Multi-Scale Attention Network for Building Extraction from High-Resolution Remote Sensing Images.

The precise building extraction from high-resolution remote sensing images holds significant application for urban planning, resource management, and environmental conservation. In recent years, deep neural networks (DNNs) have garnered substantial attention for their adeptness in learning and extracting features, becoming integral to building extraction methodologies and yielding noteworthy performance outcomes. Nonetheless, prevailing DNN-based models for building extraction often overlook spatial information during the feature extraction phase. Additionally, many existing models employ a simplistic and direct approach in the feature fusion stage, potentially leading to spurious target detection and the amplification of internal noise. To address these concerns, we present a multi-scale attention network (MSANet) tailored for building extraction from high-resolution remote sensing images. In our approach, we initially extracted multi-scale building feature information, leveraging the multi-scale channel attention mechanism and multi-scale spatial attention mechanism. Subsequently, we employed adaptive hierarchical weighting processes on the extracted building features. Concurrently, we introduced a gating mechanism to facilitate the effective fusion of multi-scale features. The efficacy of the proposed MSANet was evaluated using the WHU aerial image dataset and the WHU satellite image dataset. The experimental results demonstrate compelling performance metrics, with the F1 scores registering at 93.76% and 77.64% on the WHU aerial imagery dataset and WHU satellite dataset II, respectively. Furthermore, the intersection over union (IoU) values stood at 88.25% and 63.46%, surpassing benchmarks set by DeepLabV3 and GSMC.

(4-Meth-oxy-phen-yl)(4-propyl-cyclo-hex-yl)methanone.

The asymmetric unit of the title compound, C17H24O2, contains two independent mol-ecules with different conformations. The least-squares plane through the cyclohexane ring makes dihedral angles of 52.9 (5) and 81.4 (4)° with the benzene ring in the two molecules. The cyclo-hexane ring adopts a chair conformation in both mol-ecules. In the crystal, weak C-H⋯O hydrogen bonds link mol-ecules related by translation in [100] into two crystallographically independent chains.

(5-Bromo-2-meth-oxy-phen-yl)(4-ethyl-cyclo-hex-yl)methanone.

In the title compound, C(16)H(21)BrO(2), the cyclo-hexane ring is in a chair conformation and its least-squares plane is at an angle of 61.3 (9)° to the benzene ring. The crystal packing is stabilized by weak π-π stacking inter-actions [centroid-centroid distance = 3.697 (9) Å] between the bromo-meth-oxy-phenyl rings of neighbouring mol-ecules.

Abiotic phosphorus recycling from adsorbed ribonucleotides on a ferrihydrite-type mineral: Probing solution and surface species.

Iron (Fe) (oxyhydr)oxide minerals, which are amongst most reactive minerals in soils and sediments, are known to exhibit strong adsorption of inorganic phosphate (Pi) and organophosphate (Po) compounds. Beyond synthetic Po compounds, much still remains unknown about the reactivity of these minerals to transform naturally-occurring Po compounds to Pi, particularly with respect to solution versus surface speciation of Po hydrolysis. To investigate this reactivity with a ferrihydrite-type mineral and ribonucleotides, we employed high-resolution liquid chromatography-mass spectrometry (LC-MS), X-ray absorption near-edge structure (XANES), Fourier-transform infrared (FTIR) spectroscopy, and molecular modeling. Kinetic experiments were conducted with the mineral (1 g L-1) reacted with adenosine monophosphate, diphosphate, or triphosphate (respectively AMP, ADP, ATP; 50 µM). Analysis of solution organic species by LC-MS implied that only adsorption occurred with AMP and ADP but both adsorption and dephosphorylation of ATP were evident. Maximum adsorption capacities per gram of mineral were 40.6 ±â€¯0.8 µmol AMP, 35.7 ±â€¯1.6 µmol ADP, and 10.9 ±â€¯1.0 µmol ATP; solution dephosphorylated by-products accounted for 15% of initial ATP. Subsequent XANES analysis of the surface species revealed that 16% of adsorbed AMP and 30% of adsorbed ATP were subjected to dephosphorylation, which was not fully quantifiable from the solution measurements. Molecular simulations predicted that ADP and ATP were complexed mainly via the phosphate groups whereas AMP binding also involved multiple hydrogen bonds with the adenosine moiety; our FTIR data confirmed these binding confirmations. Our findings thus imply that specific adsorption mechanisms dictate the recycling and subsequent trapping of Pi from ribonucleotide-like biomolecules reacted with Fe (oxyhydr)oxide minerals.