Rapid visual screening of soft-story buildings from street view images using deep learning classification     

Yu  Qian  Wang  Chaofeng  McKenna  Frank  Yu  Stella X.  Taciroglu  Ertugrul  Cetiner  Barbaros  Law  Kincho H. 《地震工程与工程振动(英文版)》2020,19(4):827-838

Rapid and accurate identification of potential structural deficiencies is a crucial task in evaluating seismic vulnerability of large building inventories in a region. In the case of multi-story structures, abrupt vertical variations of story stiffness are known to significantly increase the likelihood of collapse during moderate or severe earthquakes. Identifying and retrofitting buildings with such irregularities—generally termed as soft-story buildings—is, therefore, vital in earthquake preparedness and loss mitigation efforts. Soft-story building identification through conventional means is a labor-intensive and time-consuming process. In this study, an automated procedure was devised based on deep learning techniques for identifying soft-story buildings from street-view images at a regional scale. A database containing a large number of building images and a semi-automated image labeling approach that effectively annotates new database entries was developed for developing the deep learning model. Extensive computational experiments were carried out to examine the effectiveness of the proposed procedure, and to gain insights into automated soft-story building identification.

  相似文献   

Chemical controls on the solubility, speciation and mobility of lanthanum at near surface conditions: A geochemical modeling study     

Ziya S. Cetiner  Yongliang Xiong   《Applied Geochemistry》2008,23(8):2301-2315

Recent experimental determinations of the solubility products of common rare earth minerals such as monazite and xenotime and stability constants for chloride, sulfate, carbonate and hydroxide complexes provide a basis to model quantitatively the solubility, and therefore the mobility, of rare earth elements (REE) at near surface conditions. Data on the mobility of REE and stabilities of REE complexes at near-neutral conditions are of importance to safe nuclear waste disposal, and environmental monitoring. The aim of this study is to understand REE speciation and solubility of a given REE in natural environments. In this study, a series of formation constants for La aqueous complexes are recommended by using the specific interaction theory (SIT) for extrapolation to infinite dilution. Then, a thermodynamic model has been employed for calculation of the solubility and speciation of La in soil solutions reacted with the La end-member of mineral monazite (LaPO₄), and other La-bearing solid phases including amorphous lanthanum hydroxide (La(OH)₃, am) and different La carbonates, as a function of various inorganic and organic ligand concentrations. Calculations were carried out at near-neutral pH (pH 5.5–8.5) and 25 °C at atmospheric CO₂ partial pressure. The model takes account of the species: La³⁺, LaCl²⁺, , , , , , , , , La(OH)²⁺, LaOx⁺, , LaAc²⁺ and (where Ox²⁻ = oxalate and Ac⁻ = acetate).The calculations indicate that the La species that dominate at pH 5.5–8.5 in the baseline model soil solution (BMSS) include La³⁺, LaOx⁺, , and in order of increasing importance as pH rises. The solubility of monazite in the BMSS remains less than 3 × 10⁻⁹ M, exhibiting a minimum of 2 × 10⁻¹² M at pH 7.5. The calculations quantitatively demonstrate that the concentrations of La controlled by the solubility of other La-bearing solid phases are many orders of magnitude higher than those controlled by monazite in the pH range from 5.5 to 8.5, suggesting that monazite is likely to be the solubility-controlling phase at this pH range. The calculations also suggest that significant mobility of La (and other REE) is unlikely because high water–rock ratios on the order of at least 10⁴ (mass ratio) are required to move 50% of the La from a soil. An increase in concentration of oxalate by one order of magnitude from that of the baseline model solution results in the dominance of LaOx⁺ at pH 5.5–7.5. Similarly, the increase in concentration of by one order of magnitude makes the dominant species at pH 5.5–7.5. Above pH 7.5, carbonate complexes are important. The increase in oxalate or concentrations by one order of magnitude can enhance the solubility of monazite by a factor of up to about 6 below neutral pH, in comparison with that in the baseline model soil solution. From pH 7.0 to 8.5, the solubility of monazite in the soil solutions with higher concentrations of oxalate or is similar, or almost identical, to that in the BMSS.  相似文献