Dataset Information

Remotely sensed above-ground storage tank dataset for object detection and infrastructure assessment.

ABSTRACT: Remotely sensed imagery has increased dramatically in quantity and public availability. However, automated, large-scale analysis of such imagery is hindered by a lack of the annotations necessary to train and test machine learning algorithms. In this study, we address this shortcoming with respect to above-ground storage tanks (ASTs) that are used in a wide variety of industries. We annotated available high-resolution, remotely sensed imagery to develop an original, publicly available multi-class dataset of ASTs. This dataset includes geospatial coordinates, border vertices, diameters, and orthorectified imagery for over 130,000 ASTs from five labeled classes (external floating roof tanks, closed roof tanks, spherical pressure tanks, sedimentation tanks, and water towers) across the contiguous United States. This dataset can be used directly or to train machine learning algorithms for large-scale risk and hazard assessment, production and capacity estimation, and infrastructure evaluation.

SUBMITTER: Robinson C

PROVIDER: S-EPMC10786938 | biostudies-literature | 2024 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Remotely sensed above-ground storage tank dataset for object detection and infrastructure assessment.

Robinson Celine C Bradbury Kyle K Borsuk Mark E ME

Scientific data 20240112 1

Remotely sensed imagery has increased dramatically in quantity and public availability. However, automated, large-scale analysis of such imagery is hindered by a lack of the annotations necessary to train and test machine learning algorithms. In this study, we address this shortcoming with respect to above-ground storage tanks (ASTs) that are used in a wide variety of industries. We annotated available high-resolution, remotely sensed imagery to develop an original, publicly available multi-clas ...[more]

PMID: 38216568

Similar Datasets

Project description:Crop phenology is very important in regular crop monitoring. Generally, phenology is monitored through field observation surveys or satellite data. The relationships between ground observations and remotely sensed derived phenological data can enable near-real-time monitoring over large areas, which has never been attempted on hazelnuts. In this study, we extracted phenological metrics derived from MODIS Enhanced Vegetation Index (EVI) in hazelnut production regions and compared them with the spring ground phenological data (BBCH scale) from orchards located in the same area of Turkey over the period from 2019 to 2022. We observed a specific temporal dynamic between remote sensing phenometrics and ground observations. The metrics Greenup, Upturning Date, and Threshold 20% metrics corresponded to the early of EVI growth and were synchronous with the female flowering of hazelnut and ending before bud break. The metrics Threshold 50% and Start of season were associated with the steepest portion of the EVI curve, i.e., canopy greening and thickening, and occurred between ovaries enlargement and leaves unfolding. The metrics Peak of Season, Stabilization Date, and Maturity corresponded to the end of spring vegetative growth. The main outcomes are that (i) female flowering occurred before 20% of vegetation development (BBCH 64P occurred about one month before Threshold 20%), (ii) phenometrics from satellite remote sensing (i.e., Upturning Date and Threshold 20%) well-reflected leaf emergence (rs = 0.30 and rs = 0.32, respectively; p < 0.05) and unfolding (rs = 0.35 and rs = 0.39, respectively; p < 0.05), and (iii) cluster appearance temporally aligned with the peak of the EVI curve (Stabilization Date and BBCH 71P differed by around 4 days). Our method is transferable to operational phenology monitoring, and future applications will consider the senescence season and the effect of environmental variability on the comprehension of vegetation dynamics.

Dataset Information

Remotely sensed above-ground storage tank dataset for object detection and infrastructure assessment.

Publications

Remotely sensed above-ground storage tank dataset for object detection and infrastructure assessment.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets