egret, and Upland Buzzard.

It integrates three types of data: bird characteristic data, distribution prediction data, and image annotation data. The bird characteristic data were manually extracted from published literature and books and contain 15 fields, including species name, Latin name, activity rhythm, migration type, food preference, nesting location, habitat characteristics, human-induced flushing distance, noise tolerance, natural enemies, power grid hazard level, prevention and control measures, and references.

Read the rest (2 more)

The distribution prediction data were derived from GBIF occurrence records. MaxEnt and two-dimensional kernel density estimation were used to generate monthly relative activity intensity grids for the Beijing–Tianjin–Hebei region and national habitat suitability maps. The image data were obtained from GBIF.

After two rounds of manual screening and YOLOv8-assisted verification, 83,782 high-quality images were retained from 115,423 original photographs and annotated in YOLO format, yielding 119,276 bounding boxes, including 117,831 bird boxes and 1,445 nest boxes. The dataset is approximately 2 GB in size and includes jpg, tif, and csv formats. It can provide fundamental data support for mechanism analysis of bird-related power grid faults, intelligent bird recognition, bird hazard risk assessment, and differentiated prevention and control.

Links

Where it is published

Catalogue records · 1

Topics

Inferred from text
Bioinformatics and computational biology 71% · Image 75%
Provenance · 1 source records, 12 field assertions
SourceKeyLast seenRaw
ScienceDB10.57760/sciencedb.zoology.0000f9 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · scidb cnconnector:scidb_cn@1.0.0
concepts[field].anzsrc:group:3102enrichment · scidb cntaxonomy-embedding@1.0.0title+keywords+description (71%)
concepts[field].local:field:earth-environmentalmapping · scidb cnconnector:scidb_cn@1.0.0
concepts[field].local:field:engineeringmapping · scidb cnconnector:scidb_cn@1.0.0
concepts[field].local:field:humanitiesmapping · scidb cnconnector:scidb_cn@1.0.0
concepts[field].local:field:life-sciencesmapping · scidb cnconnector:scidb_cn@1.0.0
concepts[field].local:field:social-sciencemapping · scidb cnconnector:scidb_cn@1.0.0
concepts[modality].local:modality:imageenrichment · scidb cnkeyword-concept-rules@1.0.0title+description (75%)
descriptionsource · scidb cnconnector:scidb_cn@1.0.0/metadata/dc/description
licensesource · scidb cnconnector:scidb_cn@1.0.0/metadata/dc/rights
publication_datesource · scidb cnconnector:scidb_cn@1.0.0
titlesource · scidb cnconnector:scidb_cn@1.0.0/metadata/dc/title